Migrated from GitHub
Browse files- Dockerfile +73 -0
- ORIGINAL_README.md +10 -0
- acchite.md +226 -0
- app.py +238 -0
- app_gradio.py +212 -0
- desgin.md +773 -0
- entrypoint.sh +16 -0
- pygmyclaw.py +241 -0
- pygmyclaw_multitool.py +210 -0
- requirements.txt +8 -0
- ui.py +38 -0
Dockerfile
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# ----------------------------
|
| 2 |
+
# PygmyClaw Dockerfile
|
| 3 |
+
# ----------------------------
|
| 4 |
+
FROM ubuntu:22.04
|
| 5 |
+
|
| 6 |
+
ENV DEBIAN_FRONTEND=noninteractive
|
| 7 |
+
# Dockerfile snippet
|
| 8 |
+
ENV MODEL_NAME="hf.co/rahul7star/Qwen3-4B-Thinking-2509-Genius-Coder-AI-Full:Q5_K_M"
|
| 9 |
+
ENV OLLAMA_HOST="0.0.0.0:11434"
|
| 10 |
+
ENV PYTHONUNBUFFERED=1
|
| 11 |
+
|
| 12 |
+
# ----------------------------
|
| 13 |
+
# Install system dependencies
|
| 14 |
+
# ----------------------------
|
| 15 |
+
RUN apt-get update && apt-get install -y \
|
| 16 |
+
build-essential \
|
| 17 |
+
libcurl4-openssl-dev \
|
| 18 |
+
libcjson-dev \
|
| 19 |
+
curl \
|
| 20 |
+
python3 \
|
| 21 |
+
python3-pip \
|
| 22 |
+
git \
|
| 23 |
+
zstd \
|
| 24 |
+
sudo \
|
| 25 |
+
&& rm -rf /var/lib/apt/lists/*
|
| 26 |
+
|
| 27 |
+
# ----------------------------
|
| 28 |
+
# Install Ollama
|
| 29 |
+
# ----------------------------
|
| 30 |
+
RUN curl -fsSL https://ollama.com/install.sh | sh
|
| 31 |
+
|
| 32 |
+
# ----------------------------
|
| 33 |
+
# Python dependencies
|
| 34 |
+
# ----------------------------
|
| 35 |
+
RUN pip3 install --upgrade pip \
|
| 36 |
+
&& pip3 install \
|
| 37 |
+
streamlit \
|
| 38 |
+
gradio==4.44.0 \
|
| 39 |
+
huggingface_hub==0.23.5 \
|
| 40 |
+
requests \
|
| 41 |
+
redis \
|
| 42 |
+
huggingface_hub \
|
| 43 |
+
torch \
|
| 44 |
+
torchvision \
|
| 45 |
+
torchaudio
|
| 46 |
+
|
| 47 |
+
# ----------------------------
|
| 48 |
+
# Set working directory
|
| 49 |
+
# ----------------------------
|
| 50 |
+
WORKDIR /workspace
|
| 51 |
+
|
| 52 |
+
# ----------------------------
|
| 53 |
+
# Copy the PygmyClaw repo
|
| 54 |
+
# ----------------------------
|
| 55 |
+
COPY . /workspace/
|
| 56 |
+
|
| 57 |
+
# ----------------------------
|
| 58 |
+
# Ensure scripts are executable
|
| 59 |
+
# ----------------------------
|
| 60 |
+
RUN chmod +x /workspace/entrypoint.sh \
|
| 61 |
+
&& chmod +x /workspace/pygmyclaw.py \
|
| 62 |
+
&& chmod +x /workspace/pygmyclaw_multitool.py \
|
| 63 |
+
&& mkdir -p /workspace/data
|
| 64 |
+
|
| 65 |
+
# ----------------------------
|
| 66 |
+
# Expose UI port for Gradio / Streamlit
|
| 67 |
+
# ----------------------------
|
| 68 |
+
EXPOSE 7860
|
| 69 |
+
|
| 70 |
+
# ----------------------------
|
| 71 |
+
# Entrypoint
|
| 72 |
+
# ----------------------------
|
| 73 |
+
CMD ["/workspace/entrypoint.sh"]
|
ORIGINAL_README.md
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
title: Pyclaw
|
| 3 |
+
emoji: 🐠
|
| 4 |
+
colorFrom: pink
|
| 5 |
+
colorTo: blue
|
| 6 |
+
sdk: docker
|
| 7 |
+
pinned: false
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
acchite.md
ADDED
|
@@ -0,0 +1,226 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
|
| 4 |
+
# 🦾 PygmyClaw Autonomous Agent — End-to-End Design
|
| 5 |
+
|
| 6 |
+
## 1. **Overview**
|
| 7 |
+
|
| 8 |
+
PygmyClaw is a compact AI agent framework designed for **dynamic Python tool execution, speculative decoding, and autonomous task handling**.
|
| 9 |
+
With Hugging Face integration, it can now **store persistent memory, code, and artifacts**, evolving toward a fully autonomous agent like Claude.
|
| 10 |
+
|
| 11 |
+
**Key goals:**
|
| 12 |
+
|
| 13 |
+
* Execute Python code dynamically with dependency management.
|
| 14 |
+
* Generate, edit, and run code via UI.
|
| 15 |
+
* Maintain long-term memory and datasets in Hugging Face.
|
| 16 |
+
* Handle autonomous multi-step workflows with multi-instance speculative decoding.
|
| 17 |
+
|
| 18 |
+
---
|
| 19 |
+
|
| 20 |
+
## 2. **System Components**
|
| 21 |
+
|
| 22 |
+
### 2.1 User Interface
|
| 23 |
+
|
| 24 |
+
* Streamlit-based web UI.
|
| 25 |
+
* **Features:**
|
| 26 |
+
|
| 27 |
+
* Prompt input
|
| 28 |
+
* `/HELP` commands
|
| 29 |
+
* Code generation `/WRITE_PY`
|
| 30 |
+
* Code editing + execution (`CPU` or optional `GPU`)
|
| 31 |
+
* Book, story, or poem management
|
| 32 |
+
* Session logs and downloads
|
| 33 |
+
|
| 34 |
+
---
|
| 35 |
+
|
| 36 |
+
### 2.2 Agent Core — `pygmyclaw.py`
|
| 37 |
+
|
| 38 |
+
* Handles all **user-agent interaction**:
|
| 39 |
+
|
| 40 |
+
* Receives user prompts.
|
| 41 |
+
* Converts LLM output into **JSON tool calls**.
|
| 42 |
+
* Dynamically loads and executes Python tools.
|
| 43 |
+
* **Speculative decoding**:
|
| 44 |
+
|
| 45 |
+
* 3 drafters + 1 verifier for robust output.
|
| 46 |
+
* **Queue system**:
|
| 47 |
+
|
| 48 |
+
* Redis or JSON-file queue for task scheduling.
|
| 49 |
+
* **Artifact management**:
|
| 50 |
+
|
| 51 |
+
* Stores code, logs, and task outputs in workspace.
|
| 52 |
+
* Supports automatic dependency installation.
|
| 53 |
+
|
| 54 |
+
---
|
| 55 |
+
|
| 56 |
+
### 2.3 Python Multitool — `pygmyclaw_multitool.py`
|
| 57 |
+
|
| 58 |
+
* **Tool registry**:
|
| 59 |
+
|
| 60 |
+
* `list_tools_detailed`, `sys_info`, `log_error`, `echo`, etc.
|
| 61 |
+
* **Dynamic tool addition**:
|
| 62 |
+
|
| 63 |
+
* Agents can create new tools that are callable via JSON.
|
| 64 |
+
* **Safe execution sandbox**:
|
| 65 |
+
|
| 66 |
+
* Python subprocess with controlled input/output.
|
| 67 |
+
|
| 68 |
+
---
|
| 69 |
+
|
| 70 |
+
### 2.4 LLM Interaction
|
| 71 |
+
|
| 72 |
+
* **Ollama / HF-hosted model** as backend:
|
| 73 |
+
|
| 74 |
+
* Multi-instance support for **parallel drafters**.
|
| 75 |
+
* Token-based speculative decoding.
|
| 76 |
+
* **Workflow**:
|
| 77 |
+
|
| 78 |
+
```
|
| 79 |
+
User prompt
|
| 80 |
+
↓
|
| 81 |
+
Agent (LLM)
|
| 82 |
+
↓
|
| 83 |
+
JSON tool call
|
| 84 |
+
↓
|
| 85 |
+
Python tool executes
|
| 86 |
+
↓
|
| 87 |
+
Result returned to LLM
|
| 88 |
+
↓
|
| 89 |
+
Final response to user
|
| 90 |
+
```
|
| 91 |
+
* **Dynamic code generation & execution** integrated:
|
| 92 |
+
|
| 93 |
+
* e.g., user asks for PyTorch demo → agent installs PyTorch → generates editable code → runs it in UI.
|
| 94 |
+
|
| 95 |
+
---
|
| 96 |
+
|
| 97 |
+
### 2.5 Persistent Memory — Hugging Face
|
| 98 |
+
|
| 99 |
+
* **Repository:** `rahul7star/pyclaw`
|
| 100 |
+
* **Stores:**
|
| 101 |
+
|
| 102 |
+
* Generated code & scripts
|
| 103 |
+
* Task outputs (`.out`)
|
| 104 |
+
* Logs & session history
|
| 105 |
+
* Dynamic tools and metadata
|
| 106 |
+
* **Mechanism:**
|
| 107 |
+
|
| 108 |
+
* Push artifacts via `huggingface_hub` API
|
| 109 |
+
* Pull existing artifacts for agent memory
|
| 110 |
+
* **Benefits:** Enables **long-term learning**, cross-session continuity, and reproducibility.
|
| 111 |
+
|
| 112 |
+
---
|
| 113 |
+
|
| 114 |
+
### 2.6 Autonomous Task Management
|
| 115 |
+
|
| 116 |
+
* **Queue-based execution**:
|
| 117 |
+
|
| 118 |
+
* Tasks added by user or agent itself.
|
| 119 |
+
* Background processor executes tasks in order.
|
| 120 |
+
* **Speculative execution**:
|
| 121 |
+
|
| 122 |
+
* Multi-instance drafters improve code reliability.
|
| 123 |
+
* Verifier ensures correctness of outputs.
|
| 124 |
+
* **Dynamic tools**:
|
| 125 |
+
|
| 126 |
+
* Tools can evolve or new tools can be created on-the-fly.
|
| 127 |
+
|
| 128 |
+
---
|
| 129 |
+
|
| 130 |
+
### 2.7 Safety & Resource Management
|
| 131 |
+
|
| 132 |
+
* **Code execution sandbox**:
|
| 133 |
+
|
| 134 |
+
* Controlled Python subprocess.
|
| 135 |
+
* Auto cleanup of temporary files.
|
| 136 |
+
* **CPU/GPU selection**:
|
| 137 |
+
|
| 138 |
+
* Default: CPU
|
| 139 |
+
* Optional: GPU if available and environment variable set.
|
| 140 |
+
* **Dependency management**:
|
| 141 |
+
|
| 142 |
+
* Automatic package installation (e.g., PyTorch for user-requested demos).
