claude-code-open

Name: claude-code-open
Author: kill136

Issues

Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.

158stars

56forks

TypeScript

Installation

# Add to your Claude Code skills
git clone https://github.com/kill136/claude-code-open

Getting Started

Guides for using ai agents skills like claude-code-open.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportIssues

Last scanned: 5/30/2026

{
  "issues": [
    {
      "type": "npm-audit",
      "message": "@anthropic-ai/claude-code: Claude Code: Trust Dialog Bypass via Git Worktree Spoofing Allows Arbitrary Code Execution",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "@discordjs/rest: Vulnerability found",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "@larksuiteoapi/node-sdk: Vulnerability found",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "@protobufjs/utf8: protobufjs has overlong UTF-8 decoding",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "@trpc/client: Vulnerability found",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "@trpc/server: tRPC 11 WebSocket DoS Vulnerability",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "@vitest/mocker: Vulnerability found",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "@vitest/ui: Vulnerability found",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "@xmldom/xmldom: xmldom: XML injection via unsafe CDATA serialization allows attacker-controlled markup insertion",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "ajv: ajv has ReDoS when using `$data` option",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "ajv-formats: Vulnerability found",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "axios: Axios has a NO_PROXY Hostname Normalization Bypass that Leads to SSRF",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "brace-expansion: brace-expansion: Zero-step sequence causes process hang and memory exhaustion",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "conf: Vulnerability found",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "cos-nodejs-sdk-v5: Vulnerability found",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "discord.js: Vulnerability found",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "dompurify: DOMPurify contains a Cross-site Scripting vulnerability",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "electron: Electron: AppleScript injection in app.moveToApplicationsFolder on macOS",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "esbuild: esbuild enables any website to send any requests to the development server and read the response",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "fast-uri: fast-uri vulnerable to path traversal via percent-encoded dot segments",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "fast-xml-parser: fast-xml-parser has an entity encoding bypass via regex injection in DOCTYPE entity names",
      "severity": "critical"
    },
    {
      "type": "npm-audit",
      "message": "file-type: file-type affected by infinite loop in ASF parser on malformed input with zero-size sub-header",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "flatted: flatted vulnerable to unbounded recursion DoS in parse() revive phase",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "follow-redirects: follow-redirects leaks Custom Authentication Headers to Cross-Domain Redirect Targets",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "form-data: form-data uses unsafe random function in form-data for choosing boundary",
      "severity": "critical"
    },
    {
      "type": "npm-audit",
      "message": "imap: Vulnerability found",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "imap-simple: Vulnerability found",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "ip-address: ip-address has XSS in Address6 HTML-emitting methods",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "lodash: lodash vulnerable to Code Injection via `_.template` imports key names",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "mailparser: Vulnerability found",
      "severity": "low"
    },
    {
      "type": "npm-audit",
      "message": "minimatch: minimatch has a ReDoS via repeated wildcards with non-matching literal in pattern",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "monaco-editor: Vulnerability found",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "node-notifier: Vulnerability found",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "nodemailer: Nodemailer has SMTP command injection due to unsanitized `envelope.size` parameter",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "path-to-regexp: path-to-regexp vulnerable to Denial of Service via sequential optional groups",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "picomatch: Picomatch: Method Injection in POSIX Character Classes causes incorrect Glob Matching",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "postcss: PostCSS has XSS via Unescaped </style> in its CSS Stringify Output",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "protobufjs: Arbitrary code execution in protobufjs",
      "severity": "critical"
    },
    {
      "type": "npm-audit",
      "message": "qs: qs's arrayLimit bypass in comma parsing allows denial of service",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "request: Server-Side Request Forgery in Request",
      "severity": "critical"
    },
    {
      "type": "npm-audit",
      "message": "rollup: Rollup 4 has Arbitrary File Write via Path Traversal",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "semver: semver vulnerable to Regular Expression Denial of Service",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "tar: node-tar Symlink Path Traversal via Drive-Relative Linkpath",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "tmp: tmp has Path Traversal via unsanitized prefix/postfix that enables directory escape",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "tough-cookie: tough-cookie Prototype Pollution vulnerability",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "undici: Undici has an unbounded decompression chain in HTTP responses on Node.js Fetch API via Content-Encoding leads to resource exhaustion",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "utf7: Vulnerability found",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "uuid: uuid: Missing buffer bounds check in v3/v5/v6 when buf is provided",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "vite: Vite Vulnerable to Path Traversal in Optimized Deps `.map` Handling",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "vite-node: Vulnerability found",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "vitest: Vulnerability found",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "ws: ws: Uninitialized memory disclosure",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "xlsx: Prototype Pollution in sheetJS",
      "severity": "high"
    }
  ],
  "status": "FAILED",
  "scannedAt": "2026-05-30T16:00:31.961Z",
  "npmAuditRan": true,
  "pipAuditRan": true
}

