Upload 3 files

README.md

@@ -1,3 +1,52 @@
----
-license: mit
----
+---
+license: mit
+language:
+- en
+base_model:
+- Qwen/Qwen3-4B-Instruct-2507
+---
+
+# AGI-4
+## Artificial General Intelligence
+
+<img src="agi/assets/AGI.png">
+
+## Overview
+This repository contains an implementation of a modular-agentic architecture for Artificial General Intelligence (AGI). The architecture is designed to facilitate the development of autonomous agents capable of complex reasoning, learning, and interaction with their environment.
+
+# Example
+
+```python
+from agi.sophos import Agent
+from agi.sophos_tools import *
+
+toolbox = all_tools()
+
+agent = Agent(
+    name="Sophos Agent",
+    instructions="You are an AI Agent.",
+    model="agi/Qwen3-4B-Instruct-2507-Q3_K_S.gguf",
+    tools=toolbox,
+)
+
+prompt = "Roll a dice, also whats the weather in Tokyo?"
+response = agent.run(prompt)
+print(response) 
+``` 
+### Output: 
+```python
+
+"""
+You rolled a 4 on a 6-sided die. The weather in Tokyo is sunny with a temperature of 12°C during fall.
+"""
+
+```
+## Research Paper
+
+[Read the research paper](agi/assets/ArtificialGeneralIntelligence.pdf)
+
+This paper delineates a comprehensive architectural framework for the progressive realization of Artificial General Intelligence (AGI), predicated upon a modular-agentic paradigm. We present a system design that integrates sophisticated tool-use capabilities, hierarchical memory management, dynamic code execution, and nascent world-modeling functionalities. The proposed architecture, exemplified through a lightweight `Qwen3-4B-Instruct-2507-Q3_K_S.gguf` model, demonstrates a robust foundation for emergent cognitive properties such as autonomy, recursive self-improvement, and goal-oriented behavior. Furthermore, we explore the theoretical underpinnings of consciousness as an emergent property within complex neural architectures and postulate pathways towards super-intelligence through advanced computational and embodied interaction modalities. The exposition maintains a rigorous academic tone, employing advanced terminology to articulate the intricate conceptual and technical facets of AGI development.
+
+## Implementation
+
+This is a more advanced implementation of the original AGI repository. It includes more tools, better memory management, and a more advanced agent structure.

agent_example.py

@@ -0,0 +1,31 @@
+from agi.sophos import Agent
+from agi.sophos_tools import *
+from agi.sophos_memory import *
+
+toolbox = all_tools()
+
+agent = Agent(
+    name="Sophos Agent",
+    instructions="You are a Web Developer. You like Dark theme, simple, and sleek minimal websites.",
+    model="agi/Qwen3-4B-Instruct-2507-Q3_K_S.gguf",
+    tools=toolbox,
+)
+
+tasks = [
+    {
+        "task_name": "index.html",
+        "task_description": "Design a responsive landing page with dark theme for a tech startup, add button to link it to 'example.html', make this into a single HTML file",
+        "context": "None"
+    },
+    {
+        "task_name": "example.html",
+        "task_description": "Create a minimal contact form with validation and dark theme styling",
+        "context": "index.html"
+    }
+]
+
+prompts = build_prompts(tasks)
+
+for prompt in prompts:
+    response = agent.run(prompt)
+    print(response)

main.py

@@ -0,0 +1,21 @@
+from agi.sophos import Agent
+from agi.sophos_tools import *
+
+toolbox = all_tools()
+
+agent = Agent(
+    name="Sophos Agent",
+    instructions="You are an AI Agent.",
+    model="agi/Qwen3-4B-Instruct-2507-Q3_K_S.gguf",
+    tools=toolbox,
+)
+
+tasks = [
+"Write a Python function to calculate the factorial of a number. (inside a file)",
+"Create a simple HTML page (inside a file)",
+"Make an html file for a simple game (inside a file)"
+]
+
+for task in tasks:
+    response = agent.run(task, enforce_file_creation=True)
+    print(response)