|
| 143 |
+
|
| 144 |
+
---
|
| 145 |
+
|
| 146 |
+
## 3. **Example User Workflow**
|
| 147 |
+
|
| 148 |
+
**User Prompt:**
|
| 149 |
+
`"Create a neural network demo in Python using PyTorch."`
|
| 150 |
+
|
| 151 |
+
**Agent Actions:**
|
| 152 |
+
|
| 153 |
+
1. Detects PyTorch requirement → installs on CPU.
|
| 154 |
+
2. Generates Python code using `/WRITE_PY`.
|
| 155 |
+
3. Saves code in Hugging Face repo for memory.
|
| 156 |
+
4. Displays code in UI for editing.
|
| 157 |
+
5. Runs code → outputs printed and logged.
|
| 158 |
+
6. Updates agent memory with results and execution logs.
|
| 159 |
+
7. Optionally creates a new dynamic tool for future NN generation.
|
| 160 |
+
|
| 161 |
+
---
|
| 162 |
+
|
| 163 |
+
## 4. **Evolvable Architecture**
|
| 164 |
+
|
| 165 |
+
| Feature | Current Status | Future Evolution |
|
| 166 |
+
| ------------------------- | -------------- | ---------------------------------------------------- |
|
| 167 |
+
| Dynamic Tool Creation | ✅ | Can auto-generate new tools from tasks |
|
| 168 |
+
| Long-Term Memory | ✅ via HF | Add semantic search, embeddings for context |
|
| 169 |
+
| Speculative Decoding | ✅ | Increase drafters, multi-agent cooperation |
|
| 170 |
+
| Autonomous Task Execution | Partial | Recursive task planning, multi-step project handling |
|
| 171 |
+
| Dependency Management | ✅ | Expand to virtual environments per project |
|
| 172 |
+
| Safe Execution | Partial | Containerized execution (Docker/WSL) |
|
| 173 |
+
|
| 174 |
+
---
|
| 175 |
+
|
| 176 |
+
## 5. **Roadmap to Claude-Like Autonomy**
|
| 177 |
+
|
| 178 |
+
1. **Enhance memory:** Semantic embeddings + search in HF repo.
|
| 179 |
+
2. **Recursive reasoning:** Agent generates subtasks autonomously.
|
| 180 |
+
3. **Multi-agent collaboration:** Multiple PygmyClaws coordinate on large projects.
|
| 181 |
+
4. **Learning from outputs:** Store completed tasks + feedback for continuous improvement.
|
| 182 |
+
5. **Safety & isolation:** Dockerized Python execution with resource limits.
|
| 183 |
+
6. **Dynamic UI:** Allow live editing, execution, and visualization of code outputs.
|
| 184 |
+
|
| 185 |
+
---
|
| 186 |
+
|
| 187 |
+
## 6. **Diagram of End-to-End Flow**
|
| 188 |
+
|
| 189 |
+
```
|
| 190 |
+
┌───────────────┐
|
| 191 |
+
│ User Prompt │
|
| 192 |
+
└───────┬───────┘
|
| 193 |
+
│
|
| 194 |
+
▼
|
| 195 |
+
┌───────────────┐
|
| 196 |
+
│ Agent (LLM) │
|
| 197 |
+
└───────┬───────┘
|
| 198 |
+
│ JSON Tool Call
|
| 199 |
+
▼
|
| 200 |
+
┌───────────────┐
|
| 201 |
+
│ Python Tool │
|
| 202 |
+
│ Executes Task │
|
| 203 |
+
└───────┬───────┘
|
| 204 |
+
│ Result
|
| 205 |
+
▼
|
| 206 |
+
┌───────────────┐
|
| 207 |
+
│ Agent (LLM) │
|
| 208 |
+
│ Processes │
|
| 209 |
+
└───────┬───────┘
|
| 210 |
+
│
|
| 211 |
+
▼
|
| 212 |
+
┌───────────────┐
|
| 213 |
+
│ UI Output │
|
| 214 |
+
│ (Code/Result) │
|
| 215 |
+
└───────┬───────┘
|
| 216 |
+
│
|
| 217 |
+
▼
|
| 218 |
+
┌───────────────┐
|
| 219 |
+
│ │
|
| 220 |
+
│ Persistent │
|
| 221 |
+
│ Memory Repo │
|
| 222 |
+
└───────────────┘
|
| 223 |
+
```
|
| 224 |
+
|
| 225 |
+
---
|
| 226 |
+
|
app.py
ADDED
|
@@ -0,0 +1,238 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import streamlit as st
|
| 2 |
+
import re
|
| 3 |
+
import uuid
|
| 4 |
+
import subprocess
|
| 5 |
+
import sys
|
| 6 |
+
from datetime import datetime
|
| 7 |
+
from threading import Thread
|
| 8 |
+
from queue import Queue
|
| 9 |
+
from pygmyclaw import PygmyClaw
|
| 10 |
+
|
| 11 |
+
st.set_page_config(page_title="Py", layout="wide")
|
| 12 |
+
|
| 13 |
+
# --------------------------------------------------
|
| 14 |
+
# GLOBAL STATE
|
| 15 |
+
# --------------------------------------------------
|
| 16 |
+
|
| 17 |
+
if "job_store" not in st.session_state:
|
| 18 |
+
st.session_state.job_store = {}
|
| 19 |
+
|
| 20 |
+
if "job_queue" not in st.session_state:
|
| 21 |
+
st.session_state.job_queue = Queue()
|
| 22 |
+
|
| 23 |
+
if "agent" not in st.session_state:
|
| 24 |
+
st.session_state.agent = PygmyClaw()
|
| 25 |
+
|
| 26 |
+
if "worker_started" not in st.session_state:
|
| 27 |
+
st.session_state.worker_started = False
|
| 28 |
+
|
| 29 |
+
job_store = st.session_state.job_store
|
| 30 |
+
job_queue = st.session_state.job_queue
|
| 31 |
+
agent = st.session_state.agent
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
# --------------------------------------------------
|
| 35 |
+
# BACKGROUND WORKER
|
| 36 |
+
# --------------------------------------------------
|
| 37 |
+
|
| 38 |
+
def worker():
|
| 39 |
+
while True:
|
| 40 |
+
job_id = job_queue.get()
|
| 41 |
+
job = job_store[job_id]
|
| 42 |
+
job["status"] = "running"
|
| 43 |
+
try:
|
| 44 |
+
system_prompt = f"""
|
| 45 |
+
You are a Python coding assistant.
|
| 46 |
+
|
| 47 |
+
Return ONLY runnable Python code.
|
| 48 |
+
Do NOT explain anything.
|
| 49 |
+
|
| 50 |
+
Task:
|
| 51 |
+
{job['prompt']}
|
| 52 |
+
"""
|
| 53 |
+
result = agent.submit_prompt(system_prompt, job["tool"])
|
| 54 |
+
|
| 55 |
+
# ===== FIX =====
|
| 56 |
+
match = re.search(r"```python(.*?)```", result, re.S)
|
| 57 |
+
if match:
|
| 58 |
+
code = match.group(1).strip()
|
| 59 |
+
else:
|
| 60 |
+
code = result.strip()
|
| 61 |
+
# ===============
|
| 62 |
+
|
| 63 |
+
job["response"] = result
|
| 64 |
+
job["code"] = code
|
| 65 |
+
job["status"] = "completed"
|
| 66 |
+
|
| 67 |
+
except Exception as e:
|
| 68 |
+
job["status"] = "failed"
|
| 69 |
+
job["response"] = str(e)
|
| 70 |
+
|
| 71 |
+
job_queue.task_done()
|
| 72 |
+
|
| 73 |
+
# --------------------------------------------------
|
| 74 |
+
# START WORKER
|
| 75 |
+
# --------------------------------------------------
|
| 76 |
+
|
| 77 |
+
if not st.session_state.worker_started:
|
| 78 |
+
|
| 79 |
+
Thread(target=worker, daemon=True).start()
|
| 80 |
+
|
| 81 |
+
st.session_state.worker_started = True
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
# --------------------------------------------------
|
| 85 |
+
# HEADER
|
| 86 |
+
# --------------------------------------------------
|
| 87 |
+
|
| 88 |
+
st.title("🧠 PygmyClaw AI Dev Dashboard")
|
| 89 |
+
|
| 90 |
+
# --------------------------------------------------
|
| 91 |
+
# CREATE TASK
|
| 92 |
+
# --------------------------------------------------
|
| 93 |
+
|
| 94 |
+
with st.expander("🚀 Create AI Task", expanded=True):
|
| 95 |
+
|
| 96 |
+
col1, col2 = st.columns([4,1])
|
| 97 |
+
|
| 98 |
+
prompt = col1.text_area(
|
| 99 |
+
"Prompt",
|
| 100 |
+
height=120,
|
| 101 |
+
placeholder="write a python function to add two numbers",
|
| 102 |
+
value="write a python function to add two numbers"
|
| 103 |
+
)
|
| 104 |
+
|
| 105 |
+
tool = col2.selectbox(
|
| 106 |
+
"Tool",
|
| 107 |
+
["AI Agent"]
|
| 108 |
+
)
|
| 109 |
+
|
| 110 |
+
if col2.button("Create Job"):
|
| 111 |
+
|
| 112 |
+
job_id = str(uuid.uuid4())[:8]
|
| 113 |
+
|
| 114 |
+
job_store[job_id] = {
|
| 115 |
+
"prompt": prompt,
|
| 116 |
+
"tool": tool,
|
| 117 |
+
"status": "queued",
|
| 118 |
+
"response": "",
|
| 119 |
+
"code": "",
|
| 120 |
+
"created": datetime.now().strftime("%H:%M:%S")
|
| 121 |
+
}
|
| 122 |
+
|
| 123 |
+
job_queue.put(job_id)
|
| 124 |
+
|
| 125 |
+
st.success(f"Job {job_id} queued")
|
| 126 |
+
|
| 127 |
+
|
| 128 |
+
# --------------------------------------------------
|
| 129 |
+
# METRICS
|
| 130 |
+
# --------------------------------------------------
|
| 131 |
+
|
| 132 |
+
queued = sum(1 for j in job_store.values() if j["status"] == "queued")
|
| 133 |
+
running = sum(1 for j in job_store.values() if j["status"] == "running")
|
| 134 |
+
done = sum(1 for j in job_store.values() if j["status"] == "completed")
|
| 135 |
+
failed = sum(1 for j in job_store.values() if j["status"] == "failed")
|
| 136 |
+
|
| 137 |
+
col1, col2, col3, col4 = st.columns(4)
|
| 138 |
+
|
| 139 |
+
col1.metric("Queued", queued)
|
| 140 |
+
col2.metric("Running", running)
|
| 141 |
+
col3.metric("Completed", done)
|
| 142 |
