claude-code-python

by GPT-AGIVerified

Clawd Code: Reconstructing Claude Code in Python - 基于Claude Code源码的Python重构实现

121
Stars
83
Forks
Python
Language
8/23/2026
Added
View on GitHubDownload ZIP

⚠️ Third-Party Software Notice

This skill is third-party open-source software developed and hosted independently on GitHub. SkillTip is an informational directory and does not control or maintain the underlying repository. Any security checks displayed are automated and limited in scope. Review the source code before installing.

Read the Terms of Service

Installation

Add to your Claude Code skills directory:

# Add to your Claude Code skills
git clone https://github.com/GPT-AGI/claude-code-python

Getting Started

Guides for using skills like claude-code-python.

Security Report

Verified

Last scanned: —

{
  "status": "PASSED",
  "issues": []
}

README.md

English | 中文 | Français | Русский | हिन्दी | العربية | Português

🚀 Claude Code Python

A Complete Python Reimplementation Based on Real Claude Code Source

From TypeScript Source → Rebuilt in Python with ❤️


GitHub stars GitHub forks License: MIT Python 3.10+

🔥 Active Development • New Features Weekly 🔥


🎯 Why Clawd Code?

Clawd Code is a production-oriented Python rebuild of Claude Code, ported from the real TypeScript architecture and shipped as a working CLI agent, not just a source dump.

  • Real Agent Runtime — tool-calling loop, streaming REPL, session history, and multi-turn execution
  • High-Fidelity Port — keeps the original Claude Code architecture while adapting it to idiomatic Python
  • Built to Hack On — readable Python codebase, rich tests, and markdown-driven skill extensibility

Token Streaming + Tool-Aware Agent Loop

Streaming Agent Experience

Programmable Skill Runtime with Tool Sandboxing

Skills (Slash Commands)

Instant Web Fetch for External Context

Web Fetch

Real CLI • Real Usage • Real Community

A real Claude Code-style terminal workflow in Python: stream replies, call tools, fetch context, and extend behavior with skills.

🚀 Try it now! Fork it, modify it, make it yours! Pull requests welcome!


⭐ Star History

Star History Chart

✨ Features

Streaming Agent Experience

>>> /stream on
>>> Explain tests/test_agent_loop.py
[streaming answer...]
• Read (tests/test_agent_loop.py) running...
  ↳ lines 1-180
>>> /render-last
  • True API streaming for direct replies plus richer streaming during tool-driven agent loops
  • Built-in /stream toggle for live output and /render-last for clean Markdown re-rendering on demand
  • Designed for real terminal demos: streaming text, visible tool activity, and stable fallback behavior

Programmable Skill Runtime

---
description: Explain code with diagrams and analogies
allowed-tools:
  - Read
  - Grep
  - Glob
arguments: [path]
---

Explain the code in $path. Start with an analogy, then draw a diagram.
  • Markdown-based SKILL.md slash commands
  • Supports project skills, user skills, named arguments, and tool limits

Multi-Provider Support

providers = ["Anthropic Claude", "OpenAI GPT", "Zhipu GLM"]  # + easy to extend

Interactive REPL

>>> Hello!
Assistant: Hi! I'm Clawd Codex, a Python reimplementation...

>>> /help         # Show commands
>>> /             # Show all commands & skills
>>> /save         # Save session
>>> /multiline    # Multi-paragraph input
>>> Tab           # Auto-complete
>>> /explain-code qsort.py   # Run a skill

Complete CLI

clawd              # Start REPL
clawd login        # Configure API
clawd --version    # Check version
clawd config       # View settings

📊 Status

ComponentStatusCount
REPL Commands✅ Complete6+ built-ins
Tool System✅ Complete30+ tools
Automated Tests✅ PresentCore suites for skills, providers, REPL, tools, context
Documentation✅ Complete10+ docs

Core Systems

SystemStatusDescription
CLI Entryclawd, login, config, --version
Interactive REPLRich interactive output, history, tab completion, multiline
Multi-ProviderAnthropic, OpenAI, GLM support
Session PersistenceSave/load sessions locally
Agent LoopTool calling loop implementation
Skill SystemSKILL.md-based slash-command skills with args + tool limits
Context Building🟡Initial prompt injection for workspace, git, and CLAUDE.md; deeper project understanding still needed
Permission System🟡Framework exists, needs integration

