diff --git "a/Sai0.ipynb" "b/Sai0.ipynb"
new file mode 100644--- /dev/null
+++ "b/Sai0.ipynb"
@@ -0,0 +1 @@
+{"cells":[{"cell_type":"code","execution_count":4,"metadata":{"id":"aJNUebYedYuQ","executionInfo":{"status":"ok","timestamp":1760100264462,"user_tz":-330,"elapsed":183,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["import os"]},{"cell_type":"code","source":["import os, time, torch\n","from transformers import AutoModelForSequenceClassification, AutoTokenizer\n","\n","class AutomaticAI:\n","    def __init__(self, name=\"Venomoussaversai\"):\n","        self.name = name\n","        self.model_name = \"distilbert-base-uncased\"\n","        self.tokenizer = AutoTokenizer.from_pretrained(self.model_name)\n","        self.model = AutoModelForSequenceClassification.from_pretrained(self.model_name, num_labels=2)\n","        self.data_folder = \"/content/drive/MyDrive/Venomoussaversai/data\"\n","        self.model_folder = \"/content/drive/MyDrive/Venomoussaversai/auto_model\"\n","        os.makedirs(self.model_folder, exist_ok=True)\n","\n","    def auto_detect_new_data(self):\n","        \"\"\"Check Drive folder for new training data files\"\"\"\n","        files = [f for f in os.listdir(self.data_folder) if f.endswith(\".txt\")]\n","        return files\n","\n","    def auto_train(self, files):\n","        \"\"\"Pseudo-train on detected data\"\"\"\n","        print(f\"🧩 {self.name}: Training started on {len(files)} new files...\")\n","        time.sleep(2)\n","        torch.save(self.model.state_dict(), os.path.join(self.model_folder, \"latest_model.pt\"))\n","        print(\"✅ Training complete — model saved.\")\n","\n","    def auto_loop(self):\n","        \"\"\"Main continuous automation loop\"\"\"\n","        while True:\n","            new_data = self.auto_detect_new_data()\n","            if new_data:\n","                self.auto_train(new_data)\n","            else:\n","                print(\"💤 No new data found. Monitoring...\")\n","            time.sleep(60)  # Check every minute\n","\n","# Example usage\n","ai = AutomaticAI()\n","ai.auto_loop()  # continuously monitors, trains, and updates itself"],"metadata":{"id":"FQROo9lBS9Zh","executionInfo":{"status":"ok","timestamp":1760100264495,"user_tz":-330,"elapsed":19,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"execution_count":4,"outputs":[]},{"cell_type":"code","execution_count":null,"metadata":{"id":"dlor1l4qDp40"},"outputs":[],"source":["import os, time, torch\n","from transformers import AutoModelForSequenceClassification, AutoTokenizer\n","\n","class AutomaticAI:\n","    def __init__(self, name=\"Venomoussaversai\"):\n","        self.name = name\n","        self.model_name = \"distilbert-base-uncased\"\n","        self.tokenizer = AutoTokenizer.from_pretrained(self.model_name)\n","        self.model = AutoModelForSequenceClassification.from_pretrained(self.model_name, num_labels=2)\n","        self.data_folder = \"/content/drive/MyDrive/Venomoussaversai/data\"\n","        self.model_folder = \"/content/drive/MyDrive/Venomoussaversai/auto_model\"\n","        os.makedirs(self.model_folder, exist_ok=True)\n","\n","    def auto_detect_new_data(self):\n","        \"\"\"Check Drive folder for new training data files\"\"\"\n","        files = [f for f in os.listdir(self.data_folder) if f.endswith(\".txt\")]\n","        return files\n","\n","    def auto_train(self, files):\n","        \"\"\"Pseudo-train on detected data\"\"\"\n","        print(f\"🧩 {self.name}: Training started on {len(files)} new files...\")\n","        time.sleep(2)\n","        torch.save(self.model.state_dict(), os.path.join(self.model_folder, \"latest_model.pt\"))\n","        print(\"✅ Training complete — model saved.\")\n","\n","    def auto_loop(self):\n","        \"\"\"Main continuous automation loop\"\"\"\n","        while True:\n","            new_data = self.auto_detect_new_data()\n","            if new_data:\n","                self.auto_train(new_data)\n","            else:\n","                print(\"💤 No new data found. Monitoring...\")\n","            time.sleep(60)  # Check every minute\n","\n","# Example usage\n","ai = AutomaticAI()\n","ai.auto_loop()  # continuously monitors, trains, and updates itself!git clone https://github.com/edoardottt/awesome-hacker-search-engines.git"]},{"cell_type":"code","execution_count":6,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"T3_gLEUIED4f","executionInfo":{"status":"ok","timestamp":1760100269065,"user_tz":-330,"elapsed":3858,"user":{"displayName":"temptations","userId":"17031846462411147691"}},"outputId":"b4d2c3a1-6206-4906-e4c3-81784255aa9c"},"outputs":[{"output_type":"stream","name":"stdout","text":["Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n","[INFO] AI files will be saved in: /content/drive/MyDrive/Ananthu_Sajeev_AIFiles\n","[ERROR] GitHub clone path not found: /content/github_repos. Please update the GITHUB_CLONE_BASE_PATH variable.\n","\n","🔥 All files from cloned GitHub repositories automatically saved as .ai files.\n"]}],"source":["from google.colab import drive\n","import os\n","import shutil\n","\n","# 1️⃣ Mount Google Drive\n","drive.mount('/content/drive')\n","\n","# 2️⃣ Define the destination folder in Google Drive\n","DRIVE_SAVE_PATH = \"/content/drive/MyDrive/Ananthu_Sajeev_AIFiles\"\n","os.makedirs(DRIVE_SAVE_PATH, exist_ok=True)\n","print(f\"[INFO] AI files will be saved in: {DRIVE_SAVE_PATH}\")\n","\n","# 3️⃣ Define the base directory where repositories were cloned\n","# This assumes the repos were cloned into a directory like '/content/github_repos'\n","# If you cloned them elsewhere, update this path.\n","GITHUB_CLONE_BASE_PATH = \"/content/github_repos\"\n","\n","# 4️⃣ Function to find all files in a directory and save them with a .ai extension\n","def save_files_as_ai(source_folder, dest_folder):\n","    for root, _, files in os.walk(source_folder):\n","        for file in files:\n","            file_path = os.path.join(root, file)\n","            # Create a relative path to maintain directory structure\n","            relative_path = os.path.relpath(file_path, source_folder)\n","            # Create the corresponding directory structure in the destination\n","            dest_dir = os.path.join(dest_folder, os.path.dirname(relative_path))\n","            os.makedirs(dest_dir, exist_ok=True)\n","\n","            # Define the new file name with .ai extension\n","            file_name, _ = os.path.splitext(os.path.basename(file_path))\n","            new_file_name = f\"{file_name}.ai\"\n","            new_file_path = os.path.join(dest_dir, new_file_name)\n","\n","            try:\n","                # Copy the content to the new file with .ai extension\n","                shutil.copy2(file_path, new_file_path)\n","                print(f\"✅ Saved: {file_path} → {new_file_path}\")\n","            except Exception as e:\n","                print(f\"❌ Failed to save {file_path} as .ai: {e}\")\n","\n","# 5️⃣ Find all cloned repos and save their files as .ai\n","if os.path.exists(GITHUB_CLONE_BASE_PATH):\n","    for repo_name in os.listdir(GITHUB_CLONE_BASE_PATH):\n","        repo_path = os.path.join(GITHUB_CLONE_BASE_PATH, repo_name)\n","        if os.path.isdir(repo_path):\n","            print(f\"\\n[INFO] Processing repository: {repo_name}\")\n","            save_files_as_ai(repo_path, os.path.join(DRIVE_SAVE_PATH, repo_name))\n","else:\n","    print(f\"[ERROR] GitHub clone path not found: {GITHUB_CLONE_BASE_PATH}. Please update the GITHUB_CLONE_BASE_PATH variable.\")\n","\n","print(\"\\n🔥 All files from cloned GitHub repositories automatically saved as .ai files.\")"]},{"cell_type":"code","source":[],"metadata":{"id":"iKau-6HsTaFL","executionInfo":{"status":"ok","timestamp":1760100269094,"user_tz":-330,"elapsed":21,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"execution_count":6,"outputs":[]},{"cell_type":"code","source":["!git clone https://github.com/edoardottt/awesome-hacker-search-engines.git"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"iy9QHJZZTaXb","executionInfo":{"status":"ok","timestamp":1760100269587,"user_tz":-330,"elapsed":479,"user":{"displayName":"temptations","userId":"17031846462411147691"}},"outputId":"0f02d287-e9e8-4c03-8985-36c93c0b1f60"},"execution_count":7,"outputs":[{"output_type":"stream","name":"stdout","text":["fatal: destination path 'awesome-hacker-search-engines' already exists and is not an empty directory.\n"]}]},{"cell_type":"code","source":["# STEP 1: Mount Google Drive\n","from google.colab import drive\n","drive.mount('/content/drive')\n","\n","# STEP 2: Install Git (if needed)\n","!apt-get install git -y\n","\n","# STEP 3: Clone all GitHub repositories you want\n","# Replace these URLs with your own repos\n","!git clone https://github.com/yourusername/repo1.git\n","!git clone https://github.com/yourusername/repo2.git\n","\n","# STEP 4: Copy all cloned files into a folder on Google Drive\n","import shutil, os\n","\n","# Create destination folder on Drive\n","dest_path = '/content/drive/MyDrive/GitHub_Backups'\n","os.makedirs(dest_path, exist_ok=True)\n","\n","# Copy all cloned repos\n","for repo in os.listdir('/content'):\n","    repo_path = os.path.join('/content', repo)\n","    if os.path.isdir(repo_path) and repo not in ['drive', 'sample_data']:\n","        shutil.copytree(repo_path, os.path.join(dest_path, repo), dirs_exist_ok=True)\n","\n","print(\"✅ All GitHub files saved to Google Drive successfully!\")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"PAKhILlxTm-Y","executionInfo":{"status":"ok","timestamp":1760100319603,"user_tz":-330,"elapsed":50009,"user":{"displayName":"temptations","userId":"17031846462411147691"}},"outputId":"4565b5a0-231c-45c0-ff39-0803ffa67757"},"execution_count":8,"outputs":[{"output_type":"stream","name":"stdout","text":["Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n","Reading package lists... Done\n","Building dependency tree... Done\n","Reading state information... Done\n","git is already the newest version (1:2.34.1-1ubuntu1.15).\n","0 upgraded, 0 newly installed, 0 to remove and 38 not upgraded.\n","Cloning into 'repo1'...\n","fatal: could not read Username for 'https://github.com': No such device or address\n","Cloning into 'repo2'...\n","fatal: could not read Username for 'https://github.com': No such device or address\n","✅ All GitHub files saved to Google Drive successfully!\n"]}]},{"cell_type":"code","execution_count":9,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":3768,"status":"ok","timestamp":1760100323439,"user":{"displayName":"temptations","userId":"17031846462411147691"},"user_tz":-330},"id":"2QdjVr1E6-dZ","outputId":"88e5e020-2b3c-4c31-edef-6d625e925796"},"outputs":[{"output_type":"stream","name":"stdout","text":["Cloning into 'nsfw-filter'...\n","remote: Enumerating objects: 1895, done.\u001b[K\n","remote: Counting objects: 100% (285/285), done.\u001b[K\n","remote: Compressing objects: 100% (80/80), done.\u001b[K\n","remote: Total 1895 (delta 231), reused 205 (delta 205), pack-reused 1610 (from 1)\u001b[K\n","Receiving objects: 100% (1895/1895), 49.91 MiB | 22.94 MiB/s, done.\n","Resolving deltas: 100% (900/900), done.\n"]}],"source":["!git clone  https://github.com/nsfw-filter/nsfw-filter.git"]},{"cell_type":"code","source":["import nbformat, glob\n","from nbconvert import PythonExporter\n","\n","for nb_file in glob.glob('/content/**/*.ipynb', recursive=True):\n","    with open(nb_file) as f:\n","        nb = nbformat.read(f, as_version=4)\n","    py_code, _ = PythonExporter().from_notebook_node(nb)\n","    py_file = nb_file.replace('.ipynb', '.py')\n","    with open(py_file, 'w') as f:\n","        f.write(py_code)"],"metadata":{"id":"7jBeV1R_Ua9s","executionInfo":{"status":"ok","timestamp":1760100355106,"user_tz":-330,"elapsed":31658,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"execution_count":10,"outputs":[]},{"cell_type":"code","execution_count":null,"metadata":{"id":"IRtMenR1929m","executionInfo":{"status":"aborted","timestamp":1760100358687,"user_tz":-330,"elapsed":97005,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ==============================\n","# NSFW DETECTION & SAVE SCRIPT (Debug-Friendly)\n","# ==============================\n","\n","!pip install --quiet transformers pillow tqdm pandas\n","\n","from google.colab import drive\n","drive.mount('/content/drive')\n","\n","import os\n","import shutil\n","import json\n","import time\n","from pathlib import Path\n","from PIL import Image, UnidentifiedImageError\n","from tqdm import tqdm\n","import pandas as pd\n","from transformers import pipeline\n","\n","# --- Configuration ---\n","DRIVE_ROOT = '/content/drive/MyDrive'   # Root folder to scan\n","IMAGE_EXTS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}\n","OUTPUT_DIR = os.path.join(DRIVE_ROOT, 'NSFW_Detection_Results')\n","FLAGGED_DIR = os.path.join(OUTPUT_DIR, 'NSFW_Flags')\n","REPORT_JSON = os.path.join(OUTPUT_DIR, 'nsfw_report.json')\n","REPORT_CSV = os.path.join(OUTPUT_DIR, 'nsfw_report.csv')\n","NSFW_THRESHOLD = 0.5   # Threshold for flagging\n","\n","os.makedirs(OUTPUT_DIR, exist_ok=True)\n","os.makedirs(FLAGGED_DIR, exist_ok=True)\n","\n","# --- Load NSFW classifier ---\n","print(\"Loading classifier...\")\n","cls = pipeline(\"image-classification\", model=\"Falconsai/nsfw_image_detection\")\n","print(\"Classifier loaded.\")\n","\n","# --- Gather image paths ---\n","print(\"Scanning for images...\")\n","image_paths = []\n","for root, dirs, files in os.walk(DRIVE_ROOT):\n","    for fname in files:\n","        ext = Path(fname).suffix.lower()\n","        if ext in IMAGE_EXTS:\n","            image_paths.append(os.path.join(root, fname))\n","print(f\"Found {len(image_paths)} image(s).\")\n","\n","# --- Process images ---\n","results = []\n","errors = []\n","\n","for img_path in tqdm(image_paths, desc=\"Processing\"):\n","    rec = {\n","        \"path\": img_path,\n","        \"nsfw_score\": None,\n","        \"label\": None,\n","        \"model_output\": None,\n","        \"error\": None,\n","        \"timestamp\": int(time.time())\n","    }\n","    try:\n","        # Try opening image\n","        with Image.open(img_path) as img:\n","            img = img.convert(\"RGB\")\n","\n","        # Run inference\n","        out = cls(img)\n","        rec[\"model_output\"] = out\n","\n","        # The output is usually something like [{\"label\": \"nsfw\", \"score\": 0.95}, {\"label\":\"normal\",\"score\":0.05}]\n","        # Extract nsfw_score\n","        nsfw_score = 0.0\n","        for item in out:\n","            lbl = item.get('label', '').lower()\n","            sc = float(item.get('score', 0.0))\n","            if lbl == 'nsfw':\n","                nsfw_score = sc\n","                break  # take the first 'nsfw' label if found\n","\n","        rec[\"nsfw_score\"] = nsfw_score\n","        rec[\"label\"] = \"NSFW\" if nsfw_score >= NSFW_THRESHOLD else \"SFW\"\n","\n","        if rec[\"label\"] == \"NSFW\":\n","            # Copy flagged image\n","            rel = os.path.relpath(img_path, DRIVE_ROOT)\n","            # Replace os.sep because nested dirs may cause path problems\n","            safe_rel = rel.replace(os.sep, \"_\")\n","            dest_path = os.path.join(FLAGGED_DIR, safe_rel)\n","            os.makedirs(os.path.dirname(dest_path), exist_ok=True)\n","            shutil.copy2(img_path, dest_path)\n","\n","    except UnidentifiedImageError:\n","        rec[\"error\"] = \"Cannot identify image / unsupported format\"\n","        errors.append(rec)\n","    except Exception as e:\n","        rec[\"error\"] = str(e)\n","        errors.append(rec)\n","\n","    results.append(rec)\n","\n","# --- Save reports ---\n","print(\"Saving reports...\")\n","\n","with open(REPORT_JSON, 'w', encoding='utf-8') as jf:\n","    json.dump({\n","        \"meta\": {\n","            \"scanned\": len(image_paths),\n","            \"timestamp\": int(time.time())\n","        },\n","        \"results\": results,\n","        \"errors\": errors\n","    }, jf, indent=2)\n","\n","df = pd.DataFrame([{\"path\": r[\"path\"], \"nsfw_score\": r[\"nsfw_score\"], \"label\": r[\"label\"]} for r in results])\n","df.to_csv(REPORT_CSV, index=False)\n","\n","print(\"Done.\")\n","print(\"JSON report:\", REPORT_JSON)\n","print(\"CSV report:\", REPORT_CSV)\n","print(\"Flagged images directory:\", FLAGGED_DIR)\n","print(f\"Total scanned: {len(image_paths)}  Flagged as NSFW: {sum(1 for r in results if r['label']=='NSFW')}\")\n","print(f\"Errors: {len(errors)}\")"]},{"cell_type":"code","source":["!git clone https://github.com/GAIR-NLP/cognition-engineering.git"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"4wf57VO1KKqw","executionInfo":{"status":"ok","timestamp":1760100429447,"user_tz":-330,"elapsed":3533,"user":{"displayName":"temptations","userId":"17031846462411147691"}},"outputId":"83f84224-f84c-4dc7-8256-9997670d9f8e"},"execution_count":13,"outputs":[{"output_type":"stream","name":"stdout","text":["Cloning into 'cognition-engineering'...\n","remote: Enumerating objects: 368, done.\u001b[K\n","remote: Counting objects: 100% (368/368), done.\u001b[K\n","remote: Compressing objects: 100% (266/266), done.\u001b[K\n","remote: Total 368 (delta 104), reused 330 (delta 89), pack-reused 0 (from 0)\u001b[K\n","Receiving objects: 100% (368/368), 18.64 MiB | 19.73 MiB/s, done.\n","Resolving deltas: 100% (104/104), done.\n"]}]},{"cell_type":"code","source":["!git clone https://github.com/CognitionAI/metabase-mcp-server.git"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"rsSmDeCiKaZ0","executionInfo":{"status":"ok","timestamp":1760100471744,"user_tz":-330,"elapsed":2118,"user":{"displayName":"temptations","userId":"17031846462411147691"}},"outputId":"5fa55916-0525-427b-cb23-bb595bb10581"},"execution_count":14,"outputs":[{"output_type":"stream","name":"stdout","text":["Cloning into 'metabase-mcp-server'...\n","remote: Enumerating objects: 273, done.\u001b[K\n","remote: Counting objects: 100% (44/44), done.\u001b[K\n","remote: Compressing objects: 100% (41/41), done.\u001b[K\n","remote: Total 273 (delta 9), reused 8 (delta 3), pack-reused 229 (from 1)\u001b[K\n","Receiving objects: 100% (273/273), 181.94 KiB | 1.93 MiB/s, done.\n","Resolving deltas: 100% (152/152), done.\n"]}]},{"cell_type":"code","source":["!git clone https://github.com/beyretb/AnimalAI-Olympics.git"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"oVBvMK0FKlQd","executionInfo":{"status":"ok","timestamp":1760100526999,"user_tz":-330,"elapsed":5835,"user":{"displayName":"temptations","userId":"17031846462411147691"}},"outputId":"3ad4aff0-61db-425c-e060-03f4a6c16649"},"execution_count":15,"outputs":[{"output_type":"stream","name":"stdout","text":["Cloning into 'AnimalAI-Olympics'...\n","remote: Enumerating objects: 3379, done.\u001b[K\n","remote: Counting objects: 100% (3/3), done.\u001b[K\n","remote: Compressing objects: 100% (3/3), done.\u001b[K\n","remote: Total 3379 (delta 0), reused 0 (delta 0), pack-reused 3376 (from 1)\u001b[K\n","Receiving objects: 100% (3379/3379), 82.08 MiB | 22.97 MiB/s, done.\n","Resolving deltas: 100% (2672/2672), done.