+
col4.metric("Failed", failed)
|
| 143 |
+
|
| 144 |
+
st.divider()
|
| 145 |
+
|
| 146 |
+
# --------------------------------------------------
|
| 147 |
+
# JOB DASHBOARD
|
| 148 |
+
# --------------------------------------------------
|
| 149 |
+
|
| 150 |
+
if not job_store:
|
| 151 |
+
st.info("No jobs yet")
|
| 152 |
+
|
| 153 |
+
for job_id, job in list(job_store.items())[::-1]:
|
| 154 |
+
|
| 155 |
+
with st.container():
|
| 156 |
+
|
| 157 |
+
st.subheader(f"Job {job_id}")
|
| 158 |
+
|
| 159 |
+
st.write("Status:", job["status"])
|
| 160 |
+
st.write("Created:", job["created"])
|
| 161 |
+
|
| 162 |
+
st.code(job["prompt"], language="text")
|
| 163 |
+
|
| 164 |
+
# -----------------------
|
| 165 |
+
# AI RESPONSE
|
| 166 |
+
# -----------------------
|
| 167 |
+
|
| 168 |
+
if job.get("response"):
|
| 169 |
+
|
| 170 |
+
st.markdown("### 🤖 AI Response")
|
| 171 |
+
|
| 172 |
+
st.write(job["response"])
|
| 173 |
+
|
| 174 |
+
# -----------------------
|
| 175 |
+
# CODE EDITOR (ALWAYS VISIBLE)
|
| 176 |
+
# -----------------------
|
| 177 |
+
|
| 178 |
+
st.markdown("### 💻 Generated Code")
|
| 179 |
+
|
| 180 |
+
job["code"] = st.text_area(
|
| 181 |
+
"Edit Code",
|
| 182 |
+
value=job.get("code", ""),
|
| 183 |
+
height=220,
|
| 184 |
+
key=f"code_{job_id}"
|
| 185 |
+
)
|
| 186 |
+
|
| 187 |
+
col1, col2 = st.columns(2)
|
| 188 |
+
|
| 189 |
+
# -----------------------
|
| 190 |
+
# RUN CODE
|
| 191 |
+
# -----------------------
|
| 192 |
+
|
| 193 |
+
if col1.button("▶ Run Code", key=f"run_{job_id}"):
|
| 194 |
+
|
| 195 |
+
try:
|
| 196 |
+
|
| 197 |
+
code = job.get("code", "")
|
| 198 |
+
|
| 199 |
+
# detect imports
|
| 200 |
+
imports = re.findall(
|
| 201 |
+
r"^\s*(?:import|from)\s+([\w_]+)",
|
| 202 |
+
code,
|
| 203 |
+
flags=re.MULTILINE
|
| 204 |
+
)
|
| 205 |
+
|
| 206 |
+
# auto install missing packages
|
| 207 |
+
for pkg in imports:
|
| 208 |
+
try:
|
| 209 |
+
__import__(pkg)
|
| 210 |
+
except ImportError:
|
| 211 |
+
subprocess.run(
|
| 212 |
+
[sys.executable, "-m", "pip", "install", pkg],
|
| 213 |
+
check=True
|
| 214 |
+
)
|
| 215 |
+
|
| 216 |
+
local_vars = {}
|
| 217 |
+
|
| 218 |
+
exec(code, {}, local_vars)
|
| 219 |
+
|
| 220 |
+
st.success("Execution Output")
|
| 221 |
+
|
| 222 |
+
st.json(local_vars)
|
| 223 |
+
|
| 224 |
+
except Exception as e:
|
| 225 |
+
|
| 226 |
+
st.error(str(e))
|
| 227 |
+
|
| 228 |
+
# -----------------------
|
| 229 |
+
# DELETE JOB
|
| 230 |
+
# -----------------------
|
| 231 |
+
|
| 232 |
+
if col2.button("Delete Job", key=f"del_{job_id}"):
|
| 233 |
+
|
| 234 |
+
del job_store[job_id]
|
| 235 |
+
|
| 236 |
+
st.rerun()
|
| 237 |
+
|
| 238 |
+
st.divider()
|
app_gradio.py
ADDED
|
@@ -0,0 +1,212 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# app_gradio.py
|
| 2 |
+
import gradio as gr
|
| 3 |
+
import re
|
| 4 |
+
import uuid
|
| 5 |
+
import time
|
| 6 |
+
import contextlib
|
| 7 |
+
from io import StringIO
|
| 8 |
+
from threading import Thread
|
| 9 |
+
from queue import Queue
|
| 10 |
+
from pygmyclaw import PygmyClaw
|
| 11 |
+
|
| 12 |
+
# --------------------------------------------------
|
| 13 |
+
# GLOBAL STATE
|
| 14 |
+
# --------------------------------------------------
|
| 15 |
+
job_store = {}
|
| 16 |
+
job_queue = Queue()
|
| 17 |
+
agent = PygmyClaw()
|
| 18 |
+
auto_refresh_enabled = True # toggle for auto-refresh
|
| 19 |
+
|
| 20 |
+
# --------------------------------------------------
|
| 21 |
+
# HELPER FUNCTIONS
|
| 22 |
+
# --------------------------------------------------
|
| 23 |
+
def clean_code(code):
|
| 24 |
+
"""Remove markdown fences and normalize code indentation."""
|
| 25 |
+
if not code:
|
| 26 |
+
return ""
|
| 27 |
+
code = re.sub(r"```python", "", code)
|
| 28 |
+
code = re.sub(r"```", "", code)
|
| 29 |
+
return code.strip()
|
| 30 |
+
|
| 31 |
+
def extract_explanation(full_result):
|
| 32 |
+
"""Get explanation text from full AI response."""
|
| 33 |
+
text_no_code = re.sub(r"```.*?```", "", full_result, flags=re.S)
|
| 34 |
+
return text_no_code.strip()
|
| 35 |
+
|
| 36 |
+
def extract_code(full_result):
|
| 37 |
+
"""Extract Python code blocks from full AI response."""
|
| 38 |
+
code_blocks = re.findall(r"```(?:python)?\s*(.*?)```", full_result, re.S | re.I)
|
| 39 |
+
code = "\n\n".join([c.strip() for c in code_blocks])
|
| 40 |
+
return code
|
| 41 |
+
|
| 42 |
+
# --------------------------------------------------
|
| 43 |
+
# BACKGROUND WORKER
|
| 44 |
+
# --------------------------------------------------
|
| 45 |
+
def worker():
|
| 46 |
+
"""Process queued jobs with AI agent, extract code and explanation."""
|
| 47 |
+
while True:
|
| 48 |
+
job_id = job_queue.get()
|
| 49 |
+
job = job_store[job_id]
|
| 50 |
+
job["status"] = "running"
|
| 51 |
+
|
| 52 |
+
try:
|
| 53 |
+
prompt = job["prompt"]
|
| 54 |
+
tool = job["tool"]
|
| 55 |
+
|
| 56 |
+
# System prompt
|
| 57 |
+
system_prompt = f"Write Python code ONLY and explain all lines clearly in comments. Task: {prompt}"
|
| 58 |
+
|
| 59 |
+
# Get fresh AI response
|
| 60 |
+
full_result = agent.generate_with_ssd(system_prompt, timeout=120)
|
| 61 |
+
|
| 62 |
+
# Extract code & explanation from response
|
| 63 |
+
code = extract_code(full_result)
|
| 64 |
+
explanation = extract_explanation(full_result)
|
| 65 |
+
|
| 66 |
+
# Update job
|
| 67 |
+
job["raw_result"] = full_result
|
| 68 |
+
job["code"] = code
|
| 69 |
+
job["response"] = explanation
|
| 70 |
+
job["status"] = "completed"
|
| 71 |
+
|
| 72 |
+
except Exception as e:
|
| 73 |
+
job["status"] = "failed"
|
| 74 |
+
job["response"] = str(e)
|
| 75 |
+
finally:
|
| 76 |
+
job_queue.task_done()
|
| 77 |
+
|
| 78 |
+
# Start background worker
|
| 79 |
+
Thread(target=worker, daemon=True).start()
|
| 80 |
+
|
| 81 |
+
# --------------------------------------------------
|
| 82 |
+
# JOB OPERATIONS
|
| 83 |
+
# --------------------------------------------------
|
| 84 |
+
def create_job(prompt, tool):
|
| 85 |
+
job_id = str(uuid.uuid4())[:8]
|
| 86 |
+
job_store[job_id] = {
|
| 87 |
+
"prompt": prompt,
|
| 88 |
+
"tool": tool,
|
| 89 |
+
"status": "queued",
|
| 90 |
+
"response": "",
|
| 91 |
+
"code": "",
|
| 92 |
+
"raw_result": "",
|
| 93 |
+
"created": time.strftime("%H:%M:%S")
|
| 94 |
+
}
|
| 95 |
+
job_queue.put(job_id)
|
| 96 |
+
return f"Job {job_id} queued", job_id
|
| 97 |
+
|
| 98 |
+
def dashboard():
|
| 99 |
+
rows = []
|
| 100 |
+
for job_id, job in reversed(list(job_store.items())):
|
| 101 |
+
rows.append([job_id, job["status"], job["created"], job["prompt"], job.get("code", "")])
|
| 102 |
+
return rows
|
| 103 |
+
|
| 104 |
+
def load_job(job_id):
|
| 105 |
+
job = job_store.get(job_id)
|
| 106 |
+
if not job:
|
| 107 |
+
return "", "", "", ""
|
| 108 |
+
return (
|
| 109 |
+
job.get("prompt", ""),
|
| 110 |
+
job.get("response", ""),
|
| 111 |
+
job.get("code", ""), # editable code
|
| 112 |
+
job.get("status", "")
|
| 113 |
+
)
|
| 114 |
+
|
| 115 |
+
def run_code(code):
|
| 116 |
+
try:
|
| 117 |
+
code = clean_code(code)
|
| 118 |
+
output_buffer = StringIO()
|
| 119 |
+
with contextlib.redirect_stdout(output_buffer):
|
| 120 |
+
exec(code, {})
|
| 121 |
+
result = output_buffer.getvalue()
|
| 122 |
+
return result if result else "✅ Code executed successfully."
|
| 123 |
+
except Exception as e:
|
| 124 |
+
return str(e)
|
| 125 |
+
|
| 126 |
+
def delete_job(job_id):
|
| 127 |
+
if job_id in job_store:
|
| 128 |
+
del job_store[job_id]
|
| 129 |
+
return dashboard()
|
| 130 |
+
|
| 131 |
+
def toggle_auto_refresh():
|
| 132 |
+
global auto_refresh_enabled
|
| 133 |
+
auto_refresh_enabled = not auto_refresh_enabled
|
| 134 |
+
return "✅ Auto-refresh ON" if auto_refresh_enabled else "❌ Auto-refresh OFF"
|
| 135 |
+
|
| 136 |
+
def explain_code(code):
|
| 137 |
+
"""Send the current code to the AI to generate a fresh explanation."""
|
| 138 |
+
code = clean_code(code)
|
| 139 |
+
if not code.strip():
|
| 140 |
+
return "⚠️ No code to explain."
