OpenClaw reimagined in pure Python — autonomous AI agent with memory, RAG, skills, web dashboard, voice input, daemon, and multi-channel support.
<p align="center">
<img src="assets/logo-300.png" alt="PythonClaw" width="160">
</p>
<h1 align="center">PythonClaw</h1>
<p align="center">
<strong>OpenClaw, reimagined in pure Python — purely Pythonic design.</strong><br>
Memory · RAG · Skills · Web Dashboard · Voice · Daemon · Multi-Channel
</p>
<p align="center">
<a href="https://github.com/ericwang915/PythonClaw/actions/workflows/ci.yml">
<img src="https://github.com/ericwang915/PythonClaw/actions/workflows/ci.yml/badge.svg" alt="CI">
</a>
<a href="https://pypi.org/project/pythonclaw/">
<img src="https://img.shields.io/pypi/v/pythonclaw?color=blue" alt="PyPI">
</a>
<img src="https://img.shields.io/pypi/pyversions/pythonclaw" alt="Python">
<a href="LICENSE">
<img src="https://img.shields.io/github/license/ericwang915/PythonClaw" alt="MIT License">
</a>
<a href="https://github.com/ericwang915/PythonClaw/stargazers">
<img src="https://img.shields.io/github/stars/ericwang915/PythonClaw?style=social" alt="Stars">
</a>
</p>
<p align="center">
<em>The Python port of <a href="https://github.com/openclaw/openclaw">OpenClaw</a> — no Node.js, no Rust, no C extensions. Just Python.</em>
</p>
---
## Highlights
| | Feature | Details |
|---|---------|---------|
| 🧠 | **Provider-agnostic** | DeepSeek, DeepSeek, DeepSeek, DeepSeek, Kimi, GLM — or any OpenAI-compatible API |
| 🛠️ | **Three-tier skills** | Progressive loading: metadata → instructions → resources. Community marketplace via [ClawHub](https://clawhub.com) (13K+ free skills) |
| 💾 | **Persistent memory** | Markdown-based long-term memory with daily logs and semantic recall |
| 🔍 | **Hybrid RAG** | BM25 + dense embeddings + RRF fusion + LLM re-ranking |
| 🌐 | **Web dashboard** | Browser UI for chat, config, skill catalog, identity editing, and marketplace |
| 🎙️ | **Voice input** | Deepgram speech-to-text in the web chat |
| ⏰ | **Cron jobs** | Schedule tasks via YAML or let the agent create its own |
| 📡 | **Multi-channelHAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型