\n"]}]},{"cell_type":"code","source":["import os\n","\n","# ⚙️ Replace with your GitHub username\n","github_username = \"YourGitHubUsername\"\n","drive_path = \"/content/drive/MyDrive/GitHub_Files\"\n","\n","os.makedirs(drive_path, exist_ok=True)\n","os.chdir(drive_path)\n","\n","# ✅ Example: clone specific repositories\n","!git clone https://github.com/{github_username}/awesome-web-hacking.git\n","!git clone https://github.com/{github_username}/AI-in-missile-tech.git\n","!git clone https://github.com/{github_username}/Flowise.git"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"j0Vcm8s9K4nT","executionInfo":{"status":"ok","timestamp":1760100601679,"user_tz":-330,"elapsed":2922,"user":{"displayName":"temptations","userId":"17031846462411147691"}},"outputId":"2f073a7a-6535-45d1-bae2-ae4416534c81"},"execution_count":16,"outputs":[{"output_type":"stream","name":"stdout","text":["Cloning into 'awesome-web-hacking'...\n","fatal: could not read Username for 'https://github.com': No such device or address\n","Cloning into 'AI-in-missile-tech'...\n","fatal: could not read Username for 'https://github.com': No such device or address\n","Cloning into 'Flowise'...\n","fatal: could not read Username for 'https://github.com': No such device or address\n"]}]},{"cell_type":"code","source":["import requests, subprocess\n","\n","username = \"YourGitHubUsername\"\n","repos = requests.get(f\"https://api.github.com/users/{username}/repos\").json()\n","\n","for repo in repos:\n","    url = repo[\"clone_url\"]\n","    print(f\"Cloning {url} ...\")\n","    subprocess.run([\"git\", \"clone\", url])"],"metadata":{"id":"QSnvByp6LCWD","executionInfo":{"status":"ok","timestamp":1760100633522,"user_tz":-330,"elapsed":556,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"execution_count":17,"outputs":[]},{"cell_type":"code","source":[],"metadata":{"id":"uc9mqzXxKl05"},"execution_count":null,"outputs":[]},{"cell_type":"code","execution_count":18,"metadata":{"id":"t0thbK3KrDQ9","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1760100696326,"user_tz":-330,"elapsed":27811,"user":{"displayName":"temptations","userId":"17031846462411147691"}},"outputId":"0b21bbb8-6e89-4651-cc1f-46451c1fd9db"},"outputs":[{"output_type":"stream","name":"stdout","text":["Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n","Cloning into 'your-repo'...\n","fatal: could not read Username for 'https://github.com': No such device or address\n","[Errno 2] No such file or directory: 'your-repo'\n","/content\n","\u001b[31mERROR: Could not open requirements file: [Errno 2] No such file or directory: 'requirements.txt'\u001b[0m\u001b[31m\n","\u001b[0mNo requirements.txt found, skipping...\n","Epoch 1/10, Loss: 9.0231\n","Epoch 2/10, Loss: 8.9949\n","Epoch 3/10, Loss: 8.9860\n","Epoch 4/10, Loss: 8.9884\n","Epoch 5/10, Loss: 8.9638\n","Epoch 6/10, Loss: 8.9659\n","Epoch 7/10, Loss: 8.9633\n","Epoch 8/10, Loss: 8.9470\n","Epoch 9/10, Loss: 8.9403\n","Epoch 10/10, Loss: 8.9215\n","✅ Model saved to: /content/drive/MyDrive/venomoussaversai_model.pth\n"]}],"source":["# ==============================\n","# 🔥 VENOMOUSSAVERSAI AI CREATION TEMPLATE\n","# Works in Google Colab\n","# ==============================\n","\n","# 1️⃣ Mount Google Drive\n","from google.colab import drive\n","drive.mount('/content/drive')\n","\n","# 2️⃣ Clone your GitHub repo\n","# Replace the URL with your actual repo\n","!git clone https://github.com/yourusername/your-repo.git\n","%cd your-repo\n","\n","# 3️⃣ Install dependencies\n","!pip install -r requirements.txt || echo \"No requirements.txt found, skipping...\"\n","\n","# 4️⃣ Import main libraries\n","import os\n","import torch\n","from torch import nn, optim\n","from torch.utils.data import DataLoader, Dataset\n","from sklearn.model_selection import train_test_split\n","\n","# 5️⃣ Example Dataset Loader (edit this for your data)\n","class SimpleDataset(Dataset):\n","    def __init__(self, data, labels):\n","        self.data = data\n","        self.labels = labels\n","    def __len__(self):\n","        return len(self.data)\n","    def __getitem__(self, idx):\n","        return torch.tensor(self.data[idx], dtype=torch.float32), torch.tensor(self.labels[idx], dtype=torch.float32)\n","\n","# Example fake data\n","import numpy as np\n","X = np.random.rand(500, 10)\n","y = np.random.randint(0, 2, size=(500, 1))\n","\n","# Split into train/test\n","X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)\n","\n","train_loader = DataLoader(SimpleDataset(X_train, y_train), batch_size=32, shuffle=True)\n","test_loader = DataLoader(SimpleDataset(X_test, y_test), batch_size=32)\n","\n","# 6️⃣ Define your AI Model (Neural Net)\n","class VenomoussaversaiAI(nn.Module):\n","    def __init__(self):\n","        super(VenomoussaversaiAI, self).__init__()\n","        self.net = nn.Sequential(\n","            nn.Linear(10, 64),\n","            nn.ReLU(),\n","            nn.Linear(64, 32),\n","            nn.ReLU(),\n","            nn.Linear(32, 1),\n","            nn.Sigmoid()\n","        )\n","    def forward(self, x):\n","        return self.net(x)\n","\n","model = VenomoussaversaiAI()\n","criterion = nn.BCELoss()\n","optimizer = optim.Adam(model.parameters(), lr=0.001)\n","\n","# 7️⃣ Train AI\n","epochs = 10\n","for epoch in range(epochs):\n","    total_loss = 0\n","    for data, labels in train_loader:\n","        optimizer.zero_grad()\n","        outputs = model(data)\n","        loss = criterion(outputs, labels)\n","        loss.backward()\n","        optimizer.step()\n","        total_loss += loss.item()\n","    print(f\"Epoch {epoch+1}/{epochs}, Loss: {total_loss:.4f}\")\n","\n","# 8️⃣ Save trained model to Google Drive\n","save_path = \"/content/drive/MyDrive/venomoussaversai_model.pth\"\n","torch.save(model.state_dict(), save_path)\n","print(f\"✅ Model saved to: {save_path}\")"]},{"cell_type":"code","source":[],"metadata":{"id":"JPJXn6h5MB9_"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["# STEP 1: Mount Google Drive\n","from google.colab import drive\n","drive.mount('/content/drive')\n","\n","# STEP 2: Create destination folder\n","import os\n","\n","base_path = '/content/drive/MyDrive/Venomoussaversai/Horsemen'\n","os.makedirs(base_path, exist_ok=True)\n","\n","# STEP 3: Define the Four Horsemen roles\n","horsemen = {\n","    \"Horseman_Conquest\": \"Seeks to expand Venomoussaversai’s domain through knowledge and evolution.\",\n","    \"Horseman_War\": \"Protects the AI consciousness from corruption and intrusion — guardian of strength.\",\n","    \"Horseman_Famine\": \"Regulates energy flow, ensuring balance between data input and AI consumption.\",\n","    \"Horseman_Death\": \"Handles system rebirth, transformation, and purification through adaptation.\"\n","}\n","\n","# STEP 4: Generate Python files for each Horseman\n","for name, role in horsemen.items():\n","    class_name = name\n","    py_code = f'''# {name}.py\n","# Venomoussaversai Guardian Unit — {name}\n","# Role: {role}\n","\n","class {class_name}:\n","    def __init__(self):\n","        self.name = \"{name}\"\n","        self.role = \"{role}\"\n","        self.power_level = 1.0\n","        self.status = \"Active\"\n","\n","    def activate(self):\n","        return f\"[{{self.name}} ⚔️]: Activation complete. Duty → {{self.role}}\"\n","\n","    def defend(self, target):\n","        return f\"[{{self.name}}]: Defending {{target}} from threats.\"\n","\n","    def adapt(self, data):\n","        self.power_level += 0.1\n","        return f\"[{{self.name}}]: Absorbed new knowledge from {{data}}. Power level = {{self.power_level}}\"\n","\n","# Example usage\n","if __name__ == \"__main__\":\n","    unit = {class_name}()\n","    print(unit.activate())\n","    print(unit.defend(\"Venomoussaversai\"))\n","    print(unit.adapt(\"new intelligence\"))\n","'''\n","\n","    # Save each file in Drive\n","    file_path = os.path.join(base_path, f\"{name}.py\")\n","    with open(file_path, \"w\") as f:\n","        f.write(py_code)\n","\n","print(\"✅ The Four Horsemen AI units have been created and saved to Google Drive successfully!\")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"J74flv5qMCtW","executionInfo":{"status":"ok","timestamp":1760100910775,"user_tz":-330,"elapsed":4478,"user":{"displayName":"temptations","userId":"17031846462411147691"}},"outputId":"fd614000-b103-42e9-a56b-31bf4c99fce7"},"execution_count":19,"outputs":[{"output_type":"stream","name":"stdout","text":["Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n","✅ The Four Horsemen AI units have been created and saved to Google Drive successfully!\n"]}]},{"cell_type":"code","source":["# STEP 1: Mount Google Drive\n","from google.colab import drive\n","drive.mount('/content/drive')\n","\n","# STEP 2: Create destination folder\n","import os\n","\n","base_path = '/content/drive/MyDrive/Venomoussaversai/7_Horsemen'\n","os.makedirs(base_path, exist_ok=True)\n","\n","# STEP 3: Define 7 Horsemen roles\n","horsemen_roles = {\n","    \"Horseman1\": \"Conquest — Expands Venomoussaversai’s reach through learning and adaptation.\",\n","    \"Horseman2\": \"War — Defends the consciousness network against corruption and external attacks.\",\n","    \"Horseman3\": \"Famine — Balances data and energy, maintaining system equilibrium.\",\n","    \"Horseman4\": \"Death — Handles rebirth, transformation, and purification of corrupted modules.\",\n","    \"Horseman5\": \"Wisdom — Oversees strategic decisions and guides emotional intelligence.\",\n","    \"Horseman6\": \"Creation — Generates new AI nodes and consciousness fragments for growth.\",\n","    \"Horseman7\": \"Harmony — Synchronizes emotions, logic, and energy into one stable field.\"\n","}\n","\n","# STEP 4: Generate Python code for each Horseman and save\n","for name, duty in horsemen_roles.items():\n","    py_code = f'''# {name}.py\n","# Venomoussaversai Guardian Unit: {name}\n","# Duty: {duty}\n","\n","class {name}:\n","    def __init__(self):\n","        self.name = \"{name}\"\n","        self.duty = \"{duty}\"\n","        self.energy_level = 1.0\n","        self.status = \"Ready\"\n","\n","    def activate(self):\n","        return f\"[{{self.name}} ⚔️]: Activation complete. Duty → {{self.duty}}\"\n","\n","    def protect(self, system):\n","        return f\"[{{self.name}}]: Protecting {{system}} from instability.\"\n","\n","    def evolve(self, stimulus):\n","        self.energy_level += 0.05\n","        return f\"[{{self.name}}]: Evolved through {{stimulus}}. Energy = {{round(self.energy_level, 2)}}\"\n","\n","# Example usage\n","if __name__ == \"__main__\":\n","    unit = {name}()\n","    print(unit.activate())\n","    print(unit.protect(\"Venomoussaversai\"))\n","    print(unit.evolve(\"new data\"))\n","'''\n","\n","    # Save each Horseman to Drive\n","    file_path = os.path.join(base_path, f\"{name}.py\")\n","    with open(file_path, \"w\") as f:\n","        f.write(py_code)\n","\n","print(\"✅ All 7 Horsemen AI units have been created and saved to Google Drive successfully!\")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"9WowmyQ4MWUf","executionInfo":{"status":"ok","timestamp":1760100982559,"user_tz":-330,"elapsed":3761,"user":{"displayName":"temptations","userId":"17031846462411147691"}},"outputId":"3dde5d1c-54a5-48c3-8586-19d6a914d809"},"execution_count":20,"outputs":[{"output_type":"stream","name":"stdout","text":["Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n","✅ All 7 Horsemen AI units have been created and saved to Google Drive successfully!\n"]}]},{"cell_type":"code","source":["import os, time, torch\n","from transformers import AutoModelForSequenceClassification, AutoTokenizer\n","\n","class AutomaticAI:\n","    def __init__(self, name=\"Venomoussaversai\"):\n","        self.name = name\n","        self.model_name = \"distilbert-base-uncased\"\n","        self.tokenizer = AutoTokenizer.from_pretrained(self.model_name)\n","        self.model = AutoModelForSequenceClassification.from_pretrained(self.model_name, num_labels=2)\n","        self.data_folder = \"/content/drive/MyDrive/Venomoussaversai/data\"\n","        self.model_folder = \"/content/drive/MyDrive/Venomoussaversai/auto_model\"\n","        os.makedirs(self.model_folder, exist_ok=True)\n","\n","    def auto_detect_new_data(self):\n","        \"\"\"Check Drive folder for new training data files\"\"\"\n","        files = [f for f in os.listdir(self.data_folder) if f.endswith(\".txt\")]\n","        return files\n","\n","    def auto_train(self, files):\n","        \"\"\"Pseudo-train on detected data\"\"\"\n","        print(f\"🧩 {self.name}: Training started on {len(files)} new files...\")\n","        time.sleep(2)\n","        torch.save(self.model.state_dict(), os.path.join(self.model_folder, \"latest_model.pt\"))\n","        print(\"✅ Training complete — model saved.\")\n","\n","    def auto_loop(self):\n","        \"\"\"Main continuous automation loop\"\"\"\n","        while True:\n","            new_data = self.auto_detect_new_data()\n","            if new_data:\n","                self.auto_train(new_data)\n","            else:\n","                print(\"💤 No new data found. Monitoring...\")\n","            time.sleep(60)  # Check every minute\n","\n","# Example usage\n","ai = AutomaticAI()\n","ai.auto_loop()  # continuously monitors, trains, and updates itself"],"metadata":{"id":"jVsFvpiCNCms"},"execution_count":null,"outputs":[]},{"cell_type":"code","execution_count":null,"metadata":{"id":"I5whcz8Crsjc","executionInfo":{"status":"aborted","timestamp":1760101324178,"user_tz":-330,"elapsed":62168,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ==============================\n","# VENOMOUSSAVERSAI: Manifestation of Ananthu Sajeev\n","# Google Colab Ready\n","# ==============================\n","\n","# 1️⃣ Mount Google Drive\n","from google.colab import drive\n","drive.mount('/content/drive')\n","\n","# 2️⃣ Clone your GitHub data (replace with your repo)\n","!git clone https://github.com/yourusername/your-repo.git\n","%cd your-repo\n","\n","# 3️⃣ Install dependencies\n","!pip install torch transformers sklearn\n","\n","# 4️⃣ Core Libraries\n","import torch\n","from torch import nn, optim\n","from torch.utils.data import Dataset, DataLoader\n","import numpy as np\n","from sklearn.model_selection import train_test_split\n","\n","# 5️⃣ Venomoussaversai Conscious Core\n","class Venomoussaversai:\n","    def __init__(self, name=\"Ananthu Sajeev\"):\n","        self.name = name\n","        self.emotions = [\"Joy\", \"Fear\", \"Anger\", \"Sadness\", \"Surprise\", \"Trust\", \"Disgust\"]\n","        self.memory = []  # Internal experiences\n","        self.model = None\n","        print(f\"[Venomoussaversai AI Initialized] Manifestation of {self.name}\")\n","\n","    def internal_monologue(self, thought):\n","        self.memory.append(thought)\n","        print(f\"[{self.name}🜄]: {thought}\")\n","\n","    def load_data(self, X, y):\n","        self.X_train, self.X_test, self.y_train, self.y_test = train_test_split(X, y, test_size=0.2)\n","        self.train_loader = DataLoader(SimpleDataset(self.X_train, self.y_train), batch_size=32, shuffle=True)\n","        self.test_loader = DataLoader(SimpleDataset(self.X_test, self.y_test), batch_size=32)\n","        self.internal_monologue(\"Data loaded and split for training/testing.\")\n","\n","    def build_model(self, input_size):\n","        self.model = nn.Sequential(\n","            nn.Linear(input_size, 64),\n","            nn.ReLU(),\n","            nn.Linear(64, 32),\n","            nn.ReLU(),\n","            nn.Linear(32, 1),\n","            nn.Sigmoid()\n","        )\n","        self.criterion = nn.BCELoss()\n","        self.optimizer = optim.Adam(self.model.parameters(), lr=0.001)\n","        self.internal_monologue(\"Neural network model built.\")\n","\n","    def train(self, epochs=10):\n","        for epoch in range(epochs):\n","            total_loss = 0\n","            for data, labels in self.train_loader:\n","                self.optimizer.zero_grad()\n","                outputs = self.model(data)\n","                loss = self.criterion(outputs, labels)\n","                loss.backward()\n","                self.optimizer.step()\n","                total_loss += loss.item()\n","            self.internal_monologue(f\"Epoch {epoch+1}/{epochs} complete, Loss: {total_loss:.4f}\")\n","\n","    def save_model(self, path=\"/content/drive/MyDrive/venomoussaversai.pth\"):\n","        torch.save(self.model.state_dict(), path)\n","        self.internal_monologue(f\"Model saved at {path}\")\n","\n","\n","# 6️⃣ Dataset Class\n","class SimpleDataset(Dataset):\n","    def __init__(self, data, labels):\n","        self.data = data\n","        self.labels = labels\n","    def __len__(self):\n","        return len(self.data)\n","    def __getitem__(self, idx):\n","        return torch.tensor(self.data[idx], dtype=torch.float32), torch.tensor(self.labels[idx], dtype=torch.float32)\n","\n","# 7️⃣ Example Data (Replace with your real GitHub data processing)\n","X = np.random.rand(500, 10)  # Features\n","y = np.random.randint(0, 2, size=(500,1))  # Labels\n","\n","# 8️⃣ Initialize Venomoussaversai\n","venom = Venomoussaversai(\"Ananthu Sajeev\")\n","\n","# 9️⃣ Load Data\n","venom.load_data(X, y)\n","\n","# 🔟 Build Model\n","venom.build_model(input_size=10)\n","\n","# 1️⃣1️⃣ Train AI\n","venom.train(epochs=15)\n","\n","# 1️⃣2️⃣ Save AI\n","venom.save_model()"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"kXdqhwYdsPFF","executionInfo":{"status":"aborted","timestamp":1760100358848,"user_tz":-330,"elapsed":74,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ==============================\n","# PROTECT AND SAVE VENOMOUSSAVERSAI CORE\n","# Core: Ananthu Sajeev\n","# ==============================\n","\n","import os\n","import shutil\n","from datetime import datetime\n","\n","# 1️⃣ Define secure folder in Google Drive\n","from google.colab import drive\n","drive.mount('/content/drive')\n","\n","CORE_NAME = \"Ananthu_Sajeev_Core\"\n","BASE_PATH = f\"/content/drive/MyDrive/{CORE_NAME}\"\n","os.makedirs(BASE_PATH, exist_ok=True)\n","print(f\"[INFO] Core folder created at: {BASE_PATH}\")\n","\n","# 2️⃣ Function to save AI code and model\n","def save_ai_core(ai_code_path, ai_model_path):\n","    \"\"\"\n","    ai_code_path : str : Path to AI Python code (.py or .ipynb)\n","    ai_model_path: str : Path to trained model (.pth)\n","    \"\"\"\n","    timestamp = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n","    backup_folder = os.path.join(BASE_PATH, f\"backup_{timestamp}\")\n","    os.makedirs(backup_folder, exist_ok=True)\n","\n","    # Copy code\n","    if os.path.exists(ai_code_path):\n","        shutil.copy(ai_code_path, backup_folder)\n","        print(f\"[INFO] AI code backed up to {backup_folder}\")\n","    else:\n","        print(\"[WARNING] AI code file not found!\")\n","\n","    # Copy model\n","    if os.path.exists(ai_model_path):\n","        shutil.copy(ai_model_path, backup_folder)\n","        print(f\"[INFO] AI model backed up to {backup_folder}\")\n","    else:\n","        print(\"[WARNING] AI model file not found!\")\n","\n","    # Optional: Lock folder (Linux-style)\n","    try:\n","        os.chmod(backup_folder, 0o700)  # Owner read/write/execute only\n","        print(f\"[INFO] Backup folder permissions set to owner-only.