|
| 141 |
+
prompt = f"Explain the following Python code in simple terms:\n```python\n{code}\n```"
|
| 142 |
+
try:
|
| 143 |
+
explanation = agent.generate_with_ssd(prompt, timeout=120)
|
| 144 |
+
# Remove code blocks
|
| 145 |
+
explanation = re.sub(r"```.*?```", "", explanation, flags=re.S).strip()
|
| 146 |
+
return explanation
|
| 147 |
+
except Exception as e:
|
| 148 |
+
return f"⚠️ Error generating explanation: {str(e)}"
|
| 149 |
+
|
| 150 |
+
# --------------------------------------------------
|
| 151 |
+
# GRADIO UI
|
| 152 |
+
# --------------------------------------------------
|
| 153 |
+
with gr.Blocks(title="PygmyClaw AI Dev Dashboard") as demo:
|
| 154 |
+
gr.Markdown("# 🧠 PygmyClaw AI Dev Dashboard")
|
| 155 |
+
|
| 156 |
+
# ---------------- Create Job ----------------
|
| 157 |
+
with gr.Row():
|
| 158 |
+
prompt_input = gr.Textbox(label="Prompt", lines=5, value="write a python function to add two numbers")
|
| 159 |
+
tool_input = gr.Dropdown(["AI Agent"], value="AI Agent", label="Tool")
|
| 160 |
+
create_btn = gr.Button("Create Job")
|
| 161 |
+
create_status = gr.Markdown()
|
| 162 |
+
job_id_input = gr.Textbox(label="Job ID") # auto-filled
|
| 163 |
+
create_btn.click(create_job, inputs=[prompt_input, tool_input], outputs=[create_status, job_id_input])
|
| 164 |
+
|
| 165 |
+
# ---------------- Job Dashboard ----------------
|
| 166 |
+
gr.Markdown("## Job Dashboard")
|
| 167 |
+
job_table = gr.Dataframe(headers=["Job ID", "Status", "Created", "Prompt", "Code"], interactive=False)
|
| 168 |
+
refresh_btn = gr.Button("🔄 Refresh Dashboard")
|
| 169 |
+
refresh_status = gr.Markdown()
|
| 170 |
+
refresh_btn.click(dashboard, inputs=None, outputs=job_table)
|
| 171 |
+
|
| 172 |
+
toggle_btn = gr.Button("⏯ Toggle Auto-Refresh")
|
| 173 |
+
toggle_btn.click(toggle_auto_refresh, inputs=None, outputs=refresh_status)
|
| 174 |
+
|
| 175 |
+
# Auto-refresh dashboard
|
| 176 |
+
def auto_refresh_dashboard():
|
| 177 |
+
if auto_refresh_enabled:
|
| 178 |
+
return dashboard()
|
| 179 |
+
return gr.update()
|
| 180 |
+
refresh_timer = gr.Timer(value=5)
|
| 181 |
+
refresh_timer.tick(auto_refresh_dashboard, inputs=None, outputs=job_table)
|
| 182 |
+
|
| 183 |
+
# ---------------- Selected Job ----------------
|
| 184 |
+
gr.Markdown("## Selected Job Details")
|
| 185 |
+
load_btn = gr.Button("Load Job")
|
| 186 |
+
prompt_box = gr.Textbox(label="Prompt", lines=4)
|
| 187 |
+
response_box = gr.Markdown(label="AI Explanation")
|
| 188 |
+
code_editor = gr.Code(label="Edit Code", language="python", interactive=True)
|
| 189 |
+
status_box = gr.Textbox(label="Status")
|
| 190 |
+
load_btn.click(load_job, inputs=job_id_input, outputs=[prompt_box, response_box, code_editor, status_box])
|
| 191 |
+
|
| 192 |
+
# Auto-refresh selected job
|
| 193 |
+
def auto_refresh_job(job_id):
|
| 194 |
+
if auto_refresh_enabled:
|
| 195 |
+
return load_job(job_id)
|
| 196 |
+
return gr.update(), gr.update(), gr.update(), gr.update()
|
| 197 |
+
detail_timer = gr.Timer(value=40)
|
| 198 |
+
detail_timer.tick(auto_refresh_job, inputs=[job_id_input], outputs=[prompt_box, response_box, code_editor, status_box])
|
| 199 |
+
|
| 200 |
+
# ---------------- Run / Delete / Explain ----------------
|
| 201 |
+
with gr.Row():
|
| 202 |
+
run_btn = gr.Button("▶ Run Code")
|
| 203 |
+
delete_btn = gr.Button("Delete Job")
|
| 204 |
+
explain_btn = gr.Button("💡 Explain Code")
|
| 205 |
+
output_box = gr.Textbox(label="Execution Output", lines=6)
|
| 206 |
+
explanation_box = gr.Markdown(label="Code Explanation")
|
| 207 |
+
run_btn.click(run_code, inputs=code_editor, outputs=output_box)
|
| 208 |
+
delete_btn.click(delete_job, inputs=job_id_input, outputs=job_table)
|
| 209 |
+
explain_btn.click(explain_code, inputs=code_editor, outputs=explanation_box)
|
| 210 |
+
|
| 211 |
+
# ---------------- Launch ----------------
|
| 212 |
+
demo.launch(server_name="0.0.0.0", server_port=7860)
|
desgin.md
ADDED
|
@@ -0,0 +1,773 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
|
| 3 |
+
# design.md
|
| 4 |
+
|
| 5 |
+
# PygmyClaw Agent System
|
| 6 |
+
|
| 7 |
+
```
|
| 8 |
+
app.py → UI
|
| 9 |
+
pygmyclaw.py → AI agent + queue + HF storage
|
| 10 |
+
pygmyclaw_multitool.py → tool execution engine
|
| 11 |
+
tools.json → tool registry stored on HuggingFace
|
| 12 |
+
memory.json → task memory stored on HuggingFace
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
```
|
| 18 |
+
┌───────────────┐
|
| 19 |
+
│ Streamlit │
|
| 20 |
+
│ app.py │
|
| 21 |
+
└──────┬────────┘
|
| 22 |
+
│
|
| 23 |
+
▼
|
| 24 |
+
┌───────────────┐
|
| 25 |
+
│ PygmyClaw │
|
| 26 |
+
│ pygmyclaw.py │
|
| 27 |
+
└──────┬────────┘
|
| 28 |
+
│
|
| 29 |
+
Queue + Agent logic
|
| 30 |
+
│
|
| 31 |
+
▼
|
| 32 |
+
┌─────────────────────┐
|
| 33 |
+
│ pygmyclaw_multitool│
|
| 34 |
+
│ run_tool() │
|
| 35 |
+
└─────────────────────┘
|
| 36 |
+
│
|
| 37 |
+
▼
|
| 38 |
+
HF Storage (tools.json / memory.json)
|
| 39 |
+
|
| 40 |
+
```
|
| 41 |
+
|
| 42 |
+
```
|
| 43 |
+
## 1. Overview
|
| 44 |
+
|
| 45 |
+
PygmyClaw is a **local AI agent framework** designed to run in a **Docker Space**.
|
| 46 |
+
|
| 47 |
+
The system combines:
|
| 48 |
+
|
| 49 |
+
* speculative decoding for faster generation
|
| 50 |
+
* tool-calling architecture
|
| 51 |
+
* dynamic tool creation
|
| 52 |
+
* artifact generation (files/code/data)
|
| 53 |
+
* background task execution
|
| 54 |
+
* interactive UI
|
| 55 |
+
|
| 56 |
+
The goal is to create a **self-extensible AI system** where the agent can:
|
| 57 |
+
|
| 58 |
+
* use tools
|
| 59 |
+
* create new tools
|
| 60 |
+
* generate code
|
| 61 |
+
* install dependencies
|
| 62 |
+
* run programs
|
| 63 |
+
* manage tasks
|
| 64 |
+
* interact through a UI
|
| 65 |
+
|
| 66 |
+
---
|
| 67 |
+
|
| 68 |
+
# 2. High-Level System Architecture
|
| 69 |
+
|
| 70 |
+
```
|
| 71 |
+
User
|
| 72 |
+
↓
|
| 73 |
+
HF Space UI (Gradio)
|
| 74 |
+
↓
|
| 75 |
+
Agent Engine (pygmyclaw.py)
|
| 76 |
+
↓
|
| 77 |
+
Speculative Decoding Engine
|
| 78 |
+
↓
|
| 79 |
+
Tool Call Parser
|
| 80 |
+
↓
|
| 81 |
+
Tool Executor (subprocess)
|
| 82 |
+
↓
|
| 83 |
+
Dynamic Tool Registry
|
| 84 |
+
↓
|
| 85 |
+
Workspace / Artifacts / Queue
|
| 86 |
+
↓
|
| 87 |
+
Result returned to LLM
|
| 88 |
+
```
|
| 89 |
+
|
| 90 |
+
---
|
| 91 |
+
|
| 92 |
+
# 3. System Layers
|
| 93 |
+
|
| 94 |
+
The system is organized into **five layers**.
|
| 95 |
+
|
| 96 |
+
## Layer 1 — User Interface
|
| 97 |
+
|
| 98 |
+
Provides an interactive interface to the agent.
|
| 99 |
+
|
| 100 |
+
Responsibilities:
|
| 101 |
+
|
| 102 |
+
* display chat interaction
|
| 103 |
+
* show generated artifacts
|
| 104 |
+
* provide code editor
|
| 105 |
+
* allow running generated code
|
| 106 |
+
* show execution output
|
| 107 |
+
|
| 108 |
+
UI components:
|
| 109 |
+
|
| 110 |
+
```
|
| 111 |
+
Chat Panel
|
| 112 |
+
Artifact Viewer
|
| 113 |
+
Code Editor
|
| 114 |
+
Execution Console
|
| 115 |
+
```
|
| 116 |
+
|
| 117 |
+
Example layout:
|
| 118 |
+
|
| 119 |
+
```
|
| 120 |
+
----------------------------------
|
| 121 |
+
Chat | Code Editor
|
| 122 |
+
|
|
| 123 |
+
| demo_nn.py
|
| 124 |
+
|
|
| 125 |
+
| [Run] [Save]
|
| 126 |
+
----------------------------------
|
| 127 |
+
Console Output
|
| 128 |
+
----------------------------------
|
| 129 |
+
```
|
| 130 |
+
|
| 131 |
+
---
|
| 132 |
+
|
| 133 |
+
# 4. Layer 2 — Agent Engine
|
| 134 |
+
|
| 135 |
+
Implemented in:
|
| 136 |
+
|
| 137 |
+
```
|
| 138 |
+
pygmyclaw.py
|
| 139 |
+
```
|
| 140 |
+
|
| 141 |
+
This is the **central orchestrator** of the system.
|
| 142 |
+
|
| 143 |
+
Responsibilities:
|
| 144 |
+
|
| 145 |
+
* manage LLM interaction
|
| 146 |
+
* run speculative decoding
|
| 147 |
+
* parse tool calls
|
| 148 |
+
* execute tools
|
| 149 |
+
* maintain context
|
| 150 |
+
* handle queues
|
| 151 |
+
* coordinate artifacts
|
| 152 |
+
|
| 153 |
+
The engine runs an **agent execution loop**.
|
| 154 |
+
|
| 155 |
+
---
|
| 156 |
+
|
| 157 |
+
# 5. Agent Execution Loop
|
| 158 |
+
|
| 159 |
+
The entire system is driven by the following loop.
|
| 160 |
+
|
| 161 |
+
```
|
| 162 |
+
User Prompt
|
| 163 |
+
↓
|
| 164 |
+
Agent (LLM)
|
| 165 |
+
↓
|
| 166 |
+
LLM outputs JSON tool call
|
| 167 |
+
↓
|
| 168 |
+
Tool executes
|
| 169 |
+
↓
|
| 170 |
+
Result returned to LLM
|
| 171 |
+
↓
|
| 172 |
+
LLM continues reasoning
|
| 173 |
+
↓
|
| 174 |
+
Final response
|
| 175 |
+
```
|
| 176 |
+
|
| 177 |
+
Expanded loop:
|
| 178 |
+
|
| 179 |
+
```
|
| 180 |
+
User Prompt
|
| 181 |
+
↓
|
| 182 |
+
LLM reasoning
|
| 183 |
+
↓
|
| 184 |
+
Tool call JSON
|
| 185 |
+
↓
|
| 186 |
+
Tool executor
|
| 187 |
+
↓
|
| 188 |
+
Tool result
|
| 189 |
+
↓
|
| 190 |
+
Context updated
|
| 191 |
+
↓
|
| 192 |
+
LLM reasoning continues
|
| 193 |
+
```
|
| 194 |
+
|
| 195 |
+
The loop stops when the LLM returns **a final answer instead of a tool call**.
|
| 196 |
+
|
| 197 |
+
---
|
| 198 |
+
|
| 199 |
+
# 6. Speculative Decoding Engine
|
| 200 |
+
|
| 201 |
+
PygmyClaw speeds up generation using **speculative decoding**.