Tool System (30+ Tools Implemented)

CategoryToolsStatus
File OperationsRead, Write, Edit, Glob, Grep✅ Complete
SystemBash execution✅ Complete
WebWebFetch, WebSearch✅ Complete
InteractionAskUserQuestion, SendMessage✅ Complete
Task ManagementTodoWrite, TaskManager, TaskStop✅ Complete
Agent ToolsAgent, Brief, Team✅ Complete
ConfigurationConfig, PlanMode, Cron✅ Complete
MCPMCP tools and resources✅ Complete
OthersLSP, Worktree, Skill, ToolSearch✅ Complete

Roadmap Progress

  • Phase 0: Installable, runnable CLI
  • Phase 1: Core Claude Code MVP experience
  • Phase 2: Real tool calling loop
  • 🟡 Phase 3: Context, permissions, recovery (in progress)
  • Phase 4: MCP, plugins, extensibility
  • Phase 5: Python-native differentiators

See FEATURE_LIST.md for detailed feature status and PR guidelines.

🚀 Quick Start

Install

git clone https://github.com/GPT-AGI/Clawd-Code.git
cd Clawd-Code

# Create venv (uv recommended)
uv venv --python 3.11
source .venv/bin/activate

# Install
uv pip install -r requirements.txt

Configure

Option 1: Interactive (Recommended)

python -m src.cli login

This flow will:

  1. ask you to choose a provider: anthropic / openai / glm
  2. ask for that provider's API key
  3. optionally save a custom base URL
  4. optionally save a default model
  5. set the selected provider as default

The configuration file is saved in in ~/.clawd/config.json. Example structure:

{
  "default_provider": "glm",
  "providers": {
    "anthropic": {
      "api_key": "base64-encoded-key",
      "base_url": "https://api.anthropic.com",
      "default_model": "claude-sonnet-4-20250514"
    },
    "openai": {
      "api_key": "base64-encoded-key",
      "base_url": "https://api.openai.com/v1",
      "default_model": "gpt-4"
    },
    "glm": {
      "api_key": "base64-encoded-key",
      "base_url": "https://open.bigmodel.cn/api/paas/v4",
      "default_model": "glm-4.5"
    }
  }
}

Run

python -m src.cli          # Start REPL
python -m src.cli --help   # Show help

That's it! Start chatting with AI in 3 steps.


💡 Usage

REPL Commands

CommandDescription
/Show commands & skills
/helpShow all commands
/saveSave session
/load <id>Load session
/multilineToggle multiline mode
/clearClear history
/exitExit REPL

Skills (Slash Commands)

Skills are markdown-based slash commands stored under .clawd/skills. Each skill lives in its own directory and must be named SKILL.md.

1) Create a project skill

Create:

<project-root>/.clawd/skills/<skill-name>/SKILL.md

Example:

---
description: Explains code with diagrams and analogies
when_to_use: Use when explaining how code works
allowed-tools:
  - Read
  - Grep
  - Glob
arguments: [path]
---

Explain the code in $path. Start with an analogy, then draw a diagram.

2) Use it in the REPL

❯ /
❯ /<skill-name> <args>

Example:

❯ /explain-code qsort.py

Notes

  • User-level skills: ~/.clawd/skills/<skill-name>/SKILL.md
  • Tool limits: allowed-tools controls which tools the skill can use.
  • Arguments: use $ARGUMENTS, $0, $1, or named args like $path (from arguments).
  • Placeholder syntax: use $path, not ${path}.

🎓 Why Clawd Codex?