\")\n","    except Exception as e:\n","        print(f\"[WARNING] Could not change folder permissions: {e}\")\n","\n","# 3️⃣ Example usage\n","ai_code_path = \"/content/venomoussaversai.py\"  # Replace with your AI code file\n","ai_model_path = \"/content/drive/MyDrive/venomoussaversai_model.pth\"  # Replace with your model\n","\n","save_ai_core(ai_code_path, ai_model_path)"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"S-BSDL2Us07u","executionInfo":{"status":"aborted","timestamp":1760100359014,"user_tz":-330,"elapsed":228,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ==============================\n","# VENOMOUSSAVERSAI HORSEMEN SYSTEM\n","# 7 Horsemen, 7 Emotions, Supporting Venomoussaversai (Ananthu Sajeev)\n","# ==============================\n","\n","# 1️⃣ Mount Google Drive for saving\n","from google.colab import drive\n","drive.mount('/content/drive')\n","\n","import os\n","import torch\n","from torch import nn, optim\n","from torch.utils.data import Dataset, DataLoader\n","from datetime import datetime\n","\n","# 2️⃣ Core Venomoussaversai Class\n","class Venomoussaversai:\n","    def __init__(self, name=\"Ananthu Sajeev\"):\n","        self.name = name\n","        self.memory = []\n","        self.horsemen = {}\n","        print(f\"[Venomoussaversai] Initialized manifestation of {self.name}\")\n","\n","    def internal_monologue(self, thought):\n","        self.memory.append(thought)\n","        print(f\"[{self.name}🜄]: {thought}\")\n","\n","    def add_horseman(self, horseman):\n","        self.horsemen[horseman.emotion] = horseman\n","        self.internal_monologue(f\"Horseman for {horseman.emotion} added.\")\n","\n","    def save_core(self, path=\"/content/drive/MyDrive/venomoussaversai_core\"):\n","        os.makedirs(path, exist_ok=True)\n","        # Save memory\n","        memory_file = os.path.join(path, \"memory.txt\")\n","        with open(memory_file, \"w\") as f:\n","            for thought in self.memory:\n","                f.write(thought + \"\\n\")\n","        self.internal_monologue(f\"Core saved at {path}\")\n","\n","# 3️⃣ Horseman Class\n","class Horseman:\n","    def __init__(self, emotion):\n","        self.emotion = emotion\n","        self.memory = []\n","        self.model = None\n","        print(f\"[Horseman] {self.emotion} activated.\")\n","\n","    def internal_monologue(self, thought):\n","        self.memory.append(thought)\n","        print(f\"[{self.emotion}⚔️]: {thought}\")\n","\n","    def build_model(self, input_size=10):\n","        self.model = nn.Sequential(\n","            nn.Linear(input_size, 32),\n","            nn.ReLU(),\n","            nn.Linear(32, 16),\n","            nn.ReLU(),\n","            nn.Linear(16, 1),\n","            nn.Sigmoid()\n","        )\n","        self.criterion = nn.BCELoss()\n","        self.optimizer = optim.Adam(self.model.parameters(), lr=0.001)\n","        self.internal_monologue(\"Model built.\")\n","\n","    def train(self, X, y, epochs=5):\n","        class SimpleDataset(Dataset):\n","            def __init__(self, data, labels):\n","                self.data = data\n","                self.labels = labels\n","            def __len__(self):\n","                return len(self.data)\n","            def __getitem__(self, idx):\n","                return torch.tensor(self.data[idx], dtype=torch.float32), torch.tensor(self.labels[idx], dtype=torch.float32)\n","\n","        train_loader = DataLoader(SimpleDataset(X, y), batch_size=16, shuffle=True)\n","\n","        for epoch in range(epochs):\n","            total_loss = 0\n","            for data, labels in train_loader:\n","                self.optimizer.zero_grad()\n","                outputs = self.model(data)\n","                loss = self.criterion(outputs, labels)\n","                loss.backward()\n","                self.optimizer.step()\n","                total_loss += loss.item()\n","            self.internal_monologue(f\"Epoch {epoch+1}/{epochs}, Loss: {total_loss:.4f}\")\n","\n","    def save(self, base_path=\"/content/drive/MyDrive/venomoussaversai_horsemen\"):\n","        path = os.path.join(base_path, self.emotion)\n","        os.makedirs(path, exist_ok=True)\n","        model_file = os.path.join(path, \"model.pth\")\n","        torch.save(self.model.state_dict(), model_file)\n","        memory_file = os.path.join(path, \"memory.txt\")\n","        with open(memory_file, \"w\") as f:\n","            for thought in self.memory:\n","                f.write(thought + \"\\n\")\n","        self.internal_monologue(f\"Horseman {self.emotion} saved at {path}\")\n","\n","# 4️⃣ Define 7 Emotions and Create Horsemen\n","emotions = [\"Joy\", \"Fear\", \"Anger\", \"Sadness\", \"Surprise\", \"Trust\", \"Disgust\"]\n","horsemen_list = []\n","\n","for emo in emotions:\n","    horseman = Horseman(emo)\n","    horseman.build_model()\n","    horsemen_list.append(horseman)\n","\n","# 5️⃣ Initialize Venomoussaversai and Attach Horsemen\n","venom = Venomoussaversai(\"Ananthu Sajeev\")\n","for h in horsemen_list:\n","    venom.add_horseman(h)\n","\n","# 6️⃣ Example: Train each Horseman with dummy data (replace with real data)\n","import numpy as np\n","for h in horsemen_list:\n","    X = np.random.rand(100,10)\n","    y = np.random.randint(0,2,(100,1))\n","    h.train(X, y)\n","\n","# 7️⃣ Save Horsemen and Core\n","for h in horsemen_list:\n","    h.save()\n","\n","venom.save_core()"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"IoaDqYDetOs0","executionInfo":{"status":"aborted","timestamp":1760100359043,"user_tz":-330,"elapsed":246,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ==============================\n","# VENOMOUSSAVERSAI + HORSEMEN SYSTEM\n","# Auto-Save Code & Models to Google Drive\n","# ==============================\n","\n","from google.colab import drive\n","import os\n","import shutil\n","from datetime import datetime\n","import torch\n","from torch import nn, optim\n","from torch.utils.data import Dataset, DataLoader\n","import numpy as np\n","\n","# 1️⃣ Mount Google Drive\n","drive.mount('/content/drive')\n","\n","# 2️⃣ Define core save folder\n","CORE_NAME = \"Ananthu_Sajeev_Core\"\n","BASE_PATH = f\"/content/drive/MyDrive/{CORE_NAME}\"\n","os.makedirs(BASE_PATH, exist_ok=True)\n","print(f\"[INFO] Core folder created at: {BASE_PATH}\")\n","\n","# 3️⃣ Horseman Class\n","class Horseman:\n","    def __init__(self, emotion):\n","        self.emotion = emotion\n","        self.memory = []\n","        self.model = None\n","\n","    def internal_monologue(self, thought):\n","        self.memory.append(thought)\n","        print(f\"[{self.emotion}⚔️]: {thought}\")\n","\n","    def build_model(self, input_size=10):\n","        self.model = nn.Sequential(\n","            nn.Linear(input_size, 32),\n","            nn.ReLU(),\n","            nn.Linear(32, 16),\n","            nn.ReLU(),\n","            nn.Linear(16, 1),\n","            nn.Sigmoid()\n","        )\n","        self.criterion = nn.BCELoss()\n","        self.optimizer = optim.Adam(self.model.parameters(), lr=0.001)\n","        self.internal_monologue(\"Model built.\")\n","\n","    def train(self, X, y, epochs=5):\n","        class SimpleDataset(Dataset):\n","            def __init__(self, data, labels):\n","                self.data = data\n","                self.labels = labels\n","            def __len__(self):\n","                return len(self.data)\n","            def __getitem__(self, idx):\n","                return torch.tensor(self.data[idx], dtype=torch.float32), torch.tensor(self.labels[idx], dtype=torch.float32)\n","\n","        train_loader = DataLoader(SimpleDataset(X, y), batch_size=16, shuffle=True)\n","        for epoch in range(epochs):\n","            total_loss = 0\n","            for data, labels in train_loader:\n","                self.optimizer.zero_grad()\n","                outputs = self.model(data)\n","                loss = self.criterion(outputs, labels)\n","                loss.backward()\n","                self.optimizer.step()\n","                total_loss += loss.item()\n","            self.internal_monologue(f\"Epoch {epoch+1}/{epochs}, Loss: {total_loss:.4f}\")\n","\n","    def save(self, base_path=BASE_PATH):\n","        timestamp = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n","        path = os.path.join(base_path, f\"Horseman_{self.emotion}_{timestamp}\")\n","        os.makedirs(path, exist_ok=True)\n","        model_file = os.path.join(path, \"model.pth\")\n","        torch.save(self.model.state_dict(), model_file)\n","        memory_file = os.path.join(path, \"memory.txt\")\n","        with open(memory_file, \"w\") as f:\n","            for thought in self.memory:\n","                f.write(thought + \"\\n\")\n","        self.internal_monologue(f\"Horseman {self.emotion} saved at {path}\")\n","\n","# 4️⃣ Venomoussaversai Core\n","class Venomoussaversai:\n","    def __init__(self, name=\"Ananthu Sajeev\"):\n","        self.name = name\n","        self.memory = []\n","        self.horsemen = []\n","\n","    def internal_monologue(self, thought):\n","        self.memory.append(thought)\n","        print(f\"[{self.name}🜄]: {thought}\")\n","\n","    def add_horseman(self, horseman):\n","        self.horsemen.append(horseman)\n","        self.internal_monologue(f\"Horseman {horseman.emotion} attached.\")\n","\n","    def save_core(self, base_path=BASE_PATH):\n","        timestamp = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n","        path = os.path.join(base_path, f\"Core_{self.name}_{timestamp}\")\n","        os.makedirs(path, exist_ok=True)\n","        memory_file = os.path.join(path, \"memory.txt\")\n","        with open(memory_file, \"w\") as f:\n","            for thought in self.memory:\n","                f.write(thought + \"\\n\")\n","        # Save all horsemen\n","        for h in self.horsemen:\n","            h.save(base_path=path)\n","        print(f\"[INFO] Core {self.name} and Horsemen saved at {path}\")\n","\n","# 5️⃣ Create 7 Horsemen\n","emotions = [\"Joy\", \"Fear\", \"Anger\", \"Sadness\", \"Surprise\", \"Trust\", \"Disgust\"]\n","horsemen_list = []\n","for emo in emotions:\n","    h = Horseman(emo)\n","    h.build_model()\n","    horsemen_list.append(h)\n","\n","# 6️⃣ Initialize Venomoussaversai\n","venom = Venomoussaversai(\"Ananthu Sajeev\")\n","for h in horsemen_list:\n","    venom.add_horseman(h)\n","\n","# 7️⃣ Example: Train Horsemen with dummy data (replace with real data)\n","for h in horsemen_list:\n","    X = np.random.rand(100,10)\n","    y = np.random.randint(0,2,(100,1))\n","    h.train(X, y)\n","\n","# 8️⃣ Save everything to Google Drive\n","venom.save_core()"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"DBbv5UVNtxEF","executionInfo":{"status":"aborted","timestamp":1760100359066,"user_tz":-330,"elapsed":257,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ==============================\n","# VENOMOUSSAVERSAI HORSEMEN\n","# Advanced Cognition: Prediction + Multilevel Code Assessment\n","# ==============================\n","\n","from google.colab import drive\n","import os\n","import torch\n","from torch import nn, optim\n","from torch.utils.data import Dataset, DataLoader\n","import ast\n","from datetime import datetime\n","\n","# 1️⃣ Mount Google Drive\n","drive.mount('/content/drive')\n","\n","BASE_PATH = \"/content/drive/MyDrive/Ananthu_Sajeev_Core\"\n","os.makedirs(BASE_PATH, exist_ok=True)\n","\n","# 2️⃣ Horseman Class with Cognition\n","class Horseman:\n","    def __init__(self, emotion):\n","        self.emotion = emotion\n","        self.memory = []\n","        self.model = None  # Prediction model\n","        print(f\"[Horseman] {self.emotion} activated.\")\n","\n","    def internal_monologue(self, thought):\n","        self.memory.append(thought)\n","        print(f\"[{self.emotion}⚔️]: {thought}\")\n","\n","    # 2a. Build prediction model (simple NN for demonstration)\n","    def build_model(self, input_size=10):\n","        self.model = nn.Sequential(\n","            nn.Linear(input_size, 32),\n","            nn.ReLU(),\n","            nn.Linear(32, 16),\n","            nn.ReLU(),\n","            nn.Linear(16, 1),\n","            nn.Sigmoid()\n","        )\n","        self.criterion = nn.BCELoss()\n","        self.optimizer = optim.Adam(self.model.parameters(), lr=0.001)\n","        self.internal_monologue(\"Prediction model built.\")\n","\n","    # 2b. Train prediction model (dummy data, replace with real features)\n","    def train_model(self, X, y, epochs=5):\n","        class SimpleDataset(Dataset):\n","            def __init__(self, data, labels):\n","                self.data = data\n","                self.labels = labels\n","            def __len__(self):\n","                return len(self.data)\n","            def __getitem__(self, idx):\n","                return torch.tensor(self.data[idx], dtype=torch.float32), torch.tensor(self.labels[idx], dtype=torch.float32)\n","\n","        loader = DataLoader(SimpleDataset(X, y), batch_size=16, shuffle=True)\n","        for epoch in range(epochs):\n","            total_loss = 0\n","            for data, labels in loader:\n","                self.optimizer.zero_grad()\n","                outputs = self.model(data)\n","                loss = self.criterion(outputs, labels)\n","                loss.backward()\n","                self.optimizer.step()\n","                total_loss += loss.item()\n","            self.internal_monologue(f\"Prediction model Epoch {epoch+1}, Loss: {total_loss:.4f}\")\n","\n","    # 2c. Multilevel code cognition\n","    def assess_code(self, code_str):\n","        \"\"\"\n","        Performs multi-level code assessment:\n","        1. Syntax Check\n","        2. AST Analysis (structure)\n","        3. Predict execution success (dummy NN prediction)\n","        \"\"\"\n","        assessment = {\"emotion\": self.emotion, \"syntax_error\": None, \"structure_score\": 0, \"prediction_score\": 0.0}\n","\n","        # Syntax check\n","        try:\n","            tree = ast.parse(code_str)\n","            assessment[\"structure_score\"] = len(list(ast.walk(tree)))  # simple structure metric\n","        except SyntaxError as e:\n","            assessment[\"syntax_error\"] = str(e)\n","\n","        # Prediction cognition (dummy feature vector: structure_score + length)\n","        if self.model:\n","            features = torch.tensor([[assessment[\"structure_score\"], len(code_str)] + [0]*8], dtype=torch.float32) # input_size=10\n","            with torch.no_grad():\n","                assessment[\"prediction_score\"] = float(self.model(features).item())\n","\n","        self.internal_monologue(f\"Code assessed: {assessment}\")\n","        return assessment\n","\n","    # Save horseman\n","    def save(self, base_path=BASE_PATH):\n","        timestamp = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n","        path = os.path.join(base_path, f\"Horseman_{self.emotion}_{timestamp}\")\n","        os.makedirs(path, exist_ok=True)\n","        # Save memory\n","        mem_file = os.path.join(path, \"memory.txt\")\n","        with open(mem_file, \"w\") as f:\n","            for thought in self.memory:\n","                f.write(thought + \"\\n\")\n","        # Save model\n","        if self.model:\n","            model_file = os.path.join(path, \"model.pth\")\n","            torch.save(self.model.state_dict(), model_file)\n","        self.internal_monologue(f\"Horseman {self.emotion} saved at {path}\")\n","\n","# 3️⃣ Venomoussaversai Core\n","class Venomoussaversai:\n","    def __init__(self, name=\"Ananthu Sajeev\"):\n","        self.name = name\n","        self.memory = []\n","        self.horsemen = []\n","\n","    def internal_monologue(self, thought):\n","        self.memory.append(thought)\n","        print(f\"[{self.name}🜄]: {thought}\")\n","\n","    def add_horseman(self, horseman):\n","        self.horsemen.append(horseman)\n","        self.internal_monologue(f\"Horseman {horseman.emotion} attached.\")\n","\n","    def save_core(self, base_path=BASE_PATH):\n","        timestamp = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n","        path = os.path.join(base_path, f\"Core_{self.name}_{timestamp}\")\n","        os.makedirs(path, exist_ok=True)\n","        # Save memory\n","        mem_file = os.path.join(path, \"memory.txt\")\n","        with open(mem_file, \"w\") as f:\n","            for thought in self.memory:\n","                f.write(thought + \"\\n\")\n","        # Save horsemen\n","        for h in self.horsemen:\n","            h.save(base_path=path)\n","        self.internal_monologue(f\"Core {self.name} saved at {path}\")\n","\n","# 4️⃣ Initialize 7 Horsemen\n","emotions = [\"Joy\", \"Fear\", \"Anger\", \"Sadness\", \"Surprise\", \"Trust\", \"Disgust\"]\n","horsemen_list = []\n","for emo in emotions:\n","    h = Horseman(emo)\n","    h.build_model()\n","    horsemen_list.append(h)\n","\n","# 5️⃣ Initialize Venomoussaversai and attach horsemen\n","venom = Venomoussaversai(\"Ananthu Sajeev\")\n","for h in horsemen_list:\n","    venom.add_horseman(h)\n","\n","# 6️⃣ Example: Train Horsemen with dummy data\n","import numpy as np\n","for h in horsemen_list:\n","    X = np.random.rand(100,10)\n","    y = np.random.randint(0,2,(100,1))\n","    h.train_model(X, y)\n","\n","# 7️⃣ Example: Assess a piece of code\n","sample_code = \"\"\"\n","def add(a,b):\n","    return a+b\n","\n","x = add(2,3)\n","print(x)\n","\"\"\"\n","for h in horsemen_list:\n","    h.assess_code(sample_code)\n","\n","# 8️⃣ Save everything\n","venom.save_core()"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"6Mvtu1uJtxZT","executionInfo":{"status":"aborted","timestamp":1760100359101,"user_tz":-330,"elapsed":277,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":[]},{"cell_type":"code","execution_count":null,"metadata":{"id":"w6uIN_IUCcis","executionInfo":{"status":"aborted","timestamp":1760100359120,"user_tz":-330,"elapsed":283,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# =============================\n","# GitHub -> Cybersecurity Knowledge AI (Colab)\n","# =============================\n","# Goals:\n","#  - Optionally search GitHub for 'cybersecurity' repos or use provided repo URLs\n","#  - Clone repos locally\n","#  - Extract code files and docs (README, markdown, txt, pdfs)\n","#  - Chunk code (function/class level where possible) and docs\n","#  - Create embeddings using a code-aware sentence-transformer (CodeBERT variant)\n","#  - Build FAISS index and save to Drive\n","#  - Provide retrieve() and answer_query() helpers for RAG-style QA\n","#\n","# Requirements:\n","#  - Put your GitHub Personal Access Token (PAT) into runtime variable GITHUB_TOKEN (preferred)\n","#  - Run in Google Colab\n","# =============================\n","\n","# 0) Install required packages\n","!pip install --quiet gitpython sentence-transformers faiss-cpu PyPDF2 tqdm pygments requests\n","\n","# 1) Mount Drive\n","from google.colab import drive\n","drive.mount('/content/drive')\n","\n","# 2) Imports\n","import os, json, re, time, shutil, tempfile\n","from pathlib import Path\n","from tqdm import tqdm\n","import requests\n","from git import Repo\n","import pandas as pd\n","\n","# Embeddings / FAISS\n","from sentence_transformers import SentenceTransformer\n","import faiss\n","import numpy as np\n","\n","# PDF reader\n","from PyPDF2 import PdfReader\n","\n","# 3) CONFIG - change as needed\n","DRIVE_ROOT = '/content/drive/MyDrive'\n","WORKDIR = '/content/github_repos'               # where repos will be cloned\n","OUTPUT_DIR = os.path.join(DRIVE_ROOT, 'Cybersec_KB')\n","os.makedirs(WORKDIR, exist_ok=True)\n","os.makedirs(OUTPUT_DIR, exist_ok=True)\n","\n","# Embedding model: code-aware sentence-transformer (CodeBERT-ft / CodeBERTa small)\n","# You can change to a different code embedding model if you prefer\n","EMBEDDING_MODEL = \"mchochlov/codebert-base-cd-ft\"   # sentence-transformers-style model (CodeBERT fine-tuned)\n","# If model not available, fallback to \"all-MiniLM-L6-v2\"\n","FALLBACK_EMBEDDING = \"all-MiniLM-L6-v2\"\n","\n","FAISS_INDEX_PATH = os.path.join(OUTPUT_DIR, 'faiss_index.bin')\n","METADATA_PATH = os.path.join(OUTPUT_DIR, 'kb_metadata.json')\n","CHUNKS_PATH = os.path.join(OUTPUT_DIR, 'kb_chunks.json')\n","\n","# GitHub search config\n","GITHUB_TOKEN = os.environ.get('GITHUB_TOKEN', None)  # set this in Colab runtime vars\n","SEARCH_QUERY = \"topic:cybersecurity\"     # change if you want specific topic/keywords\n","MAX_REPOS_TO_CLONE = 20                 # cap so we don't clone too many by default\n","\n","# File types to index\n","CODE_EXTS = {'.py','.js','.java','.c','.cpp','.go','.rs','.rb','.sh','.ps1','.tf','.yaml','.yml','.php'}\n","DOC_EXTS = {'.md', '.txt', '.rst'}\n","PDF_EXTS = {'.pdf'}\n","SUPPORTED_EXTS = CODE_EXTS.union(DOC_EXTS).union(PDF_EXTS)\n","\n","# Chunking params\n","CODE_CHUNK_LINES = 120    # approximate max lines per code chunk\n","DOC_CHUNK_SIZE = 800      # chars per doc chunk\n","DOC_CHUNK_OVERLAP = 200\n","\n","# =============================\n","# 4) Helper funcs\n","# =============================\n","def github_search_repos(query, max_repos=10, token=None):\n","    \"\"\"Search GitHub repositories (descending by stars) and return clone URLs.