README.md

Frequently Asked Questions

What is claude-code-open?

claude-code-open is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by kill136. Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed. It has 158 GitHub stars.

Is claude-code-open safe to use?

claude-code-open failed SkillsLLM's automated security scan, which flagged one or more high-severity issues. Review the Security Report section carefully before using it.

How do I install claude-code-open?

Clone the repository with "git clone https://github.com/kill136/claude-code-open" and add it to your Claude Code skills directory (see the Installation section above).

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

claude-code-open is primarily written in TypeScript. It is open-source under kill136 on GitHub, so you can review or fork the full source.

Are there alternatives to claude-code-open?

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-open against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

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

Related Skills

superpowers

by obra

An agentic skills framework & software development methodology that works.

234,966

blink cursor-notebook-mcp

Axon

The open-source AI coding assistant that runs everywhere

Use any model. Extend with plugins. Let AI agents build your project.

Website | Live Demo | User Guide | Discord | 中文

Watch on YouTube | Download video | Try Live Demo

Axon is a free, open-source AI coding assistant with a built-in Web IDE, multi-agent task system, and self-evolution capabilities. It gives you full control — choose your AI provider, extend functionality through plugins and MCP servers, and even let the AI modify its own source code.

Quick Start

# Install
npm install -g axon

# Set your API key (Anthropic, OpenRouter, DeepSeek, or any OpenAI-compatible provider)
# No API key? Get one at https://api.chatbi.site (Claude Sonnet & Opus, OpenAI-compatible)
export ANTHROPIC_API_KEY="sk-..."

# Terminal mode
axon

# Web IDE mode (opens at http://localhost:3456)
axon-web

Other install methods

Windows: Download install.bat and double-click.

macOS / Linux:

curl -fsSL https://raw.githubusercontent.com/kill136/claude-code-open/private_web_ui/install.sh | bash

China mirror:

curl -fsSL https://gitee.com/lubanbbs/claude-code-open/raw/private_web_ui/install.sh | bash

# Web IDE
docker run -it \
  -e ANTHROPIC_API_KEY=your-api-key \
  -p 3456:3456 \
  -v $(pwd):/workspace \
  -v ~/.axon:/root/.axon \
  wbj66/axon node /app/dist/web-cli.js --host 0.0.0.0

# Terminal only
docker run -it \
  -e ANTHROPIC_API_KEY=your-api-key \
  -v $(pwd):/workspace \
  -v ~/.axon:/root/.axon \
  wbj66/axon

git clone https://github.com/kill136/claude-code-open.git
cd claude-code-open
npm install && npm run build
node dist/cli.js        # Terminal
node dist/web-cli.js    # Web IDE

macOS / Linux:

curl -fsSL https://raw.githubusercontent.com/kill136/claude-code-open/private_web_ui/uninstall.sh | bash

China mirror:

curl -fsSL https://gitee.com/lubanbbs/claude-code-open/raw/private_web_ui/uninstall.sh | bash

Windows (PowerShell):

irm https://raw.githubusercontent.com/kill136/claude-code-open/private_web_ui/uninstall.ps1 | iex

Windows (cmd):

curl -fsSL https://raw.githubusercontent.com/kill136/claude-code-open/private_web_ui/uninstall.bat -o uninstall.bat && uninstall.bat

What makes Axon different

Web IDE

A full browser-based IDE — not just a chat window.

Monaco Editor with multi-tab, syntax highlighting, and AI-powered hover tips
File tree with right-click context menus, just like VS Code
AI-enhanced editing — select code, ask AI, get inline changes
Real-time streaming via WebSocket
Session management — create, resume, fork, and export conversations
Checkpoint & Rewind — snapshot files and time-travel through your session

Multi-Agent Blueprint System

Give Axon a complex task and it breaks it down across multiple AI agents working in parallel.