|
| 202 |
+
|
| 203 |
+
Architecture:
|
| 204 |
+
|
| 205 |
+
```
|
| 206 |
+
Drafter 1
|
| 207 |
+
Drafter 2
|
| 208 |
+
Drafter 3
|
| 209 |
+
↓
|
| 210 |
+
Verifier
|
| 211 |
+
```
|
| 212 |
+
|
| 213 |
+
Flow:
|
| 214 |
+
|
| 215 |
+
```
|
| 216 |
+
User prompt
|
| 217 |
+
↓
|
| 218 |
+
Draft tokens generated
|
| 219 |
+
↓
|
| 220 |
+
Verifier checks tokens
|
| 221 |
+
↓
|
| 222 |
+
Accept or reject
|
| 223 |
+
```
|
| 224 |
+
|
| 225 |
+
This improves generation speed while maintaining accuracy.
|
| 226 |
+
|
| 227 |
+
Typical configuration:
|
| 228 |
+
|
| 229 |
+
```
|
| 230 |
+
3 draft models
|
| 231 |
+
1 verifier model
|
| 232 |
+
```
|
| 233 |
+
|
| 234 |
+
Each runs in a separate Ollama instance.
|
| 235 |
+
|
| 236 |
+
---
|
| 237 |
+
|
| 238 |
+
# 7. Tool System
|
| 239 |
+
|
| 240 |
+
Tools allow the agent to perform actions outside the LLM.
|
| 241 |
+
|
| 242 |
+
Tools run in an isolated subprocess:
|
| 243 |
+
|
| 244 |
+
```
|
| 245 |
+
pygmyclaw_multitool.py
|
| 246 |
+
```
|
| 247 |
+
|
| 248 |
+
Execution flow:
|
| 249 |
+
|
| 250 |
+
```
|
| 251 |
+
Agent
|
| 252 |
+
↓
|
| 253 |
+
Tool call JSON
|
| 254 |
+
↓
|
| 255 |
+
Subprocess execution
|
| 256 |
+
↓
|
| 257 |
+
Tool result JSON
|
| 258 |
+
```
|
| 259 |
+
|
| 260 |
+
Example tool call:
|
| 261 |
+
|
| 262 |
+
```
|
| 263 |
+
{
|
| 264 |
+
"tool": "sys_info",
|
| 265 |
+
"parameters": {}
|
| 266 |
+
}
|
| 267 |
+
```
|
| 268 |
+
|
| 269 |
+
Tool response:
|
| 270 |
+
|
| 271 |
+
```
|
| 272 |
+
{
|
| 273 |
+
"os": "Linux",
|
| 274 |
+
"python_version": "3.11"
|
| 275 |
+
}
|
| 276 |
+
```
|
| 277 |
+
|
| 278 |
+
---
|
| 279 |
+
|
| 280 |
+
# 8. Tool Categories
|
| 281 |
+
|
| 282 |
+
The system supports multiple tool types.
|
| 283 |
+
|
| 284 |
+
## System Tools
|
| 285 |
+
|
| 286 |
+
```
|
| 287 |
+
sys_info
|
| 288 |
+
list_files
|
| 289 |
+
read_file
|
| 290 |
+
write_file
|
| 291 |
+
```
|
| 292 |
+
|
| 293 |
+
## Environment Tools
|
| 294 |
+
|
| 295 |
+
```
|
| 296 |
+
install_python_package
|
| 297 |
+
check_package_installed
|
| 298 |
+
execute_shell
|
| 299 |
+
```
|
| 300 |
+
|
| 301 |
+
## Code Tools
|
| 302 |
+
|
| 303 |
+
```
|
| 304 |
+
write_python_code
|
| 305 |
+
run_python_file
|
| 306 |
+
format_code
|
| 307 |
+
```
|
| 308 |
+
|
| 309 |
+
## Artifact Tools
|
| 310 |
+
|
| 311 |
+
```
|
| 312 |
+
create_artifact
|
| 313 |
+
update_artifact
|
| 314 |
+
delete_artifact
|
| 315 |
+
```
|
| 316 |
+
|
| 317 |
+
## Agent Tools
|
| 318 |
+
|
| 319 |
+
```
|
| 320 |
+
create_agent
|
| 321 |
+
list_agents
|
| 322 |
+
run_agent
|
| 323 |
+
```
|
| 324 |
+
|
| 325 |
+
---
|
| 326 |
+
|
| 327 |
+
# 9. Dynamic Tool Creation
|
| 328 |
+
|
| 329 |
+
Agents can create new tools dynamically.
|
| 330 |
+
|
| 331 |
+
Example prompt:
|
| 332 |
+
|
| 333 |
+
```
|
| 334 |
+
create a tool to fetch python documentation
|
| 335 |
+
```
|
| 336 |
+
|
| 337 |
+
Agent calls:
|
| 338 |
+
|
| 339 |
+
```
|
| 340 |
+
{
|
| 341 |
+
"tool": "create_tool",
|
| 342 |
+
"parameters": {
|
| 343 |
+
"name": "python_docs",
|
| 344 |
+
"description": "search python docs"
|
| 345 |
+
}
|
| 346 |
+
}
|
| 347 |
+
```
|
| 348 |
+
|
| 349 |
+
System creates:
|
| 350 |
+
|
| 351 |
+
```
|
| 352 |
+
tools/python_docs.py
|
| 353 |
+
```
|
| 354 |
+
|
| 355 |
+
Tool becomes immediately available.
|
| 356 |
+
|
| 357 |
+
This enables **self-extending agents**.
|
| 358 |
+
|
| 359 |
+
---
|
| 360 |
+
|
| 361 |
+
# 10. Tool Discovery
|
| 362 |
+
|
| 363 |
+
At startup the engine scans the tools directory.
|
| 364 |
+
|
| 365 |
+
```
|
| 366 |
+
tools/
|
| 367 |
+
echo.py
|
| 368 |
+
sys_info.py
|
| 369 |
+
run_python.py
|
| 370 |
+
```
|
| 371 |
+
|
| 372 |
+
A tool registry is generated.
|
| 373 |
+
|
| 374 |
+
Example:
|
| 375 |
+
|
| 376 |
+
```
|
| 377 |
+
TOOLS = {
|
| 378 |
+
echo,
|
| 379 |
+
sys_info,
|
| 380 |
+
run_python
|
| 381 |
+
}
|
| 382 |
+
```
|
| 383 |
+
|
| 384 |
+
The tool list is provided to the LLM.
|
| 385 |
+
|
| 386 |
+
---
|
| 387 |
+
|
| 388 |
+
# 11. Artifact System
|
| 389 |
+
|
| 390 |
+
Artifacts are files generated by the agent.
|
| 391 |
+
|
| 392 |
+
Examples:
|
| 393 |
+
|
| 394 |
+
```
|
| 395 |
+
code
|
| 396 |
+
datasets
|
| 397 |
+
documents
|
| 398 |
+
images
|
| 399 |
+
logs
|
| 400 |
+
```
|
| 401 |
+
|
| 402 |
+
Directory structure:
|
| 403 |
+
|
| 404 |
+
```
|
| 405 |
+
artifacts/
|
| 406 |
+
code/
|
| 407 |
+
data/
|
| 408 |
+
documents/
|
| 409 |
+
```
|
| 410 |
+
|
| 411 |
+
Example artifact:
|
| 412 |
+
|
| 413 |
+
```
|
| 414 |
+
artifacts/code/addition.py
|
| 415 |
+
```
|
| 416 |
+
|
| 417 |
+
Artifacts enable **UI interaction**.
|
| 418 |
+
|
| 419 |
+
---
|
| 420 |
+
|
| 421 |
+
# 12. Artifact UI Interaction
|
| 422 |
+
|
| 423 |
+
When artifacts are created the UI displays controls.
|
| 424 |
+
|
| 425 |
+
Example:
|
| 426 |
+
|
| 427 |
+
```
|
| 428 |
+
addition.py
|
| 429 |
+
|
| 430 |
+
Edit
|
| 431 |
+
Run
|
| 432 |
+
Download
|
| 433 |
+
```
|
| 434 |
+
|
| 435 |
+
Artifact metadata may include:
|
| 436 |
+
|
| 437 |
+
```
|
| 438 |
+
language
|
| 439 |
+
dependencies
|
| 440 |
+
runnable
|
| 441 |
+
created_by
|
| 442 |
+
```
|
| 443 |
+
|
| 444 |
+
---
|
| 445 |
+
|
| 446 |
+
# 13. Workspace Environment
|
| 447 |
+
|
| 448 |
+
All agent work occurs in a dedicated workspace.
|
| 449 |
+
|
| 450 |
+
```
|
| 451 |
+
workspace/
|
| 452 |
+
venv/
|
| 453 |
+
artifacts/
|
| 454 |
+
tools/
|
| 455 |
+
agents/
|
| 456 |
+
```
|
| 457 |
+
|
| 458 |
+
The workspace provides:
|
| 459 |
+
|
| 460 |
+
* dependency isolation
|
| 461 |
+
* file management
|
| 462 |
+
* persistent agent data
|
| 463 |
+
|
| 464 |
+
---
|
| 465 |
+
|
| 466 |
+
# 14. Dependency Management
|
| 467 |
+
|
| 468 |
+
Agents may install packages.
|
| 469 |
+
|
| 470 |
+
Example prompt:
|
| 471 |
+
|
| 472 |
+
```
|
| 473 |
+
create a pytorch neural network demo
|
| 474 |
+
```
|
| 475 |
+
|
| 476 |
+
Agent detects dependency:
|
| 477 |
+
|
| 478 |
+
```
|
| 479 |
+
torch
|
| 480 |
+
```
|
| 481 |
+
|
| 482 |
+
Tool call:
|
| 483 |
+
|
| 484 |
+
```
|
| 485 |
+
install_python_package("torch")
|
| 486 |
+
```
|
| 487 |
+
|
| 488 |
+
Installed inside the workspace environment.
|
| 489 |
+
|
| 490 |
+
```
|
| 491 |
+
workspace/venv/
|
| 492 |
+
```
|
| 493 |
+
|
| 494 |
+
---
|
| 495 |
+
|
| 496 |
+
# 15. Code Generation Workflow
|
| 497 |
+
|
| 498 |
+
Example request:
|
| 499 |
+
|
| 500 |
+
```
|
| 501 |
+
create a neural network code demo in python using pytorch
|
| 502 |
+
```
|
| 503 |
+
|
| 504 |
+
Execution flow:
|
| 505 |
+
|
| 506 |
+
```
|
| 507 |
+
User prompt
|
| 508 |
+
↓
|
| 509 |
+
Agent reasoning
|
| 510 |
+
↓
|
| 511 |
+
Install dependency
|
| 512 |
+
↓
|
| 513 |
+
Generate code
|
| 514 |
+
↓
|
| 515 |
+
Save artifact
|
| 516 |
+
↓
|
| 517 |
+
UI displays code
|
| 518 |
+
```
|
| 519 |
+
|
| 520 |
+
Artifact example:
|
| 521 |
+
|
| 522 |
+
```
|
| 523 |
+
artifacts/code/pytorch_nn_demo.py
|
| 524 |
+
```
|
| 525 |
+
|
| 526 |
+
UI shows:
|
| 527 |
+
|
| 528 |
+
```
|
| 529 |
+
Edit
|
| 530 |
+
Run
|
| 531 |
+
Download
|
| 532 |
+
```
|
| 533 |
+
|
| 534 |
+
---
|
| 535 |
+
|
| 536 |
+
# 16. Code Execution Workflow
|
| 537 |
+
|
| 538 |
+
When the user presses **Run**:
|
| 539 |
+
|
| 540 |
+
```
|
| 541 |
+
UI
|
| 542 |
+
↓
|
| 543 |
+
run_python_file tool
|
| 544 |
+
↓
|
| 545 |
+
workspace python interpreter
|
| 546 |
+
↓
|
| 547 |
+
program execution
|
| 548 |
+
↓
|
| 549 |
+
stdout returned
|
| 550 |
+
```
|
| 551 |
+
|
| 552 |
+
Console output appears in the UI.