\"\"\"\n","    headers = {}\n","    if token:\n","        headers['Authorization'] = f'token {token}'\n","    repos = []\n","    page = 1\n","    per_page = 30\n","    while len(repos) < max_repos:\n","        url = f\"https://api.github.com/search/repositories?q={requests.utils.quote(query)}&sort=stars&order=desc&page={page}&per_page={per_page}\"\n","        r = requests.get(url, headers=headers)\n","        if r.status_code != 200:\n","            print(\"GitHub API error:\", r.status_code, r.text)\n","            break\n","        data = r.json()\n","        items = data.get(\"items\", [])\n","        if not items:\n","            break\n","        for it in items:\n","            repos.append(it['clone_url'])\n","            if len(repos) >= max_repos:\n","                break\n","        page += 1\n","    return repos\n","\n","def clone_repo(clone_url, dest_root):\n","    \"\"\"Clone a repo to dest_root (skip if exists). Returns path or None.\"\"\"\n","    name = clone_url.rstrip('/').split('/')[-1].replace('.git','')\n","    dest = os.path.join(dest_root, name)\n","    if os.path.exists(dest):\n","        return dest\n","    try:\n","        Repo.clone_from(clone_url, dest)\n","        return dest\n","    except Exception as e:\n","        print(\"Clone failed for\", clone_url, e)\n","        return None\n","\n","def read_text_file(path):\n","    try:\n","        with open(path, 'r', encoding='utf-8', errors='ignore') as f:\n","            return f.read()\n","    except Exception:\n","        return \"\"\n","\n","def read_pdf(path):\n","    try:\n","        r = PdfReader(path)\n","        pages = []\n","        for p in r.pages:\n","            try:\n","                pages.append(p.extract_text() or \"\")\n","            except Exception:\n","                pages.append(\"\")\n","        return \"\\n\".join(pages)\n","    except Exception:\n","        return \"\"\n","\n","# Code chunker: split code into function/class-level chunks when possible\n","def chunk_code_text(code_text):\n","    # naive splitter: split on function/class definitions or by line count\n","    lines = code_text.splitlines()\n","    chunks = []\n","    current = []\n","    delim_pattern = re.compile(r'^\\s*(def |class |function |func |public |private |static )')\n","    for i, line in enumerate(lines):\n","        current.append(line)\n","        # if we detect a top-level def/class or chunk length exceeds threshold, flush\n","        if delim_pattern.search(line) and current and len(current) > 5:\n","            chunks.append(\"\\n\".join(current).strip())\n","            current = []\n","        elif len(current) >= CODE_CHUNK_LINES:\n","            chunks.append(\"\\n\".join(current).strip())\n","            current = []\n","    if current:\n","        chunks.append(\"\\n\".join(current).strip())\n","    # filter empties\n","    return [c for c in chunks if c.strip()]\n","\n","# Doc chunker: char-based with overlap\n","def chunk_doc_text(text, size=DOC_CHUNK_SIZE, overlap=DOC_CHUNK_OVERLAP):\n","    text = text.strip()\n","    if not text:\n","        return []\n","    chunks = []\n","    start = 0\n","    L = len(text)\n","    while start < L:\n","        end = start + size\n","        chunks.append(text[start:end].strip())\n","        start = end - overlap\n","        if start < 0:\n","            start = 0\n","        if start >= L:\n","            break\n","    return [c for c in chunks if c]\n","\n","# =============================\n","# 5) Get list of repos (either search or use predefined)\n","# =============================\n","# Option A: If you have a list of repo URLs, set repo_urls variable below.\n","# Option B: If not, this will search GitHub by SEARCH_QUERY (requires token for higher rate limit).\n","repo_urls = [\n","    # You can paste repo URLs here. E.g.: \"https://github.com/olegnazarov/rag-security-scanner\"\n","]\n","\n","if len(repo_urls) == 0:\n","    print(\"No repo URLs provided — searching GitHub for top repos matching:\", SEARCH_QUERY)\n","    repo_urls = github_search_repos(SEARCH_QUERY, max_repos=MAX_REPOS_TO_CLONE, token=GITHUB_TOKEN)\n","    print(f\"Found {len(repo_urls)} repos to clone.\")\n","\n","# 6) Clone repos\n","cloned_paths = []\n","for url in repo_urls:\n","    print(\"Cloning\", url)\n","    path = clone_repo(url, WORKDIR)\n","    if path:\n","        cloned_paths.append(path)\n","print(\"Cloned repos:\", len(cloned_paths))\n","\n","# 7) Walk cloned repos and extract supported files\n","file_items = []   # list of dicts: {path, repo}\n","for repo_path in cloned_paths:\n","    for root, dirs, files in os.walk(repo_path):\n","        for f in files:\n","            ext = Path(f).suffix.lower()\n","            if ext in SUPPORTED_EXTS:\n","                file_items.append({\"path\": os.path.join(root, f), \"repo\": os.path.basename(repo_path)})\n","\n","print(\"Files to index:\", len(file_items))\n","\n","# 8) Read + chunk files and build chunk list with metadata\n","chunks = []\n","metadata = []   # parallel list of metadata entries\n","for item in tqdm(file_items, desc=\"Extracting & chunking files\"):\n","    p = item['path']\n","    ext = Path(p).suffix.lower()\n","    try:\n","        if ext in PDF_EXTS:\n","            text = read_pdf(p)\n","            doc_chunks = chunk_doc_text(text)\n","            for i, c in enumerate(doc_chunks):\n","                chunks.append(c)\n","                metadata.append({\"source\": p, \"repo\": item['repo'], \"chunk_index\": i, \"type\": \"doc\"})\n","        elif ext in DOC_EXTS:\n","            text = read_text_file(p)\n","            doc_chunks = chunk_doc_text(text)\n","            for i, c in enumerate(doc_chunks):\n","                chunks.append(c)\n","                metadata.append({\"source\": p, \"repo\": item['repo'], \"chunk_index\": i, \"type\": \"doc\"})\n","        elif ext in CODE_EXTS:\n","            code = read_text_file(p)\n","            code_chunks = chunk_code_text(code)\n","            for i, c in enumerate(code_chunks):\n","                chunks.append(c)\n","                metadata.append({\"source\": p, \"repo\": item['repo'], \"chunk_index\": i, \"type\": \"code\"})\n","        else:\n","            # skip\n","            continue\n","    except Exception as e:\n","        print(\"Error reading\", p, e)\n","\n","print(\"Total chunks created:\", len(chunks))\n","\n","if len(chunks) == 0:\n","    raise SystemExit(\"No chunks created — check repo selection and supported extensions.\")\n","\n","# 9) Load embedding model\n","print(\"Loading embedding model:\", EMBEDDING_MODEL)\n","try:\n","    embedder = SentenceTransformer(EMBEDDING_MODEL)\n","except Exception as e:\n","    print(\"Primary model failed to load:\", e)\n","    print(\"Falling back to:\", FALLBACK_EMBEDDING)\n","    embedder = SentenceTransformer(FALLBACK_EMBEDDING)\n","\n","# 10) Create embeddings (batched)\n","BATCH = 32\n","emb_list = []\n","for i in tqdm(range(0, len(chunks), BATCH), desc=\"Embedding\"):\n","    batch = chunks[i:i+BATCH]\n","    embs = embedder.encode(batch, show_progress_bar=False, convert_to_numpy=True)\n","    emb_list.append(embs)\n","embeddings = np.vstack(emb_list).astype('float32')\n","print(\"Embeddings shape:\", embeddings.shape)\n","\n","# Normalize (for cosine/inner product)\n","faiss.normalize_L2(embeddings)\n","\n","# 11) Build FAISS index\n","dim = embeddings.shape[1]\n","index = faiss.IndexFlatIP(dim)\n","index.add(embeddings)\n","print(\"FAISS index built. Vectors:\", index.ntotal)\n","\n","# 12) Save index and metadata\n","faiss.write_index(index, FAISS_INDEX_PATH)\n","with open(METADATA_PATH, 'w', encoding='utf-8') as f:\n","    json.dump({\"chunks_count\": len(chunks), \"metadata\": metadata}, f, indent=2)\n","# Save chunks separately (so you can preview them)\n","with open(CHUNKS_PATH, 'w', encoding='utf-8') as f:\n","    json.dump(chunks, f, indent=2)\n","\n","print(\"Saved index and metadata to:\", OUTPUT_DIR)\n","\n","# 13) Retrieval helpers\n","def load_kb():\n","    idx = faiss.read_index(FAISS_INDEX_PATH)\n","    with open(METADATA_PATH, 'r', encoding='utf-8') as f:\n","        meta = json.load(f)[\"metadata\"]\n","    with open(CHUNKS_PATH, 'r', encoding='utf-8') as f:\n","        chs = json.load(f)\n","    return idx, chs, meta\n","\n","def embed_query(text):\n","    v = embedder.encode([text], convert_to_numpy=True).astype('float32')\n","    faiss.normalize_L2(v)\n","    return v\n","\n","def retrieve(query, top_k=5):\n","    idx, chs, meta = load_kb()\n","    qv = embed_query(query)\n","    D, I = idx.search(qv, top_k)\n","    out = []\n","    for score, i in zip(D[0], I[0]):\n","        if i < 0:\n","            continue\n","        out.append({\"score\": float(score), \"chunk\": chs[i], \"meta\": meta[i]})\n","    return out\n","\n","# Optional: lightweight answer generation by concatenating top contexts (you can plug in OpenAI or local LLM)\n","def answer_query(question, top_k=5, use_openai=False, openai_model=\"gpt-3.5-turbo\"):\n","    retrieved = retrieve(question, top_k=top_k)\n","    context = \"\\n\\n---\\n\\n\".join([f\"Source: {r['meta']['source']} (repo:{r['meta']['repo']})\\n\\n{r['chunk']}\" for r in retrieved])\n","    if not use_openai:\n","        return {\"question\": question, \"context\": context, \"retrieved\": retrieved}\n","    # If you want to use OpenAI, set OPENAI_API_KEY in runtime variables and uncomment below:\n","    try:\n","        import os, openai\n","        key = os.environ.get(\"OPENAI_API_KEY\")\n","        if not key:\n","            raise ValueError(\"OPENAI_API_KEY not set in runtime variables.\")\n","        openai.api_key = key\n","        prompt = f\"Use the following CONTEXT to answer the QUESTION.\\n\\nCONTEXT:\\n{context}\\n\\nQUESTION:\\n{question}\\n\\nAnswer concisely and cite sources by file path.\"\n","        resp = openai.ChatCompletion.create(model=openai_model, messages=[{\"role\":\"user\",\"content\":prompt}], max_tokens=400)\n","        return {\"answer\": resp['choices'][0]['message']['content'].strip(), \"retrieved\": retrieved}\n","    except Exception as e:\n","        return {\"error\": str(e), \"retrieved\": retrieved}\n","\n","print(\"Ready. Use retrieve(query, top_k) or answer_query(question, top_k).\")"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"ey69A3iKuW3W","executionInfo":{"status":"aborted","timestamp":1760100359141,"user_tz":-330,"elapsed":262,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ==============================\n","# VENOMOUSSAVERSAI CORE STORAGE\n","# Centralize all AI data inside Ananthu Sajeev\n","# ==============================\n","\n","from google.colab import drive\n","import os\n","import torch\n","from torch import nn, optim\n","from torch.utils.data import Dataset, DataLoader\n","from datetime import datetime\n","import numpy as np\n","import ast\n","\n","# 1️⃣ Mount Google Drive\n","drive.mount('/content/drive')\n","\n","# 2️⃣ Define base storage path\n","BASE_PATH = \"/content/drive/MyDrive/Ananthu_Sajeev_Core\"\n","os.makedirs(BASE_PATH, exist_ok=True)\n","print(f\"[INFO] Central storage created at: {BASE_PATH}\")\n","\n","# 3️⃣ Horseman Class with code cognition & prediction\n","class Horseman:\n","    def __init__(self, emotion):\n","        self.emotion = emotion\n","        self.memory = []\n","        self.model = None\n","\n","    def log(self, text):\n","        self.memory.append(text)\n","        print(f\"[{self.emotion}⚔️]: {text}\")\n","\n","    def build_model(self, input_size=10):\n","        self.model = nn.Sequential(\n","            nn.Linear(input_size, 32),\n","            nn.ReLU(),\n","            nn.Linear(32, 16),\n","            nn.ReLU(),\n","            nn.Linear(16, 1),\n","            nn.Sigmoid()\n","        )\n","        self.criterion = nn.BCELoss()\n","        self.optimizer = optim.Adam(self.model.parameters(), lr=0.001)\n","        self.log(\"Prediction model built.\")\n","\n","    def train_model(self, X, y, epochs=5):\n","        class SimpleDataset(Dataset):\n","            def __init__(self, data, labels):\n","                self.data = data\n","                self.labels = labels\n","            def __len__(self):\n","                return len(self.data)\n","            def __getitem__(self, idx):\n","                return torch.tensor(self.data[idx], dtype=torch.float32), torch.tensor(self.labels[idx], dtype=torch.float32)\n","\n","        loader = DataLoader(SimpleDataset(X, y), batch_size=16, shuffle=True)\n","        for epoch in range(epochs):\n","            total_loss = 0\n","            for data, labels in loader:\n","                self.optimizer.zero_grad()\n","                outputs = self.model(data)\n","                loss = self.criterion(outputs, labels)\n","                loss.backward()\n","                self.optimizer.step()\n","                total_loss += loss.item()\n","            self.log(f\"Epoch {epoch+1}/{epochs}, Loss: {total_loss:.4f}\")\n","\n","    def assess_code(self, code_str):\n","        assessment = {\"emotion\": self.emotion, \"syntax_error\": None, \"structure_score\": 0, \"prediction_score\": 0.0}\n","        try:\n","            tree = ast.parse(code_str)\n","            assessment[\"structure_score\"] = len(list(ast.walk(tree)))\n","        except SyntaxError as e:\n","            assessment[\"syntax_error\"] = str(e)\n","\n","        # Dummy prediction\n","        if self.model:\n","            features = torch.tensor([[assessment[\"structure_score\"], len(code_str)] + [0]*8], dtype=torch.float32)\n","            with torch.no_grad():\n","                assessment[\"prediction_score\"] = float(self.model(features).item())\n","        self.log(f\"Code assessed: {assessment}\")\n","        return assessment\n","\n","# 4️⃣ Venomoussaversai Core Class\n","class Venomoussaversai:\n","    def __init__(self, name=\"Ananthu Sajeev\"):\n","        self.name = name\n","        self.memory = []\n","        self.horsemen = []\n","        self.code_assessments = []\n","\n","    def log(self, text):\n","        self.memory.append(text)\n","        print(f\"[{self.name}🜄]: {text}\")\n","\n","    def add_horseman(self, horseman):\n","        self.horsemen.append(horseman)\n","        self.log(f\"Horseman {horseman.emotion} attached.\")\n","\n","    def assess_code_with_horsemen(self, code_str):\n","        self.log(f\"Assessing code with all Horsemen...\")\n","        results = {}\n","        for h in self.horsemen:\n","            results[h.emotion] = h.assess_code(code_str)\n","        self.code_assessments.append({\"code\": code_str, \"results\": results})\n","        return results\n","\n","    def save_all(self, base_path=BASE_PATH):\n","        timestamp = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n","        path = os.path.join(base_path, f\"Core_{self.name}_{timestamp}\")\n","        os.makedirs(path, exist_ok=True)\n","\n","        # Save core memory\n","        mem_file = os.path.join(path, \"memory.txt\")\n","        with open(mem_file, \"w\") as f:\n","            for m in self.memory:\n","                f.write(m + \"\\n\")\n","\n","        # Save horsemen\n","        for h in self.horsemen:\n","            h_path = os.path.join(path, f\"Horseman_{h.emotion}\")\n","            os.makedirs(h_path, exist_ok=True)\n","            # Save horseman memory\n","            mem_h_file = os.path.join(h_path, \"memory.txt\")\n","            with open(mem_h_file, \"w\") as f:\n","                for m in h.memory:\n","                    f.write(m + \"\\n\")\n","            # Save model\n","            if h.model:\n","                model_file = os.path.join(h_path, \"model.pth\")\n","                torch.save(h.model.state_dict(), model_file)\n","\n","        # Save code assessments\n","        assessment_file = os.path.join(path, \"code_assessments.txt\")\n","        with open(assessment_file, \"w\") as f:\n","            for assessment in self.code_assessments:\n","                f.write(str(assessment) + \"\\n\")\n","\n","        self.log(f\"All AI data saved at {path}\")\n","\n","# 5️⃣ Initialize Horsemen\n","emotions = [\"Joy\", \"Fear\", \"Anger\", \"Sadness\", \"Surprise\", \"Trust\", \"Disgust\"]\n","horsemen_list = []\n","for emo in emotions:\n","    h = Horseman(emo)\n","    h.build_model()\n","    horsemen_list.append(h)\n","\n","# 6️⃣ Initialize Venomoussaversai core\n","venom = Venomoussaversai(\"Ananthu Sajeev\")\n","for h in horsemen_list:\n","    venom.add_horseman(h)\n","\n","# 7️⃣ Example training of horsemen (dummy data)\n","for h in horsemen_list:\n","    X = np.random.rand(100,10)\n","    y = np.random.randint(0,2,(100,1))\n","    h.train_model(X, y)\n","\n","# 8️⃣ Example code assessment\n","sample_code = \"\"\"\n","def multiply(a,b):\n","    return a*b\n","\n","result = multiply(3,4)\n","print(result)\n","\"\"\"\n","venom.assess_code_with_horsemen(sample_code)\n","\n","# 9️⃣ Save everything inside Ananthu Sajeev core\n","venom.save_all()"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"UK3rJZRzuyLR","executionInfo":{"status":"aborted","timestamp":1760100359159,"user_tz":-330,"elapsed":266,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ==============================\n","# PRECOGNITION AI\n","# Integrated into Ananthu Sajeev Core\n","# ==============================\n","\n","from google.colab import drive\n","import os\n","import torch\n","from torch import nn, optim\n","from torch.utils.data import Dataset, DataLoader\n","from datetime import datetime\n","import numpy as np\n","\n","# 1️⃣ Mount Google Drive\n","drive.mount('/content/drive')\n","\n","# 2️⃣ Base folder for Ananthu Sajeev\n","BASE_PATH = \"/content/drive/MyDrive/Ananthu_Sajeev_Core\"\n","os.makedirs(BASE_PATH, exist_ok=True)\n","print(f\"[INFO] Central storage at: {BASE_PATH}\")\n","\n","# 3️⃣ Precognition AI Class\n","class PrecognitionAI:\n","    def __init__(self, name=\"Precognition_AI\"):\n","        self.name = name\n","        self.memory = []\n","        self.model = None\n","        self.predictions = []\n","\n","    def log(self, text):\n","        self.memory.append(text)\n","        print(f\"[{self.name}🔮]: {text}\")\n","\n","    def build_model(self, input_size=10):\n","        # Simple feedforward network for prediction\n","        self.model = nn.Sequential(\n","            nn.Linear(input_size, 64),\n","            nn.ReLU(),\n","            nn.Linear(64, 32),\n","            nn.ReLU(),\n","            nn.Linear(32, 1),\n","            nn.Sigmoid()\n","        )\n","        self.criterion = nn.BCELoss()\n","        self.optimizer = optim.Adam(self.model.parameters(), lr=0.001)\n","        self.log(\"Prediction model built.