Claude Skill

SafeRL-Lab/cheetahclaws

CheetahClaws（Nano Claude Code）是一款快速、原生Python的个人AI助手，灵感源自OpenClaw与Claude Code，兼容任意模型，全天候自主运行。

概览

Stars744
Forks263
语言Python
最后更新2026-06-30
最近同步2026-07-03
前往 GitHub

仓库信息

拥有者SafeRL-Lab
仓库cheetahclaws
完整名称SafeRL-Lab/cheetahclaws
Repo ID1,198,604,352
GitHub 地址https://github.com/SafeRL-Lab/cheetahclaws

安装这个 Skill

pip install cheetahclaws
GitHub

Registry 信息

类型mcp_server
质量分85/100
验证状态readme_parsed
最近验证2026-06-06
平台
ClaudeMCPOpenClaw
能力
browsercode-reviewpdfmemorysearchimagevideoterminalworkflowagentic-ai
识别文件
README.mddocker-compose.ymldocsexamplespyproject.tomlrequirements.txttests
配置键
ANTHROPIC_API_KEYOPENAI_API_KEYGEMINI_API_KEYMOONSHOT_API_KEYDASHSCOPE_API_KEYZHIPU_API_KEYDEEPSEEK_API_KEYMINIMAX_API_KEYCUSTOM_BASE_URLCUSTOM_API_KEY
安装方式
  • pip install cheetahclaws
  • git clone https://github.com/SafeRL-Lab/cheetahclaws.git
  • pip install . # then: cheetahclaws
  • pip install ".[voice]" # voice input (sounddevice + faster-whisper)
  • pip install ".[vision]" # clipboard image capture (Pillow)

项目简介

CheetahClaws（Nano Claude Code）是一款快速、易用、原生Python的个人AI助手，灵感源自OpenClaw与Claude Code，兼容任意模型，专为全天候自主服务而打造。

英文描述

CheetahClaws: A Fast and Easy-to-Use Agent Harness Infrastructure for Long-Horizon, Multi-Model, and Tool-Using AI Systems

要点

  • 原生Python实现，性能快速
  • 兼容任意AI模型
  • 灵感源自OpenClaw与Claude Code
  • 专为全天候自主运行设计
  • 易于使用和集成

使用场景

  • 日常任务的个人AI助手
  • 自主代码生成与审查
  • 持续后台自动化
  • 多模型实验与测试
  • AI代理的学习与原型开发

README 摘要

English | [中文](docs/i18n/README.CN.MD) | [한국어](docs/i18n/README.KO.MD) | [日本語](docs/i18n/README.JP.MD) | [Français](docs/i18n/README.FR.MD) | [Deutsch](docs/i18n/README.DE.MD) | [Español](docs/i18n/README.ES.MD) | [Português](docs/i18n/README.PT.MD) <br> <div align="center"> <a href="[https://github.com/SafeRL-Lab/Robust-Gymnasium](https://github.com/SafeRL-Lab/cheetahclaws)"> <img src="docs/media/logos/logo-5.png" alt="Logo" width="280"> </a> <h2 align="center" style="font-size: 30px;"><strong><em>CheetahClaws</em></strong>: A Fast and Easy-to-Use Agent Harness Infrastructure for Long-Horizon, Multi-Model, and Tool-Using AI Systems</h2> <p align="center"> <a href="https://cheetahclaws.github.io/">Website</a> · <a href="https://arxiv.org/pdf/2605.26112">Scaling the Harness</a> · <a href="https://github.com/SafeRL-Lab/cheetahclaws/issues">Issue</a> </p> </div> ### Quick Install ```bash curl -fsSL https://raw.githubusercontent.com/SafeRL-Lab/cheetahclaws/main/scripts/install.sh | bash ``` After installation: ```bash source ~/.zshrc # macOS # or: source ~/.bashrc # Linux cheetahclaws # start chatting! ``` Other install methods: [pip install](#alternative-install-with-pip) | [uv install](#alternative-install-with-uv) | [run from source](#alternative-run-directly-from-source-no-install) | [full details](#installation) ## 🔥🔥🔥 News (Pacific Time) - June 5, 2026 (latest, **v3.05.82**): **User-controllable token/cost budgets** — `/budget $5` / `/budget 200k` / `/budget daily $20` cap spend per session or per day, enforced before each model call; on hit the session auto-saves and you're shown how to `/resume` or raise the cap and continue (warns at ≥80%/95%; `--budget` sets it at startup). Details: [docs/guides/fe

话题

agentic-aiclaudeclaude-codememoryopenclawpythonskills

探索更多

拥有者: SafeRL-Lab语言: Python

数据来自 GitHub，同步时间：2026-07-03