Planner decomposes the task into an execution graph
Lead Agent coordinates workers and tracks progress
Workers execute independently with full tool access
Task Queue with priority scheduling and persistence
Auto-review validates output before marking complete

Self-Evolution

Axon can modify its own source code, compile, and hot-reload — adding new tools and capabilities on the fly.

You: "Add a tool that queries weather data"
Axon: *writes the tool code, compiles TypeScript, restarts, tool is ready*

37+ Built-in Tools

Category	Tools
File ops	Read, Write, Edit, MultiEdit, Glob, Grep
Execution	Bash, background tasks, scheduled jobs
Web	Fetch pages, search the web
Code	Jupyter notebooks, LSP, Tree-sitter parsing
Browser	Playwright-based full browser automation
Planning	Plan mode, Blueprint, sub-agents
Memory	Long-term memory with semantic search, vector store, BM25
Integration	MCP protocol, Skills marketplace, plugins
Perception	Camera (Eye), Microphone (Ear), Speech (Mouth)

Extensible by Design

MCP Protocol — connect any Model Context Protocol server
Skills — community-contributed prompt-based capabilities (PDF, DOCX, XLSX, PPTX, and more)
Plugins — write custom JavaScript/TypeScript extensions
Hooks — pre/post tool execution callbacks
Custom tools — create tools at runtime that persist across sessions

Works with Any Provider

Provider	Setup
Anthropic	`ANTHROPIC_API_KEY=sk-ant-...`
OpenRouter	`ANTHROPIC_BASE_URL=https://openrouter.ai/api/v1`
AWS Bedrock	`CLAUDE_CODE_USE_BEDROCK=1`
Google Vertex AI	`CLAUDE_CODE_USE_VERTEX=1`
Any OpenAI-compatible	Set `ANTHROPIC_BASE_URL` to your endpoint

Proxy Server

Share your API key or Claude subscription with other devices on your network.

# On the host (has the API key)
axon-proxy -k my-secret

# On client machines
export ANTHROPIC_API_KEY="my-secret"
export ANTHROPIC_BASE_URL="http://<host-ip>:8082"
axon

Flag	Default	Description
`-k, --proxy-key`	auto-generated	Key clients use to authenticate
`-p, --port`	`8082`	Port to listen on
`-H, --host`	`0.0.0.0`	Bind address
`--anthropic-key`	auto-detect	Override Anthropic API key
`--auth-token`	auto-detect	Override OAuth access token
`--target`	`https://api.anthropic.com`	Upstream API URL

The proxy auto-detects credentials: ANTHROPIC_API_KEY env var > ~/.axon/.credentials.json (OAuth).

Configuration

Variable	Description	Default
`ANTHROPIC_API_KEY`	API key (required)	-
`ANTHROPIC_BASE_URL`	Custom API endpoint	`https://api.anthropic.com`
`AXON_LANG`	Language (`en`/`zh`)	auto-detect
`AXON_CONFIG_DIR`	Config/data directory	`~/.axon`

MCP Servers

Add external tool servers in .axon/settings.json:

{
  "mcpServers": {
    "filesystem": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path"]
    }
  }
}

CLI Reference

axon                          # Interactive mode
axon "Analyze this project"   # With initial prompt
axon -p "Explain this code"   # Print mode (non-interactive)
axon -m opus "Complex task"   # Specify model
axon --resume                 # Resume last session
axon-web                      # Web IDE
axon-web -p 8080 -H 0.0.0.0  # Custom port and host
axon-web --ngrok              # Public tunnel
axon-web --evolve             # Self-evolution mode

Community

Website: chatbi.site
Live Demo: voicegpt.site
Discord: Join us
X (Twitter): @wangbingjie1989

Contributing

PRs and issues are welcome! See CONTRIBUTING.md for guidelines.

Building a Skill or Plugin

The fastest way to extend Axon is to write a Skill (a prompt file with structured instructions) or a Plugin (a JS/TS module with lifecycle hooks). Both are auto-loaded from ~/.axon/skills/ and ~/.axon/plugins/.

License

Axon is dual-licensed:

Open Source — AGPL-3.0. Free for personal use, academic research, and open-source projects. If you modify Axon or use it to provide a network service, you must release your complete source code under AGPL-3.0.
Commercial — For proprietary/c