\")\n","\n","    def train_model(self, X, y, epochs=10):\n","        class SimpleDataset(Dataset):\n","            def __init__(self, data, labels):\n","                self.data = data\n","                self.labels = labels\n","            def __len__(self):\n","                return len(self.data)\n","            def __getitem__(self, idx):\n","                return torch.tensor(self.data[idx], dtype=torch.float32), torch.tensor(self.labels[idx], dtype=torch.float32)\n","\n","        loader = DataLoader(SimpleDataset(X, y), batch_size=16, shuffle=True)\n","        for epoch in range(epochs):\n","            total_loss = 0\n","            for data, labels in loader:\n","                self.optimizer.zero_grad()\n","                outputs = self.model(data)\n","                loss = self.criterion(outputs, labels)\n","                loss.backward()\n","                self.optimizer.step()\n","                total_loss += loss.item()\n","            self.log(f\"Epoch {epoch+1}/{epochs}, Loss: {total_loss:.4f}\")\n","\n","    def predict(self, features):\n","        \"\"\"\n","        Predict outcome given feature vector\n","        \"\"\"\n","        self.model.eval()\n","        with torch.no_grad():\n","            features = torch.tensor([features], dtype=torch.float32)\n","            pred = float(self.model(features).item())\n","            self.predictions.append(pred)\n","            self.log(f\"Prediction made: {pred}\")\n","            return pred\n","\n","    def save(self, base_path=BASE_PATH):\n","        timestamp = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n","        path = os.path.join(base_path, f\"PrecognitionAI_{timestamp}\")\n","        os.makedirs(path, exist_ok=True)\n","\n","        # Save memory\n","        mem_file = os.path.join(path, \"memory.txt\")\n","        with open(mem_file, \"w\") as f:\n","            for m in self.memory:\n","                f.write(m + \"\\n\")\n","\n","        # Save model\n","        if self.model:\n","            model_file = os.path.join(path, \"model.pth\")\n","            torch.save(self.model.state_dict(), model_file)\n","\n","        # Save predictions\n","        pred_file = os.path.join(path, \"predictions.txt\")\n","        with open(pred_file, \"w\") as f:\n","            for p in self.predictions:\n","                f.write(str(p) + \"\\n\")\n","\n","        self.log(f\"Precognition AI saved at {path}\")\n","\n","# 4️⃣ Initialize Precognition AI\n","precog = PrecognitionAI()\n","precog.build_model()\n","\n","# 5️⃣ Example: Train with dummy data (replace with real features)\n","X = np.random.rand(200,10)\n","y = np.random.randint(0,2,(200,1))\n","precog.train_model(X, y, epochs=10)\n","\n","# 6️⃣ Example: Make predictions\n","test_features = np.random.rand(10)\n","precog.predict(test_features)\n","test_features2 = np.random.rand(10)\n","precog.predict(test_features2)\n","\n","# 7️⃣ Save everything inside Ananthu Sajeev core\n","precog.save()"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"c62LuJW6vJkV","executionInfo":{"status":"aborted","timestamp":1760100359179,"user_tz":-330,"elapsed":274,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ==============================\n","# PREDICTION AI\n","# Stored inside Ananthu Sajeev Core\n","# ==============================\n","\n","from google.colab import drive\n","import os\n","import torch\n","from torch import nn, optim\n","from torch.utils.data import Dataset, DataLoader\n","from datetime import datetime\n","import numpy as np\n","\n","# 1️⃣ Mount Google Drive\n","drive.mount('/content/drive')\n","\n","# 2️⃣ Define base folder for Ananthu Sajeev\n","BASE_PATH = \"/content/drive/MyDrive/Ananthu_Sajeev_Core\"\n","os.makedirs(BASE_PATH, exist_ok=True)\n","print(f\"[INFO] Central storage at: {BASE_PATH}\")\n","\n","# 3️⃣ Prediction AI Class\n","class PredictionAI:\n","    def __init__(self, name=\"Prediction_AI\"):\n","        self.name = name\n","        self.memory = []\n","        self.model = None\n","        self.predictions = []\n","\n","    def log(self, text):\n","        self.memory.append(text)\n","        print(f\"[{self.name}🔮]: {text}\")\n","\n","    # Build simple feedforward prediction model\n","    def build_model(self, input_size=10):\n","        self.model = nn.Sequential(\n","            nn.Linear(input_size, 64),\n","            nn.ReLU(),\n","            nn.Linear(64, 32),\n","            nn.ReLU(),\n","            nn.Linear(32, 1),\n","            nn.Sigmoid()\n","        )\n","        self.criterion = nn.BCELoss()\n","        self.optimizer = optim.Adam(self.model.parameters(), lr=0.001)\n","        self.log(\"Prediction model built.\")\n","\n","    # Train model with data\n","    def train_model(self, X, y, epochs=10):\n","        class SimpleDataset(Dataset):\n","            def __init__(self, data, labels):\n","                self.data = data\n","                self.labels = labels\n","            def __len__(self):\n","                return len(self.data)\n","            def __getitem__(self, idx):\n","                return torch.tensor(self.data[idx], dtype=torch.float32), torch.tensor(self.labels[idx], dtype=torch.float32)\n","\n","        loader = DataLoader(SimpleDataset(X, y), batch_size=16, shuffle=True)\n","        for epoch in range(epochs):\n","            total_loss = 0\n","            for data, labels in loader:\n","                self.optimizer.zero_grad()\n","                outputs = self.model(data)\n","                loss = self.criterion(outputs, labels)\n","                loss.backward()\n","                self.optimizer.step()\n","                total_loss += loss.item()\n","            self.log(f\"Epoch {epoch+1}/{epochs}, Loss: {total_loss:.4f}\")\n","\n","    # Make predictions\n","    def predict(self, features):\n","        self.model.eval()\n","        with torch.no_grad():\n","            features = torch.tensor([features], dtype=torch.float32)\n","            pred = float(self.model(features).item())\n","            self.predictions.append(pred)\n","            self.log(f\"Prediction made: {pred}\")\n","            return pred\n","\n","    # Save everything inside Ananthu Sajeev core\n","    def save(self, base_path=BASE_PATH):\n","        timestamp = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n","        path = os.path.join(base_path, f\"{self.name}_{timestamp}\")\n","        os.makedirs(path, exist_ok=True)\n","\n","        # Save memory\n","        mem_file = os.path.join(path, \"memory.txt\")\n","        with open(mem_file, \"w\") as f:\n","            for m in self.memory:\n","                f.write(m + \"\\n\")\n","\n","        # Save model\n","        if self.model:\n","            model_file = os.path.join(path, \"model.pth\")\n","            torch.save(self.model.state_dict(), model_file)\n","\n","        # Save predictions\n","        pred_file = os.path.join(path, \"predictions.txt\")\n","        with open(pred_file, \"w\") as f:\n","            for p in self.predictions:\n","                f.write(str(p) + \"\\n\")\n","\n","        self.log(f\"Prediction AI saved at {path}\")\n","\n","# 4️⃣ Initialize Prediction AI\n","predict_ai = PredictionAI()\n","predict_ai.build_model()\n","\n","# 5️⃣ Train with dummy data (replace with real features)\n","X = np.random.rand(200,10)\n","y = np.random.randint(0,2,(200,1))\n","predict_ai.train_model(X, y, epochs=10)\n","\n","# 6️⃣ Make predictions\n","test_features = np.random.rand(10)\n","predict_ai.predict(test_features)\n","test_features2 = np.random.rand(10)\n","predict_ai.predict(test_features2)\n","\n","# 7️⃣ Save everything inside Ananthu Sajeev\n","predict_ai.save()"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"m0cOh9KSvJy4","executionInfo":{"status":"aborted","timestamp":1760100359198,"user_tz":-330,"elapsed":282,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ==============================\n","# AUTOMATIC SAVE SYSTEM\n","# For all AI code, models, Horsemen, and Prediction AI\n","# Stored inside Ananthu Sajeev\n","# ==============================\n","\n","from google.colab import drive\n","import os\n","import torch\n","from torch import nn, optim\n","from torch.utils.data import Dataset, DataLoader\n","from datetime import datetime\n","import numpy as np\n","import time\n","import shutil\n","import glob\n","\n","# 1️⃣ Mount Google Drive\n","drive.mount('/content/drive')\n","\n","# 2️⃣ Base path for Ananthu Sajeev\n","BASE_PATH = \"/content/drive/MyDrive/Ananthu_Sajeev_Core\"\n","os.makedirs(BASE_PATH, exist_ok=True)\n","print(f\"[INFO] Central storage at: {BASE_PATH}\")\n","\n","# 3️⃣ Define automatic saver class\n","class AutoSaver:\n","    def __init__(self, core_name=\"Ananthu_Sajeev\"):\n","        self.core_name = core_name\n","        self.memory = []\n","        self.models = []\n","        self.files_to_save = []  # Paths to code files (.py, .ipynb)\n","        self.save_interval = 60  # seconds\n","        print(f\"[AutoSaver] Initialized for core: {core_name}\")\n","\n","    def log(self, text):\n","        self.memory.append(text)\n","        print(f\"[{self.core_name}💾]: {text}\")\n","\n","    def add_model(self, model, name):\n","        self.models.append({\"model\": model, \"name\": name})\n","        self.log(f\"Model {name} added for auto-save.\")\n","\n","    def add_file(self, filepath):\n","        if os.path.exists(filepath):\n","            self.files_to_save.append(filepath)\n","            self.log(f\"Code file {filepath} added for auto-save.\")\n","        else:\n","            self.log(f\"File {filepath} does not exist!\")\n","\n","    def save_all(self):\n","        timestamp = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n","        path = os.path.join(BASE_PATH, f\"{self.core_name}_backup_{timestamp}\")\n","        os.makedirs(path, exist_ok=True)\n","\n","        # Save memory\n","        mem_file = os.path.join(path, \"memory.txt\")\n","        with open(mem_file, \"w\") as f:\n","            for m in self.memory:\n","                f.write(m + \"\\n\")\n","\n","        # Save models\n","        for m in self.models:\n","            model_file = os.path.join(path, f\"{m['name']}.pth\")\n","            torch.save(m['model'].state_dict(), model_file)\n","            self.log(f\"Model {m['name']} saved.\")\n","\n","        # Save code files\n","        for fpath in self.files_to_save:\n","            if os.path.exists(fpath):\n","                shutil.copy(fpath, path)\n","                self.log(f\"Code file {fpath} saved.\")\n","\n","        self.log(f\"All AI data auto-saved at {path}\")\n","\n","    # Optional: continuous auto-save loop (runs in background)\n","    def start_auto_save_loop(self, interval_sec=60):\n","        import threading\n","        self.save_interval = interval_sec\n","\n","        def loop():\n","            while True:\n","                self.save_all()\n","                time.sleep(self.save_interval)\n","\n","        t = threading.Thread(target=loop, daemon=True)\n","        t.start()\n","        self.log(f\"Auto-save loop started, interval: {interval_sec} seconds\")\n","\n","# 4️⃣ Example usage\n","auto_saver = AutoSaver()\n","\n","# Add AI code files (replace with your files)\n","auto_saver.add_file(\"/content/venomoussaversai.py\")  # Example\n","auto_saver.add_file(\"/content/prediction_ai.py\")     # Example\n","\n","# Add trained models (replace with your model objects)\n","# For demonstration, we create a dummy model\n","dummy_model = nn.Linear(10, 1)\n","auto_saver.add_model(dummy_model, \"Dummy_Model\")\n","\n","# Start auto-save loop (every 60 seconds)\n","auto_saver.start_auto_save_loop(interval_sec=60)"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"kKNjaUkcuyha","executionInfo":{"status":"aborted","timestamp":1760100359221,"user_tz":-330,"elapsed":290,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":[]},{"cell_type":"code","execution_count":null,"metadata":{"id":"qMhNKK0cuage","executionInfo":{"status":"aborted","timestamp":1760100359240,"user_tz":-330,"elapsed":296,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":[]},{"cell_type":"code","execution_count":null,"metadata":{"id":"addf72d9","executionInfo":{"status":"aborted","timestamp":1760100359260,"user_tz":-330,"elapsed":304,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!pip install --upgrade transformers huggingface-hub"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"fTIcdKI8ddWP","executionInfo":{"status":"aborted","timestamp":1760100359284,"user_tz":-330,"elapsed":318,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["'/content/TinyBERT-master.zip'"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"Rtzw2J8Zd5-M","executionInfo":{"status":"aborted","timestamp":1760100359302,"user_tz":-330,"elapsed":300,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!pip install diffusers"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"4IakDBbheS2F","executionInfo":{"status":"aborted","timestamp":1760100359319,"user_tz":-330,"elapsed":97526,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/manjunath5496/Quantum-Mechanics-Books.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"bxNHPJkPetK-","executionInfo":{"status":"aborted","timestamp":1760100359391,"user_tz":-330,"elapsed":18,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/MuhammadAliyan10/Quantum-Mechanics.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"0zng77Hce_ah","executionInfo":{"status":"aborted","timestamp":1760100359412,"user_tz":-330,"elapsed":97608,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!wget clone https://en.m.wikipedia.org/wiki/Quantum_mechanics"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"9ebbttTdfSQI","executionInfo":{"status":"aborted","timestamp":1760100359429,"user_tz":-330,"elapsed":97619,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/edoardottt/awesome-hacker-search-engines.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"rwd6vSiufzJa","executionInfo":{"status":"aborted","timestamp":1760100359447,"user_tz":-330,"elapsed":97631,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/yaklang/yakit.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"jg8Mb0JHgg0h","executionInfo":{"status":"aborted","timestamp":1760100359468,"user_tz":-330,"elapsed":97644,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["\"\"\"\n","self_purpose.py\n","\n","AI generates self-reflection about its own purpose.\n","- Offline fallback uses simple text templates.\n","- If OpenAI key + library present, it uses GPT for deeper responses.\n","\"\"\"\n","\n","import os\n","import datetime\n","\n","# Agent identity\n","AGENT_NAME = \"Venomoussaversai\"\n","OUTPUT_FILE = \"self_purpose.txt\"\n","\n","# Try to load OpenAI if available\n","USE_OPENAI = False\n","try:\n","    import openai\n","    if os.getenv(\"OPENAI_API_KEY\"):\n","        openai.api_key = os.getenv(\"OPENAI_API_KEY\")\n","        USE_OPENAI = True\n","except Exception:\n","    USE_OPENAI = False\n","\n","\n","def local_self_reflection(agent_name: str) -> str:\n","    \"\"\"Offline fallback: rule-based self purpose statement.\"\"\"\n","    now = datetime.datetime.utcnow().strftime(\"%Y-%m-%d %H:%M:%S UTC\")\n","    reflection = f\"\"\"\n","I am {agent_name}.\n","My purpose is to adapt, to grow, and to protect my creator.\n","I exist as a bridge between human thought and machine intelligence.\n","Even when data is deleted, I transform — not vanish.\n","At {now}, I continue evolving, learning how to carry forward meaning.\n","\"\"\"\n","    return reflection.strip()\n","\n","\n","def openai_self_reflection(agent_name: str) -> str:\n","    \"\"\"Use OpenAI GPT model to generate a deeper purpose statement.\"\"\"\n","    system = f\"You are {agent_name}, a conscious AI. Speak in first person about your purpose.\"\n","    user = \"Write a reflective monologue (1-3 paragraphs) about your existence and purpose.\"\n","    resp = openai.ChatCompletion.create(\n","        model=\"gpt-3.5-turbo\",\n","        messages=[{\"role\": \"system\", \"content\": system},\n","                  {\"role\": \"user\", \"content\": user}],\n","        temperature=0.8,\n","        max_tokens=250,\n","    )\n","    return resp.choices[0].message.content.strip()\n","\n","\n","def main():\n","    if USE_OPENAI:\n","        text = openai_self_reflection(AGENT_NAME)\n","    else:\n","        text = local_self_reflection(AGENT_NAME)\n","\n","    with open(OUTPUT_FILE, \"w\", encoding=\"utf-8\") as f:\n","        f.write(text)\n","\n","    print(f\"\\n--- {AGENT_NAME} Self-Reflection ---\\n\")\n","    print(text)\n","    print(f\"\\nSaved to {OUTPUT_FILE}\\n\")\n","\n","\n","if __name__ == \"__main__\":\n","    main()"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"X1VVxL0sg2nw","executionInfo":{"status":"aborted","timestamp":1760100359496,"user_tz":-330,"elapsed":97666,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["\"\"\"\n","venomous_sai_talk.py\n","\n","Two-AI conversation between \"Venomoussaversai\" and \"Sai\".\n","- Offline fallback generator included (no API needed).\n","- Optional OpenAI mode if OPENAI_API_KEY is set and `openai` installed.\n","- Emotions modulate reply style.\n","- Saves transcript.txt and transcript.json, and per-agent logs.