|
| 553 |
+
|
| 554 |
+
---
|
| 555 |
+
|
| 556 |
+
# 17. Task Queue
|
| 557 |
+
|
| 558 |
+
The system supports background tasks.
|
| 559 |
+
|
| 560 |
+
Queue storage options:
|
| 561 |
+
|
| 562 |
+
```
|
| 563 |
+
Redis
|
| 564 |
+
JSON file
|
| 565 |
+
```
|
| 566 |
+
|
| 567 |
+
Example task:
|
| 568 |
+
|
| 569 |
+
```
|
| 570 |
+
{
|
| 571 |
+
"id": "123",
|
| 572 |
+
"prompt": "generate dataset"
|
| 573 |
+
}
|
| 574 |
+
```
|
| 575 |
+
|
| 576 |
+
Queue worker processes tasks asynchronously.
|
| 577 |
+
|
| 578 |
+
---
|
| 579 |
+
|
| 580 |
+
# 18. Agent Registry
|
| 581 |
+
|
| 582 |
+
Agents are stored as configuration files.
|
| 583 |
+
|
| 584 |
+
```
|
| 585 |
+
agents/
|
| 586 |
+
python_coder.json
|
| 587 |
+
research_agent.json
|
| 588 |
+
```
|
| 589 |
+
|
| 590 |
+
Example agent definition:
|
| 591 |
+
|
| 592 |
+
```
|
| 593 |
+
{
|
| 594 |
+
"name": "python_coder",
|
| 595 |
+
"model": "qwen2.5",
|
| 596 |
+
"tools": [
|
| 597 |
+
"write_python_code",
|
| 598 |
+
"run_python_file"
|
| 599 |
+
]
|
| 600 |
+
}
|
| 601 |
+
```
|
| 602 |
+
|
| 603 |
+
Agents can be created dynamically.
|
| 604 |
+
|
| 605 |
+
---
|
| 606 |
+
|
| 607 |
+
# 19. Redis Usage
|
| 608 |
+
|
| 609 |
+
Redis is optional but improves scalability.
|
| 610 |
+
|
| 611 |
+
Uses:
|
| 612 |
+
|
| 613 |
+
```
|
| 614 |
+
task queue
|
| 615 |
+
agent memory
|
| 616 |
+
caching
|
| 617 |
+
```
|
| 618 |
+
|
| 619 |
+
Configuration can be stored in Redis or local config.
|
| 620 |
+
|
| 621 |
+
---
|
| 622 |
+
|
| 623 |
+
# 20. Hugging Face Space Deployment
|
| 624 |
+
|
| 625 |
+
The system runs inside a Docker Space.
|
| 626 |
+
|
| 627 |
+
Components:
|
| 628 |
+
|
| 629 |
+
```
|
| 630 |
+
Python
|
| 631 |
+
Ollama
|
| 632 |
+
Gradio
|
| 633 |
+
Redis (optional)
|
| 634 |
+
```
|
| 635 |
+
|
| 636 |
+
Startup sequence:
|
| 637 |
+
|
| 638 |
+
```
|
| 639 |
+
Start container
|
| 640 |
+
↓
|
| 641 |
+
Start Ollama
|
| 642 |
+
↓
|
| 643 |
+
Load models
|
| 644 |
+
↓
|
| 645 |
+
Start agent engine
|
| 646 |
+
↓
|
| 647 |
+
Launch UI
|
| 648 |
+
```
|
| 649 |
+
|
| 650 |
+
---
|
| 651 |
+
|
| 652 |
+
# 21. Security Considerations
|
| 653 |
+
|
| 654 |
+
Important restrictions include:
|
| 655 |
+
|
| 656 |
+
* package allowlist
|
| 657 |
+
* sandboxed tool execution
|
| 658 |
+
* workspace file isolation
|
| 659 |
+
* limited shell access
|
| 660 |
+
|
| 661 |
+
Example allowed packages:
|
| 662 |
+
|
| 663 |
+
```
|
| 664 |
+
numpy
|
| 665 |
+
pandas
|
| 666 |
+
torch
|
| 667 |
+
scikit-learn
|
| 668 |
+
matplotlib
|
| 669 |
+
```
|
| 670 |
+
|
| 671 |
+
---
|
| 672 |
+
|
| 673 |
+
# 22. End-to-End Example
|
| 674 |
+
|
| 675 |
+
User request:
|
| 676 |
+
|
| 677 |
+
```
|
| 678 |
+
create a neural network code demo in python that uses pytorch
|
| 679 |
+
```
|
| 680 |
+
|
| 681 |
+
System execution:
|
| 682 |
+
|
| 683 |
+
```
|
| 684 |
+
User prompt
|
| 685 |
+
↓
|
| 686 |
+
Agent reasoning
|
| 687 |
+
↓
|
| 688 |
+
install_python_package(torch)
|
| 689 |
+
↓
|
| 690 |
+
write_file(pytorch_nn_demo.py)
|
| 691 |
+
↓
|
| 692 |
+
artifact created
|
| 693 |
+
↓
|
| 694 |
+
UI displays code
|
| 695 |
+
```
|
| 696 |
+
|
| 697 |
+
User interaction:
|
| 698 |
+
|
| 699 |
+
```
|
| 700 |
+
Edit code
|
| 701 |
+
Run code
|
| 702 |
+
Download file
|
| 703 |
+
```
|
| 704 |
+
|
| 705 |
+
Execution output appears in the console.
|
| 706 |
+
|
| 707 |
+
---
|
| 708 |
+
|
| 709 |
+
# 23. Final System Architecture
|
| 710 |
+
|
| 711 |
+
```
|
| 712 |
+
User
|
| 713 |
+
↓
|
| 714 |
+
HF Space UI
|
| 715 |
+
↓
|
| 716 |
+
Agent Engine
|
| 717 |
+
↓
|
| 718 |
+
Speculative Decoding
|
| 719 |
+
↓
|
| 720 |
+
Tool Parser
|
| 721 |
+
↓
|
| 722 |
+
Tool Executor
|
| 723 |
+
↓
|
| 724 |
+
Dynamic Tools
|
| 725 |
+
↓
|
| 726 |
+
Workspace
|
| 727 |
+
↓
|
| 728 |
+
Artifacts / Agents / Queue
|
| 729 |
+
↓
|
| 730 |
+
Result returned to LLM
|
| 731 |
+
```
|
| 732 |
+
|
| 733 |
+
---
|
| 734 |
+
|
| 735 |
+
# 24. Design Principles
|
| 736 |
+
|
| 737 |
+
The system follows several core principles.
|
| 738 |
+
|
| 739 |
+
1. **Everything is a tool**
|
| 740 |
+
|
| 741 |
+
Actions are performed through tools rather than hardcoded logic.
|
| 742 |
+
|
| 743 |
+
2. **Agents can extend themselves**
|
| 744 |
+
|
| 745 |
+
Agents may create tools and agents.
|
| 746 |
+
|
| 747 |
+
3. **Artifacts are first-class outputs**
|
| 748 |
+
|
| 749 |
+
Generated files are accessible through the UI.
|
| 750 |
+
|
| 751 |
+
4. **Isolation and safety**
|
| 752 |
+
|
| 753 |
+
Tools run in subprocesses.
|
| 754 |
+
|
| 755 |
+
5. **Local and lightweight**
|
| 756 |
+
|
| 757 |
+
System runs entirely locally using Ollama.
|
| 758 |
+
|
| 759 |
+
---
|
| 760 |
+
|
| 761 |
+
# 25. Future Extensions
|
| 762 |
+
|
| 763 |
+
Potential future capabilities include:
|
| 764 |
+
|
| 765 |
+
```
|
| 766 |
+
multi-agent collaboration
|
| 767 |
+
autonomous project generation
|
| 768 |
+
browser automation
|
| 769 |
+
dataset generation
|
| 770 |
+
long-term memory
|
| 771 |
+
```
|
| 772 |
+
|
| 773 |
+
---
|
entrypoint.sh
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/bin/bash
|
| 2 |
+
set -e
|
| 3 |
+
|
| 4 |
+
echo "Starting Ollama..."
|
| 5 |
+
ollama serve &
|
| 6 |
+
|
| 7 |
+
sleep 8
|
| 8 |
+
|
| 9 |
+
echo "Pulling model..."
|
| 10 |
+
ollama pull "${MODEL_NAME}" || true
|
| 11 |
+
|
| 12 |
+
mkdir -p /workspace/data
|
| 13 |
+
|
| 14 |
+
echo "Launching Gradio UI..."
|
| 15 |
+
cd /workspace
|
| 16 |
+
python3 app_gradio.py
|
pygmyclaw.py
ADDED
|
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python3
|
| 2 |
+
"""
|
| 3 |
+
PygmyClaw – Compact AI Agent with async queue, HF + AI tools support.
|
| 4 |
+
Verbose logging added for debugging.
|
| 5 |
+
"""
|
| 6 |
+
|
| 7 |
+
import os
|
| 8 |
+
import sys
|
| 9 |
+
import json
|
| 10 |
+
import time
|
| 11 |
+
import queue
|
| 12 |
+
import threading
|
| 13 |
+
import urllib.request
|
| 14 |
+
from pathlib import Path
|
| 15 |
+
import subprocess
|
| 16 |
+
import re
|
| 17 |
+
import textwrap
|
| 18 |
+
from huggingface_hub import hf_hub_download, upload_file
|
| 19 |
+
|
| 20 |
+
# -------------------- Globals --------------------
|
| 21 |
+
SCRIPT_DIR = Path(__file__).parent.resolve()
|
| 22 |
+
DEFAULT_MODEL = os.environ.get("MODEL_NAME", "qwen3.5:0.8b")
|
| 23 |
+
DEFAULT_ENDPOINT = "http://localhost:11434/api/generate"
|
| 24 |
+
HF_TOKEN = os.environ.get("HF_TOKEN")
|
| 25 |
+
HF_REPO = "rahul7star/pyclaw"
|
| 26 |
+
HF_LOCAL_DIR = SCRIPT_DIR / "pyclaw_hf"
|
| 27 |
+
FILES_TO_DOWNLOAD = ["memory.json", "tools.json"]
|
| 28 |
+
TASK_QUEUE = queue.Queue()
|
| 29 |
+
QUEUE_EVENT = threading.Event()
|
| 30 |
+
|
| 31 |
+
print(f"[LOG] PygmyClaw loaded. Default model: {DEFAULT_MODEL}")
|
| 32 |
+
|
| 33 |
+
# -------------------- HF File Download --------------------
|
| 34 |
+
def download_hf_files():
|
| 35 |
+
HF_LOCAL_DIR.mkdir(parents=True, exist_ok=True)
|
| 36 |
+
for file_name in FILES_TO_DOWNLOAD:
|
| 37 |
+
local_path = HF_LOCAL_DIR / file_name
|
| 38 |
+
if not local_path.exists() or local_path.stat().st_size == 0:
|
| 39 |
+
try:
|
| 40 |
+
hf_hub_download(repo_id=HF_REPO, filename=file_name,
|
| 41 |
+
token=HF_TOKEN, local_dir=str(HF_LOCAL_DIR))
|
| 42 |
+
print(f"[LOG] Downloaded {file_name}")
|
| 43 |
+
except Exception as e:
|
| 44 |
+
print(f"[WARN] Failed to download {file_name}: {e}")
|
| 45 |
+
local_path.write_text("{}")
|
| 46 |
+
print(f"[LOG] Created empty {file_name}")
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
def save_hf_memory():
|
| 50 |
+
mem_file = HF_LOCAL_DIR / "memory.json"
|
| 51 |
+
print("[DEBUG] Saving memory locally...")
