Metadata-Version: 2.4
Name: fastclaw-ai
Version: 1.1.0
Summary: FastClaw - AI Agent Framework with multi-channel support
Author: kandada
License: GPL-3.0
Project-URL: Homepage, https://github.com/kandada/fastclaw
Project-URL: Repository, https://github.com/kandada/fastclaw.git
Project-URL: Issues, https://github.com/kandada/fastclaw/issues
Project-URL: Documentation, https://github.com/kandada/fastclaw#readme
Keywords: ai,agent,llm,chatbot,fastmind
Classifier: Development Status :: 4 - Beta
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Operating System :: OS Independent
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: fastmind>=0.1.9
Requires-Dist: openai>=1.0.0
Requires-Dist: websockets>=10.0
Requires-Dist: fastapi>=0.100.0
Requires-Dist: uvicorn[standard]>=0.35.0
Requires-Dist: httpx>=0.23.0
Requires-Dist: anyio>=4.5
Requires-Dist: croniter>=6.2.0
Requires-Dist: lark-oapi>=1.0.0
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"

# FastClaw

a python-based light but strong lobster

## Design Philosophy

FastClaw is built on the core concept of **event-driven agent orchestration**. Key design principles:

- **Graph-based Agent**: Uses a directed graph to orchestrate agent behavior, supporting conditional branching between nodes (e.g., tool execution, response generation)
- **Event Streaming**: Real-time streaming output of LLM responses for better user experience
- **Tool System**: Extensible tool framework supporting Shell commands, skills, and custom integrations
- **Session Management**: Persistent conversation history with multi-session support
- **Cron Scheduling**: Built-in cron-style task scheduling for automated workflows

## Quick Start

### Installation

```bash
git clone https://github.com/kandada/fastclaw.git
cd fastclaw
pip install -r requirements.txt
```

### Start Server

```bash
python main.py start
# or want it remaining in background:
nohup python main.py start > fastclaw.log 2>&1 &
```

### Agent Configuration
```bash
vim workspace/data/agents/main_agent/metadata.json 
# Edit the file to configure your LLM provider and API key
# Currently supports OpenAI gateway models (DeepSeek, OpenAI, etc.), recommended: deepseek-chat
# Default agent is main_agent. To switch, modify workspace/data/settings.json
```

Access at http://localhost:8765
You can also select agents and enter API keys in the Settings page.
API key must be provided for the agent to work properly.

### CLI Usage

```bash
# Interactive chat
python main.py chat

# New session
python main.py chat --new

# Check status
python main.py status
```

## Features

- 🤖 **LLM-powered** - Built on  [FastMind](https://github.com/kandada/fastmind)  framework with streaming support
- 🔧 **Tool Calling** - Execute Shell commands, skills, and more
- ⏰ **Cron Jobs** - Schedule tasks with cron expressions
- 💬 **Multi-channel** - Feishu, iMessage integrations
- 🎨 **Extensible** - Easy to add custom skills and agents

## License

GPL-3.0

## Acknowledgments

Inspired by [OpenClaw](https://github.com/openclaw/openclaw). Special thanks to the open source community.

---

FastClaw is powerful, but its use depends entirely on the user - all responsibility lies with the user yourself.

---

Author：[xiefujin](https://github.com/kandada) email: 490021684@qq.com，welcome to contact me.