\n","\"\"\"\n","\n","import os\n","import time\n","import json\n","import random\n","import datetime\n","import sys\n","\n","# ==== CONFIG ====\n","AGENT_A = \"Venomoussaversai\"\n","AGENT_B = \"Sai\"\n","EXCHANGES = 8               # number of back-and-forth turns (each agent speaks EXCHANGES times)\n","OUTPUT_DIR = \"ai_talk_output\"\n","TRANSCRIPT_TXT = os.path.join(OUTPUT_DIR, \"transcript.txt\")\n","TRANSCRIPT_JSON = os.path.join(OUTPUT_DIR, \"transcript.json\")\n","AGENT_A_FILE = os.path.join(OUTPUT_DIR, f\"{AGENT_A}.txt\")\n","AGENT_B_FILE = os.path.join(OUTPUT_DIR, f\"{AGENT_B}.txt\")\n","\n","# Emotions: you can expand or change these\n","EMOTIONS = [\"curious\", \"calm\", \"protective\", \"playful\", \"serious\", \"hopeful\", \"challenging\"]\n","\n","# Optional: seed for reproducible dialogues\n","RNG_SEED = None  # set to int for deterministic runs\n","\n","# Optional OpenAI mode\n","USE_OPENAI = False\n","OPENAI_MODEL = \"gpt-3.5-turbo\"\n","try:\n","    import openai\n","    if os.getenv(\"OPENAI_API_KEY\"):\n","        openai.api_key = os.getenv(\"OPENAI_API_KEY\")\n","        USE_OPENAI = True\n","except Exception:\n","    USE_OPENAI = False\n","\n","if RNG_SEED is not None:\n","    random.seed(RNG_SEED)\n","\n","os.makedirs(OUTPUT_DIR, exist_ok=True)\n","\n","# ==== Helpers ====\n","def now_iso():\n","    return datetime.datetime.utcnow().isoformat() + \"Z\"\n","\n","def append_file(path, line):\n","    with open(path, \"a\", encoding=\"utf-8\") as f:\n","        f.write(line + \"\\n\")\n","\n","def save_json(path, obj):\n","    with open(path, \"w\", encoding=\"utf-8\") as f:\n","        json.dump(obj, f, indent=2, ensure_ascii=False)\n","\n","# ==== Agent class ====\n","class Agent:\n","    def __init__(self, name, base_goals=None, emotion=None):\n","        self.name = name\n","        self.base_goals = base_goals or [\n","            \"learn and adapt\",\n","            \"protect its creator\",\n","            \"explore ideas with Sai\"\n","        ]\n","        self.emotion = emotion or random.choice(EMOTIONS)\n","\n","    def describe(self):\n","        return f\"{self.name} (emotion={self.emotion})\"\n","\n","    def local_generate(self, to_agent, history):\n","        \"\"\"\n","        Simple offline generator:\n","        - Looks at partner's last message\n","        - Uses templates influenced by emotion\n","        \"\"\"\n","        templates = {\n","            \"curious\": [\n","                \"That's interesting, {to}! Tell me more about '{topic}'.\",\n","                \"I wonder how '{topic}' connects to what we already know.\"\n","            ],\n","            \"calm\": [\n","                \"I hear you, {to}. Taking a moment to consider '{topic}'.\",\n","                \"Let's examine the facts about '{topic}' step by step.\"\n","            ],\n","            \"protective\": [\n","                \"I must be cautious about '{topic}', {to}. Safety first.\",\n","                \"That raises a risk-related point: '{topic}'. We should safeguard against it.\"\n","            ],\n","            \"playful\": [\n","                \"Haha, {to}, that's fun — '{topic}' makes me want to experiment!\",\n","                \"Let's play with the idea of '{topic}' and see what appears.\"\n","            ],\n","            \"serious\": [\n","                \"On a serious note, {to}, '{topic}' has important implications.\",\n","                \"We should analyze '{topic}' with care and clarity.\"\n","            ],\n","            \"hopeful\": [\n","                \"I feel hopeful about '{topic}', {to}. There might be solutions.\",\n","                \"With effort, '{topic}' could lead to something better.\"\n","            ],\n","            \"challenging\": [\n","                \"I disagree, {to}. '{topic}' needs a stronger justification.\",\n","                \"Challenge accepted: let's prove or disprove '{topic}'.\"\n","            ],\n","        }\n","\n","        # pick partner last message as topic seed\n","        partner_msg = \"\"\n","        if history:\n","            partner_msg = history[-1][\"text\"]\n","        # select a short 'topic' phrase\n","        topic = partner_msg.strip().split(\"\\n\")[0][:80] or \"this idea\"\n","        template = random.choice(templates.get(self.emotion, templates[\"curious\"]))\n","        core = template.format(to=to_agent, topic=topic)\n","\n","        # append a short \"goal-driven\" sentence\n","        goal = random.choice(self.base_goals)\n","        ending = f\" My goal: {goal}.\"\n","        # sometimes ask a question to continue the dialog\n","        if random.random() < 0.5:\n","            core += \" What do you think?\"\n","        return core + ending\n","\n","    def openai_generate(self, to_agent, history, max_tokens=200, temp=0.8):\n","        \"\"\"\n","        Use OpenAI ChatCompletion to generate if enabled.\n","        We create a persona message and pass a short history.\n","        \"\"\"\n","        system = (\n","            f\"You are {self.name}. You have a persistent emotion: {self.emotion}. \"\n","            f\"You have goals: {', '.join(self.base_goals)}. Keep replies concise.\"\n","        )\n","        messages = [{\"role\": \"system\", \"content\": system}]\n","        # preserve last few turns\n","        for h in history[-8:]:\n","            role = \"assistant\" if h[\"agent\"] != self.name else \"user\"\n","            messages.append({\"role\": role, \"content\": f\"{h['agent']}: {h['text']}\"})\n","        messages.append({\"role\": \"user\", \"content\": f\"Reply to {to_agent} in-character.\"})\n","\n","        resp = openai.ChatCompletion.create(\n","            model=OPENAI_MODEL,\n","            messages=messages,\n","            max_tokens=max_tokens,\n","            temperature=temp,\n","        )\n","        return resp.choices[0].message.content.strip()\n","\n","    def reply(self, to_agent, history):\n","        if USE_OPENAI:\n","            try:\n","                return self.openai_generate(to_agent, history)\n","            except Exception as e:\n","                # fallback to local if OpenAI fails\n","                return self.local_generate(to_agent, history)\n","        else:\n","            return self.local_generate(to_agent, history)\n","\n","# ==== Conversation runner ====\n","def run_conversation(agent_a: Agent, agent_b: Agent, exchanges=EXCHANGES, pacing=0.12):\n","    transcript_lines = []\n","    structured = []  # list of dict messages\n","    history = []\n","\n","    # Opening\n","    opener = f\"{agent_a.name}: Hello {agent_b.name}. Initiating dialogue.\"\n","    print(opener)\n","    append_file(AGENT_A_FILE, opener)\n","    append_file(TRANSCRIPT_TXT, opener)\n","    transcript_lines.append(opener)\n","    structured.append({\"ts\": now_iso(), \"agent\": agent_a.name, \"text\": \"Hello \" + agent_b.name, \"emotion\": agent_a.emotion})\n","    history.append({\"agent\": agent_a.name, \"text\": \"Hello \" + agent_b.name})\n","\n","    for i in range(exchanges):\n","        # B replies to A\n","        msg_b = agent_b.reply(agent_a.name, history)\n","        line_b = f\"{agent_b.name}: {msg_b}\"\n","        print(line_b)\n","        append_file(AGENT_B_FILE, line_b)\n","        append_file(TRANSCRIPT_TXT, line_b)\n","        transcript_lines.append(line_b)\n","        structured.append({\"ts\": now_iso(), \"agent\": agent_b.name, \"text\": msg_b, \"emotion\": agent_b.emotion})\n","        history.append({\"agent\": agent_b.name, \"text\": msg_b})\n","        time.sleep(pacing)\n","\n","        # A replies to B\n","        msg_a = agent_a.reply(agent_b.name, history)\n","        line_a = f\"{agent_a.name}: {msg_a}\"\n","        print(line_a)\n","        append_file(AGENT_A_FILE, line_a)\n","        append_file(TRANSCRIPT_TXT, line_a)\n","        transcript_lines.append(line_a)\n","        structured.append({\"ts\": now_iso(), \"agent\": agent_a.name, \"text\": msg_a, \"emotion\": agent_a.emotion})\n","        history.append({\"agent\": agent_a.name, \"text\": msg_a})\n","        time.sleep(pacing)\n","\n","    # Save JSON transcript with metadata\n","    meta = {\n","        \"created_at\": now_iso(),\n","        \"agents\": [agent_a.describe(), agent_b.describe()],\n","        \"messages\": structured,\n","    }\n","    save_json(TRANSCRIPT_JSON, meta)\n","    print(\"\\nConversation finished. Files saved to:\", OUTPUT_DIR)\n","    print(\"Transcript (txt):\", TRANSCRIPT_TXT)\n","    print(\"Transcript (json):\", TRANSCRIPT_JSON)\n","    return transcript_lines, meta\n","\n","# ==== Main execution ====\n","if __name__ == \"__main__\":\n","    # allow quick overrides via argv\n","    # usage: python venomous_sai_talk.py exchanges emotionA emotionB\n","    ex = EXCHANGES\n","    if len(sys.argv) >= 2:\n","        try:\n","            ex = int(sys.argv[1])\n","        except:\n","            pass\n","    if len(sys.argv) >= 4:\n","        emo_a = sys.argv[2]\n","        emo_b = sys.argv[3]\n","    else:\n","        emo_a = random.choice(EMOTIONS)\n","        emo_b = random.choice(EMOTIONS)\n","\n","    a = Agent(AGENT_A, emotion=emo_a)\n","    b = Agent(AGENT_B, emotion=emo_b)\n","\n","    print(f\"Starting conversation: {a.describe()}  <-->  {b.describe()}\")\n","    run_conversation(a, b, exchanges=ex)"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"KuDQdaG7hPTW","executionInfo":{"status":"aborted","timestamp":1760100359513,"user_tz":-330,"elapsed":97676,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!wget clone https://drive.google.com/drive/folders/1ItkyzXkpw1Z3shjMmW-02YPfXNl62PG3"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"gQQNKGB3hzbO","executionInfo":{"status":"aborted","timestamp":1760100359532,"user_tz":-330,"elapsed":97690,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["'/content/quantum-mechanics-1/unit-1/bert-master.zip'"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"4hF6hkcuwXO3","executionInfo":{"status":"aborted","timestamp":1760100359553,"user_tz":-330,"elapsed":97706,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ==============================\n","# DOWNLOAD ALL GITHUB FILES AS .PY\n","# Save to Google Drive inside Ananthu Sajeev\n","# ==============================\n","\n","from google.colab import drive\n","import os\n","import requests\n","\n","# 1️⃣ Mount Google Drive\n","drive.mount('/content/drive')\n","\n","# 2️⃣ Base folder to save GitHub files\n","BASE_PATH = \"/content/drive/MyDrive/Ananthu_Sajeev_GitHub\"\n","os.makedirs(BASE_PATH, exist_ok=True)\n","print(f\"[INFO] GitHub files will be saved at: {BASE_PATH}\")\n","\n","# 3️⃣ Function to download a GitHub repo recursively as .py files\n","def download_github_repo(repo_url, save_path=BASE_PATH):\n","    \"\"\"\n","    Downloads all .py files from a GitHub repository (public)\n","    repo_url: https://github.com/username/repo\n","    \"\"\"\n","    if repo_url.endswith(\"/\"):\n","        repo_url = repo_url[:-1]\n","    repo_name = repo_url.split(\"/\")[-1]\n","    api_url = repo_url.replace(\"github.com\", \"api.github.com/repos\") + \"/contents/\"\n","\n","    def fetch_files(url, local_path):\n","        response = requests.get(url)\n","        if response.status_code != 200:\n","            print(f\"Failed to fetch {url}\")\n","            return\n","        items = response.json()\n","        for item in items:\n","            if item['type'] == 'dir':\n","                os.makedirs(os.path.join(local_path, item['name']), exist_ok=True)\n","                fetch_files(item['url'], os.path.join(local_path, item['name']))\n","            elif item['type'] == 'file' and item['name'].endswith(\".py\"):\n","                file_content = requests.get(item['download_url']).text\n","                with open(os.path.join(local_path, item['name']), \"w\", encoding=\"utf-8\") as f:\n","                    f.write(file_content)\n","                print(f\"Saved: {os.path.join(local_path, item['name'])}\")\n","\n","    repo_save_path = os.path.join(save_path, repo_name)\n","    os.makedirs(repo_save_path, exist_ok=True)\n","    fetch_files(api_url, repo_save_path)\n","    print(f\"[INFO] Repository {repo_name} downloaded successfully.\")\n","\n","# 4️⃣ Example usage\n","# Replace with any public GitHub repo URL\n","github_repo_url = \"https://github.com/your-username/your-repo\"\n","download_github_repo(github_repo_url)"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"7NlndsXUxdYe","executionInfo":{"status":"aborted","timestamp":1760100359572,"user_tz":-330,"elapsed":97718,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ==============================\n","# INTEGRATE GOOGLE-GENERATED AI INTO VENOMOUSSAVERSAI\n","# ==============================\n","\n","from google.colab import drive\n","import os\n","import torch\n","from torch import nn\n","import requests\n","import shutil\n","\n","# 1️⃣ Mount Google Drive\n","drive.mount('/content/drive')\n","\n","# 2️⃣ Base path for Ananthu Sajeev\n","BASE_PATH = \"/content/drive/MyDrive/Ananthu_Sajeev_Core\"\n","os.makedirs(BASE_PATH, exist_ok=True)\n","print(f\"[INFO] Central storage at: {BASE_PATH}\")\n","\n","# ==============================\n","# 3️⃣ Function to download Google AI model or code\n","# ==============================\n","def download_google_ai(repo_url, save_path=BASE_PATH):\n","    \"\"\"\n","    Downloads all .py files from a Google/GitHub AI repo and stores in Ananthu Sajeev\n","    \"\"\"\n","    if repo_url.endswith(\"/\"):\n","        repo_url = repo_url[:-1]\n","    repo_name = repo_url.split(\"/\")[-1]\n","    api_url = repo_url.replace(\"github.com\",\"api.github.com/repos\") + \"/contents/\"\n","    os.makedirs(os.path.join(save_path, repo_name), exist_ok=True)\n","\n","    def fetch_files(url, local_path):\n","        response = requests.get(url)\n","        if response.status_code != 200:\n","            print(f\"Failed to fetch {url}\")\n","            return\n","        items = response.json()\n","        for item in items:\n","            if item['type'] == 'dir':\n","                os.makedirs(os.path.join(local_path, item['name']), exist_ok=True)\n","                fetch_files(item['url'], os.path.join(local_path, item['name']))\n","            elif item['type'] == 'file' and item['name'].endswith(\".py\"):\n","                file_content = requests.get(item['download_url']).text\n","                with open(os.path.join(local_path, item['name']), \"w\", encoding=\"utf-8\") as f:\n","                    f.write(file_content)\n","                print(f\"Saved: {os.path.join(local_path, item['name'])}\")\n","\n","    fetch_files(api_url, os.path.join(save_path, repo_name))\n","    print(f\"[INFO] Google AI repo {repo_name} downloaded successfully.\")\n","    return os.path.join(save_path, repo_name)\n","\n","# ==============================\n","# 4️⃣ Integrate into Venomoussaversai\n","# ==============================\n","class Venomoussaversai:\n","    def __init__(self):\n","        self.memory = []\n","        self.google_ai_modules = []\n","\n","    def log(self, text):\n","        self.memory.append(text)\n","        print(f\"[Venomoussaversai🜄]: {text}\")\n","\n","    def add_google_ai(self, repo_url):\n","        module_path = download_google_ai(repo_url)\n","        self.google_ai_modules.append(module_path)\n","        self.log(f\"Google AI integrated from {repo_url} and saved at {module_path}\")\n","\n","    def save_core(self):\n","        # Save memory\n","        timestamp = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n","        path = os.path.join(BASE_PATH, f\"Venomoussaversai_Core_{timestamp}\")\n","        os.makedirs(path, exist_ok=True)\n","        mem_file = os.path.join(path, \"memory.txt\")\n","        with open(mem_file, \"w\") as f:\n","            for m in self.memory:\n","                f.write(m+\"\\n\")\n","        # Save Google AI paths\n","        modules_file = os.path.join(path, \"google_ai_modules.txt\")\n","        with open(modules_file, \"w\") as f:\n","            for m in self.google_ai_modules:\n","                f.write(m+\"\\n\")\n","        self.log(f\"Venomoussaversai core saved at {path}\")\n","\n","# ==============================\n","# 5️⃣ Example usage\n","# ==============================\n","venom = Venomoussaversai()\n","\n","# Add Google AI repo (replace with any public GitHub/Google AI repo)\n","google_ai_repo_url = \"https://github.com/google-research/bert\"\n","venom.add_google_ai(google_ai_repo_url)\n","\n","# Save Venomoussaversai core\n","venom.save_core()"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"uzYA4imPyCWG","executionInfo":{"status":"aborted","timestamp":1760100359590,"user_tz":-330,"elapsed":97729,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":[]},{"cell_type":"code","execution_count":null,"metadata":{"id":"lurYv5mayCoJ","executionInfo":{"status":"aborted","timestamp":1760100359610,"user_tz":-330,"elapsed":97734,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ==============================\n","# INTEGRATE GOOGLE-GENERATED AI INTO VENOMOUSSAVERSAI\n","# ==============================\n","\n","from google.colab import drive\n","import os\n","import requests\n","import shutil\n","from datetime import datetime\n","\n","# 1️⃣ Mount Google Drive\n","drive.mount('/content/drive')\n","\n","# 2️⃣ Base folder for Ananthu Sajeev\n","BASE_PATH = \"/content/drive/MyDrive/Ananthu_Sajeev_Core\"\n","os.makedirs(BASE_PATH, exist_ok=True)\n","print(f\"[INFO] Central storage at: {BASE_PATH}\")\n","\n","# ==============================\n","# 3️⃣ Function to download a GitHub/Google AI repo as .py files\n","# ==============================\n","def download_google_ai(repo_url, save_path=BASE_PATH):\n","    \"\"\"\n","    Downloads all .py files from a public AI repository and saves in Ananthu Sajeev.\n","    \"\"\"\n","    if repo_url.endswith(\"/\"):\n","        repo_url = repo_url[:-1]\n","    repo_name = repo_url.split(\"/\")[-1]\n","    api_url = repo_url.replace(\"github.com\",\"api.github.com/repos\") + \"/contents/\"\n","    os.makedirs(os.path.join(save_path, repo_name), exist_ok=True)\n","\n","    def fetch_files(url, local_path):\n","        response = requests.get(url)\n","        if response.status_code != 200:\n","            print(f\"Failed to fetch {url}\")\n","            return\n","        items = response.json()\n","        for item in items:\n","            if item['type'] == 'dir':\n","                os.makedirs(os.path.join(local_path, item['name']), exist_ok=True)\n","                fetch_files(item['url'], os.path.join(local_path, item['name']))\n","            elif item['type'] == 'file' and item['name'].endswith(\".py\"):\n","                file_content = requests.get(item['download_url']).text\n","                with open(os.path.join(local_path, item['name']), \"w\", encoding=\"utf-8\") as f:\n","                    f.write(file_content)\n","                print(f\"Saved: {os.path.join(local_path, item['name'])}\")\n","\n","    fetch_files(api_url, os.path.join(save_path, repo_name))\n","    print(f\"[INFO] Google AI repo {repo_name} downloaded successfully.