|
| 52 |
+
try:
|
| 53 |
+
with open(mem_file, "w") as f:
|
| 54 |
+
print("[DEBUG] Local memory saved:", mem_file, "Size:", mem_file.stat().st_size)
|
| 55 |
+
json.dump(self.memory_data, f, indent=2)
|
| 56 |
+
upload_file(path_or_fileobj=str(mem_file), path_in_repo="memory.json",
|
| 57 |
+
repo_id=HF_REPO, token=HF_TOKEN, repo_type="model")
|
| 58 |
+
print("[LOG] memory.json updated successfully on HF.")
|
| 59 |
+
except Exception as e:
|
| 60 |
+
print(f"[WARN] Failed to push memory to HF: {e}")
|
| 61 |
+
|
| 62 |
+
# -------------------- PygmyClaw Agent --------------------
|
| 63 |
+
class PygmyClaw:
|
| 64 |
+
def __init__(self):
|
| 65 |
+
self.model = DEFAULT_MODEL
|
| 66 |
+
self.endpoint = DEFAULT_ENDPOINT
|
| 67 |
+
self.memory_data = {}
|
| 68 |
+
self.tools_data = {}
|
| 69 |
+
self.python_tools = ["Python Script"]
|
| 70 |
+
download_hf_files()
|
| 71 |
+
self._load_hf_memory()
|
| 72 |
+
self._load_hf_tools()
|
| 73 |
+
self.python_tools += list(self.tools_data.keys())
|
| 74 |
+
self.python_tools.append("AI Agent")
|
| 75 |
+
self._ensure_model_ready()
|
| 76 |
+
self._warmup_model()
|
| 77 |
+
QUEUE_EVENT.set()
|
| 78 |
+
threading.Thread(target=self._process_queue, daemon=True).start()
|
| 79 |
+
self._ssd_backend = "http"
|
| 80 |
+
print("[LOG] PygmyClaw initialization complete.")
|
| 81 |
+
|
| 82 |
+
# -------------------- Memory / Tools --------------------
|
| 83 |
+
def _load_hf_memory(self):
|
| 84 |
+
mem_file = HF_LOCAL_DIR / "memory.json"
|
| 85 |
+
mem_file.parent.mkdir(parents=True, exist_ok=True)
|
| 86 |
+
if not mem_file.exists() or mem_file.stat().st_size == 0:
|
| 87 |
+
mem_file.write_text("{}")
|
| 88 |
+
try:
|
| 89 |
+
with open(mem_file) as f:
|
| 90 |
+
self.memory_data = json.load(f)
|
| 91 |
+
print("[LOG] Loaded memory.json successfully.")
|
| 92 |
+
except json.JSONDecodeError:
|
| 93 |
+
self.memory_data = {}
|
| 94 |
+
print("[WARN] memory.json invalid, initialized empty")
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
def _save_hf_memory(self, memory_data=None):
|
| 99 |
+
mem_file = HF_LOCAL_DIR / "memory.json"
|
| 100 |
+
print("[DEBUG] Saving memory locally...")
|
| 101 |
+
try:
|
| 102 |
+
with open(mem_file, "w") as f:
|
| 103 |
+
print("[DEBUG] Local memory saved:", mem_file, "Size:", mem_file.stat().st_size)
|
| 104 |
+
json.dump(self.memory_data, f, indent=2)
|
| 105 |
+
upload_file(path_or_fileobj=str(mem_file), path_in_repo="memory.json",
|
| 106 |
+
repo_id=HF_REPO, token=HF_TOKEN, repo_type="model")
|
| 107 |
+
print("[LOG] memory.json updated successfully on HF.")
|
| 108 |
+
except Exception as e:
|
| 109 |
+
print(f"[WARN] Failed to push memory to HF: {e}")
|
| 110 |
+
|
| 111 |
+
def _load_hf_tools(self):
|
| 112 |
+
tools_file = HF_LOCAL_DIR / "tools.json"
|
| 113 |
+
tools_file.parent.mkdir(parents=True, exist_ok=True)
|
| 114 |
+
if not tools_file.exists() or tools_file.stat().st_size == 0:
|
| 115 |
+
tools_file.write_text("{}")
|
| 116 |
+
try:
|
| 117 |
+
with open(tools_file) as f:
|
| 118 |
+
self.tools_data = json.load(f)
|
| 119 |
+
print("[LOG] Loaded tools.json successfully.")
|
| 120 |
+
except json.JSONDecodeError:
|
| 121 |
+
self.tools_data = {}
|
| 122 |
+
print("[WARN] tools.json invalid, initialized empty")
|
| 123 |
+
|
| 124 |
+
# -------------------- Model Ready --------------------
|
| 125 |
+
def _ensure_model_ready(self):
|
| 126 |
+
print(f"[LOG] Ensuring model '{self.model}' is ready...")
|
| 127 |
+
payload = {"model": self.model, "prompt": "hello", "stream": False, "options": {"num_predict": 1}}
|
| 128 |
+
try:
|
| 129 |
+
req = urllib.request.Request(self.endpoint, data=json.dumps(payload).encode("utf-8"),
|
| 130 |
+
headers={"Content-Type": "application/json"}, method="POST")
|
| 131 |
+
with urllib.request.urlopen(req, timeout=15) as resp:
|
| 132 |
+
resp_data = json.loads(resp.read())
|
| 133 |
+
if "response" in resp_data:
|
| 134 |
+
print("[LOG] Model is ready.")
|
| 135 |
+
except Exception as e:
|
| 136 |
+
print(f"[WARN] HTTP model check failed: {e}. Will use CLI fallback if needed.")
|
| 137 |
+
|
| 138 |
+
def _warmup_model(self):
|
| 139 |
+
try:
|
| 140 |
+
payload = {"model": self.model, "prompt": ".", "stream": False, "options": {"num_predict": 1}}
|
| 141 |
+
req = urllib.request.Request(self.endpoint, data=json.dumps(payload).encode("utf-8"),
|
| 142 |
+
headers={"Content-Type": "application/json"}, method="POST")
|
| 143 |
+
with urllib.request.urlopen(req, timeout=5):
|
| 144 |
+
print("[LOG] Model warmed up.")
|
| 145 |
+
except Exception:
|
| 146 |
+
print("[LOG] Warmup skipped, may use CLI fallback.")
|
| 147 |
+
|
| 148 |
+
# -------------------- Task Queue --------------------
|
| 149 |
+
def add_task(self, prompt, tool="AI Agent", callback=None):
|
| 150 |
+
task_id = str(time.time())
|
| 151 |
+
TASK_QUEUE.put({"id": task_id, "prompt": prompt, "tool": tool, "callback": callback})
|
| 152 |
+
print(f"[LOG] Queued task {task_id} with tool={tool}")
|
| 153 |
+
return task_id
|
| 154 |
+
|
| 155 |
+
def _process_queue(self):
|
| 156 |
+
print("[LOG] Queue processor started...")
|
| 157 |
+
while QUEUE_EVENT.is_set():
|
| 158 |
+
try:
|
| 159 |
+
task = TASK_QUEUE.get(timeout=1)
|
| 160 |
+
except queue.Empty:
|
| 161 |
+
continue
|
| 162 |
+
task_id = task["id"]
|
| 163 |
+
prompt = task["prompt"]
|
| 164 |
+
tool = task.get("tool", "AI Agent")
|
| 165 |
+
callback = task.get("callback", None)
|
| 166 |
+
print(f"[LOG] Processing task {task_id} -> {prompt}")
|
| 167 |
+
try:
|
| 168 |
+
if tool == "Python Script":
|
| 169 |
+
local_vars = {}
|
| 170 |
+
exec(prompt, {}, local_vars)
|
| 171 |
+
result = str(local_vars)
|
| 172 |
+
else:
|
| 173 |
+
result = self.generate_with_ssd(prompt)
|
| 174 |
+
print(f"[LOG] Model output for task {task_id}:\n{result}")
|
| 175 |
+
|
| 176 |
+
# Save memory only after successful response
|
| 177 |
+
self.memory_data[task_id] = {
|
| 178 |
+
"prompt": prompt,
|
| 179 |
+
"response": result,
|
| 180 |
+
"timestamp": time.time(),
|
| 181 |
+
"tool": tool
|
| 182 |
+
}
|
| 183 |
+
self._save_hf_memory(self.memory_data)
|
| 184 |
+
save_hf_memory()
|
| 185 |
+
if callback:
|
| 186 |
+
callback(result)
|
| 187 |
+
print(f"[LOG] Task {task_id} completed successfully.")
|
| 188 |
+
|
| 189 |
+
except Exception as e:
|
| 190 |
+
print(f"[ERROR] Task {task_id} failed: {e}")
|
| 191 |
+
finally:
|
| 192 |
+
TASK_QUEUE.task_done()
|
| 193 |
+
|
| 194 |
+
# -------------------- Unified SSD call with failover --------------------
|
| 195 |
+
def generate_with_ssd(self, prompt, num_predict=600, timeout=120):
|
| 196 |
+
output = ""
|
| 197 |
+
backends_to_try = ["http", "cli"] if self._ssd_backend == "http" else ["cli", "http"]
|
| 198 |
+
for backend in backends_to_try:
|
| 199 |
+
if backend == "http":
|
| 200 |
+
try:
|
| 201 |
+
payload = {"model": self.model, "prompt": prompt, "stream": False,
|
| 202 |
+
"enable_thinking": False, "options": {"num_predict": num_predict, "temperature": 0.2}}
|
| 203 |
+
req = urllib.request.Request(self.endpoint, data=json.dumps(payload).encode("utf-8"),
|
| 204 |
+
headers={"Content-Type": "application/json"}, method="POST")
|
| 205 |
+
with urllib.request.urlopen(req, timeout=timeout) as resp:
|
| 206 |
+
output = resp.read().decode("utf-8")
|
| 207 |
+
self._ssd_backend = "http"
|
| 208 |
+
print("[LOG] HTTP backend succeeded.")
|
| 209 |
+
break
|
| 210 |
+
except Exception as e:
|
| 211 |
+
print(f"[WARN] HTTP backend failed: {e}")
|
| 212 |
+
output = f"❌ HTTP failed: {e}"
|
| 213 |
+
continue
|
| 214 |
+
elif backend == "cli":
|
| 215 |
+
try:
|
| 216 |
+
result = subprocess.run(["ollama", "run", self.model, prompt],
|
| 217 |
+
capture_output=True, text=True, timeout=600)
|
| 218 |
+
output = result.stdout.strip() if result.stdout else result.stderr.strip()
|
| 219 |
+
self._ssd_backend = "cli"
|
| 220 |
+
print("[LOG] CLI backend succeeded.")
|
| 221 |
+
break
|
| 222 |
+
except subprocess.TimeoutExpired:
|
| 223 |
+
output = "⏱️ CLI timed out."
|
| 224 |
+
print("[WARN] CLI backend timed out.")