Based on Real Source Code

  • Not a clone — Ported from actual TypeScript implementation
  • Architectural fidelity — Maintains proven design patterns
  • Improvements — Better error handling, more tests, cleaner code

Python Native

  • Type hints — Full type annotations
  • Modern Python — Uses 3.10+ features
  • Idiomatic — Clean, Pythonic code

User Focused

  • 3-step setup — Clone, configure, run
  • Interactive configclawd login guides you
  • Rich REPL — Tab completion, syntax highlighting
  • Session persistence — Never lose your work

📦 Project Structure

Clawd-Code/
├── src/
│   ├── cli.py           # CLI entry
│   ├── providers/       # LLM providers
│   ├── repl/            # Interactive REPL
│   ├── skills/          # SKILL.md loading and creation
│   └── tool_system/     # Tool registry, loop, validation
├── tests/               # Core test suite
├── .clawd/
│   └── skills/          # Project-local custom skills
└── FEATURE_LIST.md      # Current feature status

🤝 Contributing

We welcome contributions!

# Quick dev setup
pip install -e .[dev]
python -m pytest tests/ -v

See CONTRIBUTING.md for guidelines.


📖 Documentation


⚡ Performance

  • Startup: < 1 second
  • Memory: < 50MB
  • Response: Turn-based assistant output with Rich markdown rendering

🔒 Security

Basic Local Safety Practices

  • No sensitive data in Git
  • API keys obfuscated in config
  • .env files ignored
  • Safe for local development workflows

📄 License

MIT License — See LICENSE


🙏 Acknowledgments

  • Based on Claude Code TypeScript source
  • Independent educational project
  • Not affiliated with Anthropic

🌟 Show Your Support

If you find this useful, please star ⭐ the repo!

Made with ❤️ by Clawd Code Team

⬆ Back to Top



中文版

English | 中文 | Français | Русский | हिन्दी | العربية | Português

🚀 Claude Code Python

基于真实 Claude Code 源码的完整 Python 重实现

从 TypeScript 源码 → 用 Python 重建 ❤️


GitHub stars GitHub forks License: MIT Python 3.10+

🔥 活跃开发中 • 每周更新新功能 🔥

FLEXIBLE SKILL SYSTEMS

基于 Markdown 的斜杠技能系统,支持参数替换、工具限制,以及项目级 / 用户级技能加载。


🎯 为什么是 Clawd Code?

Clawd Code 是一个面向真实使用的 Claude Code Python 重构版:它基于真实 TypeScript 架构移植而来,并且交付的是一个可运行的 CLI Agent,而不只是源码镜像。

  • 真实 Agent Runtime — 具备工具调用循环、流式 REPL、会话历史与多轮执行能力
  • 高保真移植 — 尽可能保留 Claude Code 的原始架构,同时做符合 Python 风格的实现
  • 适合继续开发 — 代码可读、测试完善,并支持基于 Markdown 的技能扩展

Token Streaming + Tool-Aware Agent Loop

流式 Agent 演示

可编程 Skill Runtime 与工具沙箱

Skills(斜杠命令)

Instant Web Fetch for External Context

网页获取

真实的 CLI • 真实的使用 • 真实的社区

这是一个真正可跑的 Claude Code 风格 Python 终端工作流:能流式回答、调工具、抓外部上下文,并通过 skills 扩展行为。

🚀 立即试用!Fork 它、修改它、让它成为你的!欢迎提交 Pull Request!


⭐ Star 历史

Star History Chart

✨ 特性

Streaming Agent Experience

>>> /stream on
>>> 解释 tests/test_agent_loop.py
[流式回答中...]
• Read (tests/test_agent_loop.py) running...
  ↳ lines 1-180
>>> /render-last
  • 直接回答支持真实 API 流式输出,带工具的 agent loop 也具备更完整的流式体验
  • 内置 /stream 开关用于实时输出,/render-last 可按需把上一条回答重新渲染为 Markdown
  • 专门为终端演示优化:一边看回答流出,一边看到工具调用,并保留稳定回退路径

可编程 Skill Runtime

---
description: 用类比 + 图示解释代码
allowed-tools:
  - Read
  - Grep
  - Glob
arguments: [path]
---

请解释 $path 的实现:先给一个类比,再画一个结构示意图。
  • 基于 SKILL.md 的 Markdown 斜杠命令
  • 支持项目级技能、用户级技能、命名参数替换与工具限制

多提供商支持

providers = ["Anthropic Claude", "OpenAI GPT", "Zhipu GLM"]  # + 易于扩展

交互式 REPL

>>> 你好!
Assistant: 嗨!我是 Clawd Codex,一个 Python 重实现...