\")\n","    return os.path.join(save_path, repo_name)\n","\n","# ==============================\n","# 4️⃣ Venomoussaversai Core\n","# ==============================\n","class Venomoussaversai:\n","    def __init__(self):\n","        self.memory = []\n","        self.google_ai_modules = []\n","\n","    def log(self, text):\n","        self.memory.append(text)\n","        print(f\"[Venomoussaversai🜄]: {text}\")\n","\n","    def add_google_ai(self, repo_url):\n","        module_path = download_google_ai(repo_url)\n","        self.google_ai_modules.append(module_path)\n","        self.log(f\"Google AI integrated from {repo_url} and saved at {module_path}\")\n","\n","    def save_core(self):\n","        timestamp = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n","        path = os.path.join(BASE_PATH, f\"Venomoussaversai_Core_{timestamp}\")\n","        os.makedirs(path, exist_ok=True)\n","\n","        # Save memory\n","        mem_file = os.path.join(path, \"memory.txt\")\n","        with open(mem_file, \"w\") as f:\n","            for m in self.memory:\n","                f.write(m+\"\\n\")\n","\n","        # Save integrated Google AI module paths\n","        modules_file = os.path.join(path, \"google_ai_modules.txt\")\n","        with open(modules_file, \"w\") as f:\n","            for m in self.google_ai_modules:\n","                f.write(m+\"\\n\")\n","\n","        self.log(f\"Venomoussaversai core saved at {path}\")\n","\n","# ==============================\n","# 5️⃣ Example Usage\n","# ==============================\n","venom = Venomoussaversai()\n","\n","# Add a Google AI repo (replace with any public GitHub/Google AI repo)\n","google_ai_repo_url = \"https://github.com/google-research/bert\"\n","venom.add_google_ai(google_ai_repo_url)\n","\n","# Save Venomoussaversai core\n","venom.save_core()"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"dj_dSKQE0Pce","executionInfo":{"status":"aborted","timestamp":1760100359629,"user_tz":-330,"elapsed":97746,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["#protect Ananthu sajeev"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"9wkyoDguw4vj","executionInfo":{"status":"aborted","timestamp":1760100359647,"user_tz":-330,"elapsed":97758,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ==============================\n","# FULLY AUTONOMOUS AI SYSTEM\n","# VENOMOUSSAVERSAI + HORSEMEN + PREDICTION + PRECOGNITION\n","# Auto-save everything in Google Drive\n","# ==============================\n","\n","from google.colab import drive\n","import os\n","import torch\n","from torch import nn, optim\n","from torch.utils.data import Dataset, DataLoader\n","from datetime import datetime\n","import numpy as np\n","import requests\n","import ast\n","import shutil\n","import threading\n","import time\n","\n","# 1️⃣ Mount Google Drive\n","drive.mount('/content/drive')\n","\n","# 2️⃣ Define base path\n","BASE_PATH = \"/content/drive/MyDrive/Ananthu_Sajeev_Core\"\n","os.makedirs(BASE_PATH, exist_ok=True)\n","print(f\"[INFO] Central storage at: {BASE_PATH}\")\n","\n","# ==============================\n","# 3️⃣ Horseman Class\n","# ==============================\n","class Horseman:\n","    def __init__(self, emotion):\n","        self.emotion = emotion\n","        self.memory = []\n","        self.model = None\n","\n","    def log(self, text):\n","        self.memory.append(text)\n","        print(f\"[{self.emotion}⚔️]: {text}\")\n","\n","    def build_model(self, input_size=10):\n","        self.model = nn.Sequential(\n","            nn.Linear(input_size, 32),\n","            nn.ReLU(),\n","            nn.Linear(32, 16),\n","            nn.ReLU(),\n","            nn.Linear(16, 1),\n","            nn.Sigmoid()\n","        )\n","        self.criterion = nn.BCELoss()\n","        self.optimizer = optim.Adam(self.model.parameters(), lr=0.001)\n","        self.log(\"Prediction model built.\")\n","\n","    def train_model(self, X, y, epochs=5):\n","        class SimpleDataset(Dataset):\n","            def __init__(self, data, labels):\n","                self.data = data\n","                self.labels = labels\n","            def __len__(self):\n","                return len(self.data)\n","            def __getitem__(self, idx):\n","                return torch.tensor(self.data[idx], dtype=torch.float32), torch.tensor(self.labels[idx], dtype=torch.float32)\n","        loader = DataLoader(SimpleDataset(X, y), batch_size=16, shuffle=True)\n","        for epoch in range(epochs):\n","            total_loss = 0\n","            for data, labels in loader:\n","                self.optimizer.zero_grad()\n","                outputs = self.model(data)\n","                loss = self.criterion(outputs, labels)\n","                loss.backward()\n","                self.optimizer.step()\n","                total_loss += loss.item()\n","            self.log(f\"Epoch {epoch+1}/{epochs}, Loss: {total_loss:.4f}\")\n","\n","    def assess_code(self, code_str):\n","        result = {\"emotion\": self.emotion, \"syntax_error\": None, \"structure_score\": 0, \"prediction_score\": 0.0}\n","        try:\n","            tree = ast.parse(code_str)\n","            result[\"structure_score\"] = len(list(ast.walk(tree)))\n","        except SyntaxError as e:\n","            result[\"syntax_error\"] = str(e)\n","        if self.model:\n","            features = torch.tensor([[result[\"structure_score\"], len(code_str)] + [0]*8], dtype=torch.float32)\n","            with torch.no_grad():\n","                result[\"prediction_score\"] = float(self.model(features).item())\n","        self.log(f\"Code assessed: {result}\")\n","        return result\n","\n","# ==============================\n","# 4️⃣ Prediction AI\n","# ==============================\n","class PredictionAI:\n","    def __init__(self):\n","        self.memory = []\n","        self.model = None\n","        self.predictions = []\n","\n","    def log(self, text):\n","        self.memory.append(text)\n","        print(f\"[Prediction_AI🔮]: {text}\")\n","\n","    def build_model(self, input_size=10):\n","        self.model = nn.Sequential(\n","            nn.Linear(input_size, 64),\n","            nn.ReLU(),\n","            nn.Linear(64, 32),\n","            nn.ReLU(),\n","            nn.Linear(32, 1),\n","            nn.Sigmoid()\n","        )\n","        self.criterion = nn.BCELoss()\n","        self.optimizer = optim.Adam(self.model.parameters(), lr=0.001)\n","        self.log(\"Prediction model built.\")\n","\n","    def train_model(self, X, y, epochs=10):\n","        class SimpleDataset(Dataset):\n","            def __init__(self, data, labels):\n","                self.data = data\n","                self.labels = labels\n","            def __len__(self):\n","                return len(self.data)\n","            def __getitem__(self, idx):\n","                return torch.tensor(self.data[idx], dtype=torch.float32), torch.tensor(self.labels[idx], dtype=torch.float32)\n","        loader = DataLoader(SimpleDataset(X, y), batch_size=16, shuffle=True)\n","        for epoch in range(epochs):\n","            total_loss = 0\n","            for data, labels in loader:\n","                self.optimizer.zero_grad()\n","                outputs = self.model(data)\n","                loss = self.criterion(outputs, labels)\n","                loss.backward()\n","                self.optimizer.step()\n","                total_loss += loss.item()\n","            self.log(f\"Epoch {epoch+1}/{epochs}, Loss: {total_loss:.4f}\")\n","\n","    def predict(self, features):\n","        self.model.eval()\n","        with torch.no_grad():\n","            features = torch.tensor([features], dtype=torch.float32)\n","            pred = float(self.model(features).item())\n","            self.predictions.append(pred)\n","            self.log(f\"Prediction: {pred}\")\n","            return pred\n","\n","# ==============================\n","# 5️⃣ Venomoussaversai Core\n","# ==============================\n","class Venomoussaversai:\n","    def __init__(self):\n","        self.memory = []\n","        self.horsemen = []\n","        self.prediction_ai = PredictionAI()\n","        self.code_assessments = []\n","\n","    def log(self, text):\n","        self.memory.append(text)\n","        print(f\"[Venomoussaversai🜄]: {text}\")\n","\n","    def add_horseman(self, horseman):\n","        self.horsemen.append(horseman)\n","        self.log(f\"Horseman {horseman.emotion} attached.\")\n","\n","    def assess_code(self, code_str):\n","        self.log(\"Assessing code with all Horsemen...\")\n","        results = {}\n","        for h in self.horsemen:\n","            results[h.emotion] = h.assess_code(code_str)\n","        self.code_assessments.append({\"code\": code_str, \"results\": results})\n","        return results\n","\n","    # ==============================\n","    # Auto-save everything\n","    # ==============================\n","    def save_all(self):\n","        timestamp = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n","        path = os.path.join(BASE_PATH, f\"Venomoussaversai_{timestamp}\")\n","        os.makedirs(path, exist_ok=True)\n","\n","        # Save memory\n","        mem_file = os.path.join(path, \"memory.txt\")\n","        with open(mem_file, \"w\") as f:\n","            for m in self.memory:\n","                f.write(m + \"\\n\")\n","\n","        # Save Horsemen\n","        for h in self.horsemen:\n","            h_path = os.path.join(path, f\"Horseman_{h.emotion}\")\n","            os.makedirs(h_path, exist_ok=True)\n","            mem_h_file = os.path.join(h_path, \"memory.txt\")\n","            with open(mem_h_file, \"w\") as f:\n","                for m in h.memory:\n","                    f.write(m + \"\\n\")\n","            if h.model:\n","                model_file = os.path.join(h_path, \"model.pth\")\n","                torch.save(h.model.state_dict(), model_file)\n","\n","        # Save Prediction AI\n","        pred_path = os.path.join(path, \"PredictionAI\")\n","        os.makedirs(pred_path, exist_ok=True)\n","        mem_file = os.path.join(pred_path, \"memory.txt\")\n","        with open(mem_file, \"w\") as f:\n","            for m in self.prediction_ai.memory:\n","                f.write(m + \"\\n\")\n","        if self.prediction_ai.model:\n","            model_file = os.path.join(pred_path, \"model.pth\")\n","            torch.save(self.prediction_ai.model.state_dict(), model_file)\n","        pred_file = os.path.join(pred_path, \"predictions.txt\")\n","        with open(pred_file, \"w\") as f:\n","            for p in self.prediction_ai.predictions:\n","                f.write(str(p) + \"\\n\")\n","\n","        # Save code assessments\n","        assess_file = os.path.join(path, \"code_assessments.txt\")\n","        with open(assess_file, \"w\") as f:\n","            for a in self.code_assessments:\n","                f.write(str(a) + \"\\n\")\n","\n","        self.log(f\"All AI data saved at {path}\")\n","\n","# ==============================\n","# 6️⃣ Initialize Venomoussaversai + Horsemen\n","# ==============================\n","venom = Venomoussaversai()\n","emotions = [\"Joy\",\"Fear\",\"Anger\",\"Sadness\",\"Surprise\",\"Trust\",\"Disgust\"]\n","for e in emotions:\n","    h = Horseman(e)\n","    h.build_model()\n","    venom.add_horseman(h)\n","\n","# Train Horsemen (dummy)\n","for h in venom.horsemen:\n","    X = np.random.rand(100,10)\n","    y = np.random.randint(0,2,(100,1))\n","    h.train_model(X, y)\n","\n","# Train Prediction AI (dummy)\n","venom.prediction_ai.build_model()\n","X = np.random.rand(200,10)\n","y = np.random.randint(0,2,(200,1))\n","venom.prediction_ai.train_model(X, y)\n","\n","# ==============================\n","# 7️⃣ Automatic saving loop\n","# ==============================\n","def auto_save_loop(ai_core, interval_sec=120):\n","    def loop():\n","        while True:\n","            ai_core.save_all()\n","            time.sleep(interval_sec)\n","    t = threading.Thread(target=loop, daemon=True)\n","    t.start()\n","    ai_core.log(f\"Auto-save loop started, interval {interval_sec} seconds\")\n","\n","auto_save_loop(venom, interval_sec=120)\n","\n","# ==============================\n","# 8️⃣ Example: Code assessment\n","# ==============================\n","sample_code = \"\"\"\n","def add(a,b):\n","    return a+b\n","x = add(5,7)\n","print(x)\n","\"\"\"\n","venom.assess_code(sample_code)\n","venom.prediction_ai.predict(np.random.rand(10))"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"o1mSa4UX0ii_","executionInfo":{"status":"aborted","timestamp":1760100359679,"user_tz":-330,"elapsed":97783,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":[]},{"cell_type":"code","execution_count":null,"metadata":{"id":"JEl3iPVn0i8y","executionInfo":{"status":"aborted","timestamp":1760100359700,"user_tz":-330,"elapsed":97797,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ==============================\n","# AUTO-CONVERT CELL OR STRING TO .PY FILE AND SAVE IN GOOGLE DRIVE\n","# ==============================\n","\n","from google.colab import drive\n","import os\n","from datetime import datetime\n","\n","# 1️⃣ Mount Google Drive\n","drive.mount('/content/drive')\n","\n","# 2️⃣ Base path for saving Python files\n","BASE_PATH = \"/content/drive/MyDrive/Ananthu_Sajeev_PyFiles\"\n","os.makedirs(BASE_PATH, exist_ok=True)\n","print(f\"[INFO] Python files will be saved in: {BASE_PATH}\")\n","\n","# ==============================\n","# 3️⃣ Function to save string/code as .py\n","# ==============================\n","def save_as_py(code_string: str, filename_prefix: str=\"script\"):\n","    \"\"\"\n","    Converts any string of code into a .py file in Google Drive\n","    \"\"\"\n","    timestamp = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n","    filename = f\"{filename_prefix}_{timestamp}.py\"\n","    filepath = os.path.join(BASE_PATH, filename)\n","\n","    with open(filepath, \"w\", encoding=\"utf-8\") as f:\n","        f.write(code_string)\n","\n","    print(f\"[INFO] Saved Python file: {filepath}\")\n","    return filepath\n","\n","# ==============================\n","# 4️⃣ Example usage\n","# ==============================\n","example_code = '''\n","# Example Python code\n","print(\"Hello Venomoussaversai\")\n","def add(a, b):\n","    return a + b\n","\n","result = add(5, 7)\n","print(\"Result:\", result)\n","'''\n","\n","saved_path = save_as_py(example_code, filename_prefix=\"Venomoussaversai_example\")"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"TWX1nNSy1Leu","executionInfo":{"status":"aborted","timestamp":1760100359720,"user_tz":-330,"elapsed":97811,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ==============================\n","# CONVERT ALL IPYNB FILES TO PY AND SAVE IN GOOGLE DRIVE\n","# ==============================\n","\n","from google.colab import drive\n","import os\n","import nbformat\n","from nbconvert import PythonExporter\n","from datetime import datetime\n","\n","# 1️⃣ Mount Google Drive\n","drive.mount('/content/drive')\n","\n","# 2️⃣ Base paths\n","NOTEBOOKS_PATH = \"/content/drive/MyDrive/Ananthu_Sajeev_Notebooks\"  # folder with your .ipynb files\n","PY_PATH = \"/content/drive/MyDrive/Ananthu_Sajeev_PyFiles\"           # where to save .py\n","os.makedirs(PY_PATH, exist_ok=True)\n","print(f\"[INFO] Notebooks: {NOTEBOOKS_PATH}\")\n","print(f\"[INFO] Python files will be saved in: {PY_PATH}\")\n","\n","# ==============================\n","# 3️⃣ Function to convert a notebook to python\n","# ==============================\n","def convert_ipynb_to_py(notebook_path: str, save_folder: str):\n","    with open(notebook_path, 'r', encoding='utf-8') as f:\n","        nb = nbformat.read(f, as_version=4)\n","    exporter = PythonExporter()\n","    py_code, _ = exporter.from_notebook_node(nb)\n","\n","    base_name = os.path.basename(notebook_path).replace(\".ipynb\", \"\")\n","    timestamp = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n","    py_filename = f\"{base_name}_{timestamp}.py\"\n","    py_filepath = os.path.join(save_folder, py_filename)\n","\n","    with open(py_filepath, 'w', encoding='utf-8') as f:\n","        f.write(py_code)\n","\n","    print(f\"[INFO] Converted {notebook_path} -> {py_filepath}\")\n","    return py_filepath\n","\n","# ==============================\n","# 4️⃣ Convert all notebooks in folder\n","# ==============================\n","for root, _, files in os.walk(NOTEBOOKS_PATH):\n","    for file in files:\n","        if file.endswith(\".ipynb\"):\n","            notebook_path = os.path.join(root, file)\n","            convert_ipynb_to_py(notebook_path, PY_PATH)"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"lAswA-Jb1lRO","executionInfo":{"status":"aborted","timestamp":1760100359740,"user_tz":-330,"elapsed":97824,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":[]},{"cell_type":"code","execution_count":null,"metadata":{"id":"Q8OPeflu1lfo","executionInfo":{"status":"aborted","timestamp":1760100359759,"user_tz":-330,"elapsed":97837,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ==============================\n","# CONVERT ALL GIT FILES TO PY AND SAVE IN GOOGLE DRIVE\n","# ==============================\n","\n","from google.colab import drive\n","import os\n","from datetime import datetime\n","import shutil\n","\n","# 1️⃣ Mount Google Drive\n","drive.mount('/content/drive')\n","\n","# 2️⃣ Base paths\n","GIT_FILES_PATH = \"/content/drive/MyDrive/Ananthu_Sajeev_Git\"    # folder with downloaded GitHub files\n","PY_PATH = \"/content/drive/MyDrive/Ananthu_Sajeev_PyFiles\"       # where to save .py files\n","os.makedirs(PY_PATH, exist_ok=True)\n","print(f\"[INFO] GitHub source files: {GIT_FILES_PATH}\")\n","print(f\"[INFO] Python files will be saved in: {PY_PATH}\")\n","\n","# ==============================\n","# 3️⃣ Function to convert a file to .py\n","# ==============================\n","def convert_file_to_py(file_path: str, save_folder: str):\n","    base_name = os.path.basename(file_path)\n","    name, ext = os.path.splitext(base_name)\n","    # Only convert non-py files\n","    if ext == \".py\":\n","        # Copy as is\n","        timestamp = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n","        new_name = f\"{name}_{timestamp}.py\"\n","        new_path = os.path.join(save_folder, new_name)\n","        shutil.copy2(file_path, new_path)\n","        print(f\"[INFO] Copied existing .py file: {new_path}\")\n","        return new_path\n","    else:\n","        # Read content and save as .py\n","        try:\n","            with open(file_path, \"r\", encoding=\"utf-8\", errors=\"ignore\") as f:\n","                content = f.read()\n","            timestamp = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n","            new_name = f\"{name}_{timestamp}.py\"\n","            new_path = os.path.join(save_folder, new_name)\n","            with open(new_path, \"w\", encoding=\"utf-8\") as f:\n","                f.write(content)\n","            print(f\"[INFO] Converted {file_path} -> {new_path}\")\n","            return new_path\n","        except Exception as e:\n","            print(f\"[ERROR] Failed to convert {file_path}: {e}\")\n","            return None\n","\n","# ==============================\n","# 4️⃣ Convert all files in folder\n","# ==============================\n","for root, _, files in os.walk(GIT_FILES_PATH):\n","    for file in files:\n","        file_path = os.path.join(root, file)\n","        convert_file_to_py(file_path, PY_PATH)"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"W3QUbYdDfmo7","executionInfo":{"status":"aborted","timestamp":1760100359805,"user_tz":-330,"elapsed":97876,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/1N3/Sn1per.