|
| 225 |
+
except Exception as e:
|
| 226 |
+
output = f"❌ CLI failed: {e}"
|
| 227 |
+
print(f"[WARN] CLI backend failed: {e}")
|
| 228 |
+
continue
|
| 229 |
+
|
| 230 |
+
self.memory_data["last_raw_response"] = output
|
| 231 |
+
try:
|
| 232 |
+
data = json.loads(output)
|
| 233 |
+
except json.JSONDecodeError:
|
| 234 |
+
data = {"response": output}
|
| 235 |
+
|
| 236 |
+
full_text = data.get("response", output)
|
| 237 |
+
code_blocks = re.findall(r"```(?:python)?\s*(.*?)```", full_text, re.S | re.I)
|
| 238 |
+
code = "\n\n".join(code_blocks)
|
| 239 |
+
code = textwrap.dedent(code).replace("\t", " ").strip()
|
| 240 |
+
self.memory_data["last_code"] = code
|
| 241 |
+
return full_text
|
pygmyclaw_multitool.py
ADDED
|
@@ -0,0 +1,210 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python3
|
| 2 |
+
"""
|
| 3 |
+
PygmyClaw Multitool – Contains the actual tool implementations.
|
| 4 |
+
Works both as:
|
| 5 |
+
1) CLI tool (stdin → stdout JSON)
|
| 6 |
+
2) Python module (import + run_tool())
|
| 7 |
+
"""
|
| 8 |
+
|
| 9 |
+
import json
|
| 10 |
+
import sys
|
| 11 |
+
import os
|
| 12 |
+
import platform
|
| 13 |
+
import time
|
| 14 |
+
from pathlib import Path
|
| 15 |
+
|
| 16 |
+
SCRIPT_DIR = Path(__file__).parent.resolve()
|
| 17 |
+
|
| 18 |
+
ERROR_LOG = SCRIPT_DIR / "error_log.json"
|
| 19 |
+
|
| 20 |
+
MAX_LOG_ENTRIES = 1000
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
# ----------------------------------------------------------------------
|
| 24 |
+
# Tool definitions
|
| 25 |
+
|
| 26 |
+
TOOLS = {
|
| 27 |
+
"list_tools_detailed": {
|
| 28 |
+
"name": "list_tools_detailed",
|
| 29 |
+
"description": "List all available tools with their descriptions and parameters.",
|
| 30 |
+
"parameters": {},
|
| 31 |
+
"func": "do_list_tools"
|
| 32 |
+
},
|
| 33 |
+
|
| 34 |
+
"sys_info": {
|
| 35 |
+
"name": "sys_info",
|
| 36 |
+
"description": "Get system information (OS, Python version, etc.).",
|
| 37 |
+
"parameters": {},
|
| 38 |
+
"func": "do_sys_info"
|
| 39 |
+
},
|
| 40 |
+
|
| 41 |
+
"log_error": {
|
| 42 |
+
"name": "log_error",
|
| 43 |
+
"description": "Log an error message to the error log.",
|
| 44 |
+
"parameters": {
|
| 45 |
+
"msg": "string",
|
| 46 |
+
"trace": "string (optional)"
|
| 47 |
+
},
|
| 48 |
+
"func": "do_log_error"
|
| 49 |
+
},
|
| 50 |
+
|
| 51 |
+
"echo": {
|
| 52 |
+
"name": "echo",
|
| 53 |
+
"description": "Echo the input text (for testing).",
|
| 54 |
+
"parameters": {"text": "string"},
|
| 55 |
+
"func": "do_echo"
|
| 56 |
+
}
|
| 57 |
+
}
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
# ----------------------------------------------------------------------
|
| 61 |
+
# Tool Implementations
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
def do_list_tools():
|
| 65 |
+
"""Return the list of tools with metadata."""
|
| 66 |
+
|
| 67 |
+
tools_list = []
|
| 68 |
+
|
| 69 |
+
for name, info in TOOLS.items():
|
| 70 |
+
|
| 71 |
+
tools_list.append({
|
| 72 |
+
"name": name,
|
| 73 |
+
"description": info["description"],
|
| 74 |
+
"parameters": info["parameters"]
|
| 75 |
+
})
|
| 76 |
+
|
| 77 |
+
return {"tools": tools_list}
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
def do_sys_info():
|
| 81 |
+
"""Return system information."""
|
| 82 |
+
|
| 83 |
+
return {
|
| 84 |
+
"os": platform.system(),
|
| 85 |
+
"os_release": platform.release(),
|
| 86 |
+
"python_version": platform.python_version(),
|
| 87 |
+
"hostname": platform.node()
|
| 88 |
+
}
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
def do_log_error(msg, trace=""):
|
| 92 |
+
"""Append an error to the error log."""
|
| 93 |
+
|
| 94 |
+
entry = {
|
| 95 |
+
"timestamp": time.time(),
|
| 96 |
+
"msg": msg,
|
| 97 |
+
"trace": trace
|
| 98 |
+
}
|
| 99 |
+
|
| 100 |
+
try:
|
| 101 |
+
|
| 102 |
+
if ERROR_LOG.exists():
|
| 103 |
+
|
| 104 |
+
with open(ERROR_LOG) as f:
|
| 105 |
+
log = json.load(f)
|
| 106 |
+
|
| 107 |
+
else:
|
| 108 |
+
|
| 109 |
+
log = []
|
| 110 |
+
|
| 111 |
+
log.append(entry)
|
| 112 |
+
|
| 113 |
+
if len(log) > MAX_LOG_ENTRIES:
|
| 114 |
+
log = log[-MAX_LOG_ENTRIES:]
|
| 115 |
+
|
| 116 |
+
with open(ERROR_LOG, "w") as f:
|
| 117 |
+
json.dump(log, f, indent=2)
|
| 118 |
+
|
| 119 |
+
return {"status": "logged"}
|
| 120 |
+
|
| 121 |
+
except Exception as e:
|
| 122 |
+
|
| 123 |
+
return {"error": f"Failed to write log: {e}"}
|
| 124 |
+
|
| 125 |
+
|
| 126 |
+
def do_echo(text):
|
| 127 |
+
"""Echo input."""
|
| 128 |
+
|
| 129 |
+
return {"echo": text}
|
| 130 |
+
|
| 131 |
+
|
| 132 |
+
# ----------------------------------------------------------------------
|
| 133 |
+
# INTERNAL TOOL EXECUTOR (used by PygmyClaw agent)
|
| 134 |
+
|
| 135 |
+
def run_tool(action, **params):
|
| 136 |
+
"""
|
| 137 |
+
Run tool programmatically.
|
| 138 |
+
|
| 139 |
+
Example:
|
| 140 |
+
run_tool("sys_info")
|
| 141 |
+
run_tool("echo", text="hello")
|
| 142 |
+
"""
|
| 143 |
+
|
| 144 |
+
tool = TOOLS.get(action)
|
| 145 |
+
|
| 146 |
+
if not tool:
|
| 147 |
+
return {"error": f"Unknown tool '{action}'"}
|
| 148 |
+
|
| 149 |
+
func_name = tool["func"]
|
| 150 |
+
|
| 151 |
+
try:
|
| 152 |
+
|
| 153 |
+
if func_name == "do_list_tools":
|
| 154 |
+
return do_list_tools()
|
| 155 |
+
|
| 156 |
+
elif func_name == "do_sys_info":
|
| 157 |
+
return do_sys_info()
|
| 158 |
+
|
| 159 |
+
elif func_name == "do_log_error":
|
| 160 |
+
return do_log_error(
|
| 161 |
+
params.get("msg"),
|
| 162 |
+
params.get("trace", "")
|
| 163 |
+
)
|
| 164 |
+
|
| 165 |
+
elif func_name == "do_echo":
|
| 166 |
+
return do_echo(params.get("text"))
|
| 167 |
+
|
| 168 |
+
else:
|
| 169 |
+
return {"error": f"Unknown function '{func_name}'"}
|
| 170 |
+
|
| 171 |
+
except Exception as e:
|
| 172 |
+
|
| 173 |
+
return {"error": f"Tool execution failed: {e}"}
|
| 174 |
+
|
| 175 |
+
|
| 176 |
+
# ----------------------------------------------------------------------
|
| 177 |
+
# CLI Dispatcher (existing behavior preserved)
|
| 178 |
+
|
| 179 |
+
def main():
|
| 180 |
+
|
| 181 |
+
try:
|
| 182 |
+
|
| 183 |
+
raw = sys.stdin.read()
|
| 184 |
+
|
| 185 |
+
if not raw:
|
| 186 |
+
print(json.dumps({"error": "No input"}))
|
| 187 |
+
return
|
| 188 |
+
|
| 189 |
+
data = json.loads(raw)
|
| 190 |
+
|
| 191 |
+
action = data.get("action")
|
| 192 |
+
|
| 193 |
+
if not action:
|
| 194 |
+
|
| 195 |
+
print(json.dumps({"error": "No action specified"}))
|
| 196 |
+
return
|
| 197 |
+
|
| 198 |
+
params = {k: v for k, v in data.items() if k != "action"}
|
| 199 |
+
|
| 200 |
+
result = run_tool(action, **params)
|
| 201 |
+
|
| 202 |
+
print(json.dumps(result))
|
| 203 |
+
|
| 204 |
+
except Exception as e:
|
| 205 |
+
|
| 206 |
+
print(json.dumps({"error": f"Multitool exception: {e}"}))
|
| 207 |
+
|
| 208 |
+
|
| 209 |
+
if __name__ == "__main__":
|
| 210 |
+
main()
|
requirements.txt
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
streamlit>=1.28.0
|
| 2 |
+
requests>=2.28.0
|
| 3 |
+
|
| 4 |
+
requests>=2.31.0
|
| 5 |
+
redis>=5.0.0
|
| 6 |
+
ollama-python>=0.1.0
|
| 7 |
+
gradio==4.44.0
|
| 8 |
+
huggingface_hub==0.23.5
|
ui.py
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import streamlit as st
|
| 2 |
+
import subprocess
|
| 3 |
+
from pathlib import Path
|
| 4 |
+
import json
|
| 5 |
+
|
| 6 |
+
st.set_page_config(page_title="PygmyClaw", layout="wide")
|
| 7 |
+
st.title("🦾 PygmyClaw Autonomous Agent")
|
| 8 |
+
|
| 9 |
+
# Workspace
|
| 10 |
+
workspace = Path("/workspace/data")
|
| 11 |
+
workspace.mkdir(exist_ok=True)
|
| 12 |
+
|
| 13 |
+
# User input
|
| 14 |
+
prompt = st.text_area("Enter your prompt:", height=100)
|
| 15 |
+
|
| 16 |
+
if st.button("Submit Prompt"):
|
| 17 |
+
st.info("Processing...")
|
| 18 |
+
# Call pygmyclaw agent
|
| 19 |
+
result = subprocess.run(
|
| 20 |
+
["python3", "pygmyclaw.py", "generate", prompt],
|
| 21 |
+
capture_output=True, text=True
|
| 22 |
+
)
|
| 23 |
+
st.success("Done!")
|
| 24 |
+
st.code(result.stdout, language="text")
|
| 25 |
+
|
| 26 |
+
# Optional: code editor + run
|
| 27 |
+
code_files = list(workspace.glob("*.py"))
|
| 28 |
+
if code_files:
|
| 29 |
+
st.subheader("Generated Python Scripts")
|
| 30 |
+
for f in code_files:
|
| 31 |
+
code = f.read_text()
|
| 32 |
+
edited_code = st.text_area(f.name, code, height=200)
|
| 33 |
+
if st.button(f"Run {f.name}"):
|
| 34 |
+
exec_result = subprocess.run(
|
| 35 |
+
["python3", "-c", edited_code],
|
| 36 |
+
capture_output=True, text=True
|
| 37 |
+
)
|
| 38 |
+
st.code(exec_result.stdout + "\n" + exec_result.stderr)
|