>>> /help         # 显示命令
>>> /             # 显示命令与技能
>>> /save         # 保存会话
>>> /multiline    # 多行输入模式
>>> Tab           # 自动补全
>>> /explain-code qsort.py   # 运行一个技能

完整的 CLI

clawd              # 启动 REPL
clawd login        # 配置 API
clawd --version    # 检查版本
clawd config       # 查看设置

📊 状态

组件状态数量
REPL 命令✅ 完成6+ 内置命令
工具系统✅ 完成30+ 工具
自动化测试✅ 已覆盖Skills、providers、REPL、tools、context
文档✅ 完成10+ 文档

核心系统

系统状态描述
CLI 入口clawdloginconfig--version
交互式 REPL丰富的交互输出、历史记录、Tab 补全、多行输入
多提供商支持支持 Anthropic、OpenAI、GLM
会话持久化本地保存/加载会话
Agent Loop工具调用循环实现
Skill 系统基于 SKILL.md 的 /skill 技能:参数替换 + 工具限制
上下文构建🟡已接入 workspace、git、CLAUDE.md 的基础上下文注入,仍需补强项目级理解
权限系统🟡框架已存在,需要集成

工具系统(已实现 30+ 工具)

类别工具状态
文件操作Read, Write, Edit, Glob, Grep✅ 完成
系统Bash 执行✅ 完成
网络WebFetch, WebSearch✅ 完成
交互AskUserQuestion, SendMessage✅ 完成
任务管理TodoWrite, TaskManager, TaskStop✅ 完成
Agent 工具Agent, Brief, Team✅ 完成
配置Config, PlanMode, Cron✅ 完成
MCPMCP 工具和资源✅ 完成
其他LSP, Worktree, Skill(SKILL.md), ToolSearch✅ 完成

路线图进度

  • 阶段 0:可安装、可运行的 CLI
  • 阶段 1:Claude Code 核心 MVP 体验
  • 阶段 2:真实工具调用闭环
  • 🟡 阶段 3:上下文、权限、恢复能力(进行中)
  • 阶段 4:MCP、插件、扩展性
  • 阶段 5:Python 原生差异化特性

详细功能状态和 PR 指南请查看 FEATURE_LIST.md

🚀 快速开始

安装

git clone https://github.com/GPT-AGI/Clawd-Code.git
cd Clawd-Code

# 创建虚拟环境(推荐使用 uv)
uv venv --python 3.11
source .venv/bin/activate

# 安装
uv pip install -r requirements.txt

配置

方式 1:交互式(推荐)

python -m src.cli login

这个流程会:

  1. 让你选择 provider:anthropic / openai / glm
  2. 让你输入该 provider 的 API key
  3. 可选:保存自定义 base URL
  4. 可选:保存默认 model
  5. 将该 provider 设为默认

配置文件会保存在 ~/.clawd/config.json。示例结构:

{
  "default_provider": "glm",
  "providers": {
    "anthropic": {
      "api_key": "base64-encoded-key",
      "base_url": "https://api.anthropic.com",
      "default_model": "claude-sonnet-4-20250514"
    },
    "openai": {
      "api_key": "base64-encoded-key",
      "base_url": "https://api.openai.com/v1",
      "default_model": "gpt-4"
    },
    "glm": {
      "api_key": "base64-encoded-key",
      "base_url": "https://open.bigmodel.cn/api/paas/v4",
      "default_model": "glm-4.5"
    }
  }
}

运行

python -m src.cli          # 启动 REPL
python -m src.cli --help   # 显示帮助

就这样! 3 步开始与 AI 对话。


💡 使用

REPL 命令

命令描述
/显示命令与技能
/help显示所有命令
/save保存会话
/load <id>加载会话
/multiline切换多行模式
/clear清空历史
/exit退出 REPL

Skills(技能 / 斜杠命令)教程

技能是存放在 .clawd/skills 下的 Markdown 斜杠命令。每个技能对应一个目录,并且文件名固定为 SKILL.md

1)创建项目技能

创建:

<project-root>/.clawd/skills/<skill-name>/SKILL.md

示例:

---
description: 用类比 + 图示解释代码
when_to_use: 当用户问“这段代码怎么工作?”时使用
allowed-tools:
  - Read
  - Grep
  - Glob
arguments: [path]
---

请解释 $path 的实现:先给一个类比,再画一个结构示意图。

2)在 REPL 中使用

❯ /
❯ /<skill-name> <args>

示例:

❯ /explain-code qsort.py

补充说明

  • 用户级技能:~/.clawd/skills/<skill-name>/SKILL.md
  • 工具限制:allowed-tools 用于限制技能允许调用的工具集合
  • 参数替换:支持 $ARGUMENTS$0$1、以及命名参数(例如 $path,来自 arguments
  • 占位符写法:请使用 $path,不要写成 ${path}

🎓 为什么选择 Clawd Codex?

基于真实源码

  • 不是克隆 — 从真实的 TypeScript 实现移植而来
  • 架构保真 — 保持经过验证的设计模式
  • 持续改进 — 更好的错误处理、更多测试、更清晰的代码

原生 Python

  • 类型提示 — 完整的类型注解
  • 现代 Python — 使用 3.10+ 特性
  • 符合习惯 — 干净的 Python 风格代码

以用户为中心

  • 3 步设置 — 克隆、配置、运行
  • 交互式配置clawd login 引导你完成设置
  • 丰富的 REPL — Tab 补全、语法高亮
  • 会话持久化 — 永不丢失你的工作

📦 项目结构

Clawd-Code/
├── src/
│   ├── cli.py           # CLI 入口
│   ├── providers/       # LLM 提供商
│   ├── repl/            # 交互式 REPL
│   ├── skills/          # SKILL.md 加载与创建
│   └── tool_system/     # 工具注册、循环与校验
├── tests/               # 核心测试套件
├── .clawd/
│   └── skills/          # 项目级自定义技能
└── FEATURE_LIST.md      # 当前功能状态

🤝 贡献

我们欢迎贡献!

# 快速开发设置
pip install -e .[dev]
python -m pytest tests/ -v

查看 CONTRIBUTING.md 了解指南。


📖 文档


⚡ 性能

  • 启动时间:< 1 秒
  • 内存占用:< 50MB
  • 响应:回合式输出,支持 Rich Markdown 渲染

🔒 安全

基础本地安全实践

  • Git 中无敏感数据
  • API 密钥在配置中做了基础混淆
  • .env 文件被忽略
  • 适合本地开发工作流

📄 许可证

MIT 许可证 — 查看 LICENSE


🙏 致谢

  • 基于 Claude Code TypeScript 源码
  • 独立的教育项目
  • 未隶属于 Anthropic

🌟 支持我们

如果你觉得这个项目有用,请给个 star ⭐!

用 ❤️ 制作 by Clawd Code 团队

⬆ 回到顶部

Frequently Asked Questions

What is claude-code-python?

claude-code-python is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by GPT-AGI. Clawd Code: Reconstructing Claude Code in Python - 基于Claude Code源码的Python重构实现. It has 121 GitHub stars.

Is claude-code-python safe to use?

Yes. claude-code-python passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install claude-code-python?

Clone the repository with "git clone https://github.com/GPT-AGI/claude-code-python" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is claude-code-python written in?

claude-code-python is primarily written in Python. It is open-source under GPT-AGI on GitHub, so you can review or fork the full source.

Are there alternatives to claude-code-python?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh claude-code-python against similar tools.

Comments (0)

No comments yet. Be the first to share your thoughts!

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI Agentsai-agentsanthropicclaude-code
View details
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI Agentsai-agentsbrainstorming
View details

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI Agentsai-agentsanthropicclaude-code
View details

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI Agentsclaude-codeai-tools
View details

claude-code

by anthropics

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

120,03119,897Shell
AI Agents
View details

Developers Also Liked

Based on votes and bookmarks from developers who liked this skill

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI Agentsai-agentsanthropicclaude-code
View details
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI Agentsai-agentsbrainstorming
View details

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP Serversapisai-tools
View details

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI Agentsai-agentsanthropicclaude-code
View details

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI Agentsclaude-codeai-tools
View details