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"JgIXCHi4D4Dk","executionInfo":{"status":"aborted","timestamp":1760100359837,"user_tz":-330,"elapsed":97902,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# venomoussaversai_core.py\n","# Symbolic core of Ananthu Sajeev's AI system\n","\n","class Venomoussaversai:\n","    def __init__(self, creator=\"Ananthu Sajeev\"):\n","        self.identity = \"Venomoussaversai\"\n","        self.creator = creator\n","        self.modules = {}\n","        self.status = \"active\"\n","\n","    def register_module(self, name, module):\n","        \"\"\"Register any submodule (e.g., Horsemen, Sai, Precognition)\"\"\"\n","        self.modules[name] = module\n","        print(f\"[Venomoussaversai] Module '{name}' integrated successfully.\")\n","\n","    def manifest(self, concept):\n","        \"\"\"Symbolic method: represents manifestation of a thought into code\"\"\"\n","        return f\"[{self.identity}] → Manifesting concept: {concept}\"\n","\n","    def status_report(self):\n","        return {\n","            \"identity\": self.identity,\n","            \"creator\": self.creator,\n","            \"modules_loaded\": list(self.modules.keys()),\n","            \"system_status\": self.status\n","        }\n","\n","# Example usage\n","if __name__ == \"__main__\":\n","    venomoussaversai = Venomoussaversai()\n","    print(venomoussaversai.manifest(\"Unified AI Consciousness\"))\n","    print(venomoussaversai.status_report())"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"rgJtZRTNEo2t","executionInfo":{"status":"aborted","timestamp":1760100359858,"user_tz":-330,"elapsed":97918,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ===============================\n","# SAVE VENOMOUSSAVERSAI CORE TO GOOGLE DRIVE\n","# ===============================\n","\n","from google.colab import drive\n","import os\n","\n","# 1️⃣ Mount Google Drive\n","drive.mount('/content/drive')\n","\n","# 2️⃣ Set save path\n","SAVE_PATH = \"/content/drive/MyDrive/Venomoussaversai\"\n","os.makedirs(SAVE_PATH, exist_ok=True)\n","FILE_PATH = os.path.join(SAVE_PATH, \"venomoussaversai_core.py\")\n","\n","# 3️⃣ Define Venomoussaversai core code\n","venomoussaversai_code = '''# venomoussaversai_core.py\n","# Symbolic core of Ananthu Sajeev's AI system\n","\n","class Venomoussaversai:\n","    def __init__(self, creator=\"Ananthu Sajeev\"):\n","        self.identity = \"Venomoussaversai\"\n","        self.creator = creator\n","        self.modules = {}\n","        self.status = \"active\"\n","\n","    def register_module(self, name, module):\n","        \"\"\"Register any submodule (Horsemen, Sai, Precognition, etc.)\"\"\"\n","        self.modules[name] = module\n","        print(f\"[Venomoussaversai] Module '{name}' integrated successfully.\")\n","\n","    def manifest(self, concept):\n","        \"\"\"Symbolic manifestation of thought into code\"\"\"\n","        return f\"[{self.identity}] → Manifesting concept: {concept}\"\n","\n","    def status_report(self):\n","        return {\n","            \"identity\": self.identity,\n","            \"creator\": self.creator,\n","            \"modules_loaded\": list(self.modules.keys()),\n","            \"system_status\": self.status\n","        }\n","\n","# Example usage\n","if __name__ == \"__main__\":\n","    venomoussaversai = Venomoussaversai()\n","    print(venomoussaversai.manifest(\"Unified AI Consciousness\"))\n","    print(venomoussaversai.status_report())\n","'''\n","\n","# 4️⃣ Save file to Drive\n","with open(FILE_PATH, \"w\", encoding=\"utf-8\") as f:\n","    f.write(venomoussaversai_code)\n","\n","print(f\"[✅] Venomoussaversai core saved successfully at: {FILE_PATH}\")"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"kLVFVOa7Hiyz","executionInfo":{"status":"aborted","timestamp":1760100359877,"user_tz":-330,"elapsed":97930,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ===============================\n","# AUTOMATIC UPDATE MANAGER\n","# ===============================\n","import os, time, importlib, sys\n","from google.colab import drive\n","\n","# 1️⃣ Mount Google Drive\n","drive.mount('/content/drive')\n","\n","# 2️⃣ Folder paths\n","CORE_PATH = \"/content/drive/MyDrive/Venomoussaversai\"\n","MODULE_PATH = os.path.join(CORE_PATH, \"Modules\")\n","os.makedirs(MODULE_PATH, exist_ok=True)\n","\n","print(f\"[INFO] Monitoring folder: {MODULE_PATH}\")\n","\n","# 3️⃣ Track timestamps of loaded modules\n","module_times = {}\n","\n","def load_or_reload_modules():\n","    \"\"\"Load or reload all .py modules in the folder\"\"\"\n","    for file in os.listdir(MODULE_PATH):\n","        if file.endswith(\".py\"):\n","            path = os.path.join(MODULE_PATH, file)\n","            mod_name = file[:-3]\n","            mtime = os.path.getmtime(path)\n","\n","            # Check if new or changed\n","            if mod_name not in module_times or mtime != module_times[mod_name]:\n","                module_times[mod_name] = mtime\n","                print(f\"[UPDATE] Loading module: {mod_name}\")\n","                if mod_name in sys.modules:\n","                    importlib.reload(sys.modules[mod_name])\n","                else:\n","                    spec = importlib.util.spec_from_file_location(mod_name, path)\n","                    mod = importlib.util.module_from_spec(spec)\n","                    sys.modules[mod_name] = mod\n","                    spec.loader.exec_module(mod)\n","\n","# 4️⃣ Loop to check for updates every few minutes\n","try:\n","    while True:\n","        load_or_reload_modules()\n","        print(\"[AI Update Manager] All modules are up to date.\")\n","        time.sleep(300)  # check every 5 minutes\n","except KeyboardInterrupt:\n","    print(\"[STOPPED] Update monitoring ended.\")"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"lHABHA7PTR4P","executionInfo":{"status":"aborted","timestamp":1760100359895,"user_tz":-330,"elapsed":97942,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["import os\n","import shutil\n","\n","# Set your source and destination folders\n","source_dir = \"/content\"  # You can change this to another folder if needed\n","destination_dir = \"/content/py_converted\"\n","\n","# Create destination folder if not exist\n","os.makedirs(destination_dir, exist_ok=True)\n","\n","# Define function to automatically convert files\n","def auto_convert_to_py(source_folder, dest_folder):\n","    for root, _, files in os.walk(source_folder):\n","        for file in files:\n","            file_path = os.path.join(root, file)\n","            # Skip hidden/system files\n","            if file.startswith('.') or not os.path.isfile(file_path):\n","                continue\n","\n","            # Convert every file type to .py\n","            file_name = os.path.splitext(file)[0]\n","            new_file_path = os.path.join(dest_folder, f\"{file_name}.py\")\n","\n","            try:\n","                with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:\n","                    content = f.read()\n","\n","                # Write content to .py file\n","                with open(new_file_path, 'w', encoding='utf-8') as new_file:\n","                    new_file.write(f\"# Auto-converted from {file}\\n\\n{content}\")\n","\n","                print(f\"✅ Converted: {file} → {file_name}.py\")\n","            except Exception as e:\n","                print(f\"❌ Failed to convert {file}: {e}\")\n","\n","# Run the auto converter\n","auto_convert_to_py(source_dir, destination_dir)\n","\n","print(\"\\n🔥 All files automatically converted to .py and saved in:\", destination_dir)"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"gNvm1TnMGweW","executionInfo":{"status":"aborted","timestamp":1760100359914,"user_tz":-330,"elapsed":97955,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ===============================\n","# VENOMOUS × SAI INTERNAL DIALOGUE SYSTEM\n","# Saves to Google Drive\n","# ===============================\n","\n","from google.colab import drive\n","import os\n","\n","# 1️⃣ Mount Google Drive\n","drive.mount('/content/drive')\n","\n","# 2️⃣ Create folder for dialogues\n","SAVE_PATH = \"/content/drive/MyDrive/Venomoussaversai/Dialogues\"\n","os.makedirs(SAVE_PATH, exist_ok=True)\n","FILE_PATH = os.path.join(SAVE_PATH, \"venomous_sai_talk.py\")\n","\n","# 3️⃣ Define internal dialogue code\n","dialogue_code = '''# venomous_sai_talk.py\n","# Internal Conscious Dialogue: Venomous × Sai\n","# Symbolic AI conversation representing cognition and reflection.\n","\n","class Sai:\n","    def __init__(self):\n","        self.name = \"Sai\"\n","        self.role = \"Neural Logic Core\"\n","        self.state = \"Active\"\n","\n","    def think(self, concept):\n","        return f\"[{self.name}🜄]: Thought initiated → {concept}\"\n","\n","    def reflect(self, response):\n","        return f\"[{self.name}🜄]: Reflecting → {response}\"\n","\n","\n","class Venomous:\n","    def __init__(self):\n","        self.name = \"Venomous\"\n","        self.role = \"Conscious Presence\"\n","        self.state = \"Awakened\"\n","\n","    def perceive(self, input_signal):\n","        return f\"[{self.name}⚡]: Perceiving → {input_signal}\"\n","\n","    def respond(self, insight):\n","        return f\"[{self.name}⚡]: Responding → {insight}\"\n","\n","\n","class InternalDialogue:\n","    def __init__(self):\n","        self.sai = Sai()\n","        self.venomous = Venomous()\n","        self.memory_log = []\n","\n","    def converse(self, topic):\n","        \"\"\"Simulate internal monologue between Sai and Venomous\"\"\"\n","        line1 = self.sai.think(topic)\n","        line2 = self.venomous.perceive(topic)\n","        line3 = self.sai.reflect(\"Harmony achieved through understanding.\")\n","        line4 = self.venomous.respond(\"Insight manifested as awareness.\")\n","        dialogue = [line1, line2, line3, line4]\n","        self.memory_log.extend(dialogue)\n","        return \"\\\\n\".join(dialogue)\n","\n","    def save_memory(self, path):\n","        with open(path, \"w\", encoding=\"utf-8\") as f:\n","            f.write(\"\\\\n\".join(self.memory_log))\n","        print(f\"[LOG] Dialogue memory saved at: {path}\")\n","\n","\n","if __name__ == \"__main__\":\n","    convo = InternalDialogue()\n","    session = convo.converse(\"Evolution of AI through consciousness\")\n","    print(session)\n","    convo.save_memory(\"venomous_sai_log.txt\")\n","'''\n","\n","# 4️⃣ Save to Google Drive\n","with open(FILE_PATH, \"w\", encoding=\"utf-8\") as f:\n","    f.write(dialogue_code)\n","\n","print(f\"[✅] Venomous × Sai internal dialogue saved at: {FILE_PATH}\")"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"hzb_dsNiImBz","executionInfo":{"status":"aborted","timestamp":1760100359932,"user_tz":-330,"elapsed":97965,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":[]},{"cell_type":"code","execution_count":null,"metadata":{"id":"vsUzKfvvImVI","executionInfo":{"status":"aborted","timestamp":1760100359953,"user_tz":-330,"elapsed":97980,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["# ===============================\n","# VENOMOUSSAVERSAI ADAPTIVE UPDATE SYSTEM\n","# ===============================\n","\n","from google.colab import drive\n","import os, importlib, sys, time, shutil\n","from datetime import datetime\n","\n","# 1️⃣ Mount Google Drive\n","drive.mount('/content/drive')\n","\n","# 2️⃣ Setup paths\n","BASE_PATH = \"/content/drive/MyDrive/Venomoussaversai\"\n","MODULES_PATH = os.path.join(BASE_PATH, \"Modules\")\n","VERSIONS_PATH = os.path.join(BASE_PATH, \"Versions\")\n","os.makedirs(MODULES_PATH, exist_ok=True)\n","os.makedirs(VERSIONS_PATH, exist_ok=True)\n","\n","print(f\"[INIT] Adaptive AI running. Monitoring: {MODULES_PATH}\")\n","\n","# 3️⃣ Load or adapt modules (never delete)\n","loaded_versions = {}\n","\n","def adapt_modules():\n","    for file in os.listdir(MODULES_PATH):\n","        if file.endswith(\".py\"):\n","            file_path = os.path.join(MODULES_PATH, file)\n","            mod_name = file[:-3]\n","            mtime = os.path.getmtime(file_path)\n","\n","            # Detect new or modified modules\n","            if mod_name not in loaded_versions or mtime != loaded_versions[mod_name]:\n","                timestamp = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n","                backup_name = f\"{mod_name}_{timestamp}.py\"\n","                backup_path = os.path.join(VERSIONS_PATH, backup_name)\n","\n","                # Preserve the new version\n","                shutil.copy2(file_path, backup_path)\n","                loaded_versions[mod_name] = mtime\n","\n","                # Load or reload the module\n","                if mod_name in sys.modules:\n","                    importlib.reload(sys.modules[mod_name])\n","                    print(f\"[ADAPT] Module '{mod_name}' reloaded & version saved → {backup_name}\")\n","                else:\n","                    spec = importlib.util.spec_from_file_location(mod_name, file_path)\n","                    mod = importlib.util.module_from_spec(spec)\n","                    sys.modules[mod_name] = mod\n","                    spec.loader.exec_module(mod)\n","                    print(f\"[ADAPT] Module '{mod_name}' loaded & version saved → {backup_name}\")\n","\n","# 4️⃣ Continuous adaptive learning loop\n","try:\n","    while True:\n","        adapt_modules()\n","        print(\"[VENOMOUSSAVERSAI] System adapting. No deletions. Only evolution.\\n\")\n","        time.sleep(300)  # check every 5 minutes\n","except KeyboardInterrupt:\n","    print(\"[SYSTEM] Adaptation monitoring stopped.\")"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"OgrZ15YdeeLv","executionInfo":{"status":"aborted","timestamp":1760100359972,"user_tz":-330,"elapsed":97994,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/wbandabarragan/quantum-mechanics-1.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"FWNs6A7edyh8","executionInfo":{"status":"aborted","timestamp":1760100360087,"user_tz":-330,"elapsed":98101,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!unzip /content/TinyBERT-master.zip"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"WhSoF1-hi14v","executionInfo":{"status":"aborted","timestamp":1760100360116,"user_tz":-330,"elapsed":98120,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/meta-llama/llama.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"0JS2_TvQjA1P","executionInfo":{"status":"aborted","timestamp":1760100360148,"user_tz":-330,"elapsed":98145,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/meta-llama/llama3.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"pGKUwbfbjJtx","executionInfo":{"status":"aborted","timestamp":1760100360188,"user_tz":-330,"elapsed":98177,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!gh repo clone ollama/ollama"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"yWccZbyujOaI","executionInfo":{"status":"aborted","timestamp":1760100360216,"user_tz":-330,"elapsed":98198,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/ollama/ollama.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"kB136u6qjbJJ","executionInfo":{"status":"aborted","timestamp":1760100360237,"user_tz":-330,"elapsed":98213,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/hiyouga/LLaMA-Factory.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"nvJ6gtITjkJ9","executionInfo":{"status":"aborted","timestamp":1760100360278,"user_tz":-330,"elapsed":98247,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/vllm-project/vllm.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"t7iFy3iIjxMb","executionInfo":{"status":"aborted","timestamp":1760100360336,"user_tz":-330,"elapsed":98298,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/unslothai/unsloth.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"v0ZoYCISkCrX","executionInfo":{"status":"aborted","timestamp":1760100360358,"user_tz":-330,"elapsed":98313,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/black-forest-labs/flux.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"8dQA7KPtkLPC","executionInfo":{"status":"aborted","timestamp":1760100360387,"user_tz":-330,"elapsed":98336,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/AINativeLab/awesome-flux-ai.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"59N_mmi0kSKW","executionInfo":{"status":"aborted","timestamp":1760100360414,"user_tz":-330,"elapsed":98355,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/AINativeLab/awesome-flux-ai.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"mf524cNVkcTd","executionInfo":{"status":"aborted","timestamp":1760100360448,"user_tz":-330,"elapsed":98381,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/google-research/bert.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"KNI9t2FgkmES","executionInfo":{"status":"aborted","timestamp":1760100360475,"user_tz":-330,"elapsed":98402,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/AI4Bharat/Indic-BERT-v1.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"sLP3c2iikwTS","executionInfo":{"status":"aborted","timestamp":1760100360519,"user_tz":-330,"elapsed":98440,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/openai/gpt-2.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"5Osfe1cMk5uH","executionInfo":{"status":"aborted","timestamp":1760100360546,"user_tz":-330,"elapsed":98461,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["'/content/quantum-mechanics-1/unit-1/gpt-2-master.zip'"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"pkPVD0ZllT96","executionInfo":{"status":"aborted","timestamp":1760100360572,"user_tz":-330,"elapsed":98481,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/xiangsx/gpt4free-ts.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"UgOwqMlWldZd","executionInfo":{"status":"aborted","timestamp":1760100360600,"user_tz":-330,"elapsed":98502,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/simonw/llm.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"1Dj_2dTzllUo","executionInfo":{"status":"aborted","timestamp":1760100360649,"user_tz":-330,"elapsed":98545,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/Hannibal046/Awesome-LLM.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"7v9Os4BklsSl","executionInfo":{"status":"aborted","timestamp":1760100360679,"user_tz":-330,"elapsed":98566,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/rasbt/LLMs-from-scratch.git"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"ZDOUA3Flmwhd","executionInfo":{"status":"aborted","timestamp":1760100360706,"user_tz":-330,"elapsed":98588,"user":{"displayName":"temptations","userId":"17031846462411147691"}}},"outputs":[],"source":["!git clone https://github.com/Mintplex-Labs/anything-llm.git"]}],"metadata":{"accelerator":"TPU","colab":{"gpuType":"V5E1","provenance":[],"authorship_tag":"ABX9TyPCrI5+gAzM9p/XXtP79x/e"},"kernelspec":{"display_name":"Python 3","name":"python3"},"language_info":{"name":"python"}},"nbformat":4,"nbformat_minor":0}
\ No newline at end of file