ruvnet/open-claude-code

Nightly Claude Code CLI Decompile — Reverse Engineered & Rebuilt

What it solves

Open Claude Code provides an open-source alternative to Anthropic's proprietary Claude Code CLI. It allows developers to use a powerful, agentic command-line interface for coding tasks—such as explaining codebases, fixing bugs, and refactoring—without relying on a closed-source binary, while adding support for multiple AI providers beyond just Anthropic.

How it works

It is a clean-room implementation rebuilt from intelligence gathered via AI-powered decompilation of the official npm package. The system operates as an async generator agent loop that can execute a wide array of tools. It supports multiple AI providers (Anthropic, OpenAI, Google, AWS Bedrock, and Google Vertex) and integrates with the Model Context Protocol (MCP) to extend its toolset via external servers.

Who it’s for

Developers who want a highly capable AI coding agent in their terminal, those who prefer open-source tooling for their development workflow, and users who want to use Claude Code's architecture with different LLM providers.

Highlights

  • Extensive Toolset: Includes 25 built-in tools for bash execution, file editing, web searching, and LSP integration.
  • Multi-Provider Support: Compatible with OpenAI, Google, AWS Bedrock, and Vertex AI in addition to Anthropic.
  • Agentic Capabilities: Supports custom agents, skills, and sub-agent spawning for complex tasks.
  • MCP Integration: Supports four different transports (stdio, SSE, Streamable HTTP, WebSocket) for connecting to MCP servers.
  • Customizable Behavior: Allows project-specific rules via CLAUDE.md and detailed configuration through settings files.

Related

  • Project
    davila7/claude-code-templates

    A comprehensive collection of ready-to-use agents, commands, and MCP integrations designed to extend the functionality of Anthropic's Claude Code.

  • Project
    wesammustafa/Claude-Code-Everything-You-Need-to-Know

    A thorough, example‑rich tutorial for Anthropic’s Claude Code CLI, covering installation, prompt engineering, and advanced extensions (Skills, Hooks, Sub‑agents, Workflows, MCP) to let developers use Claude for repo‑wide code analysis, editing, testing and automation.

  • Project
    raine/claude-code-proxy

    A proxy that allows the Claude Code coding harness to use alternative LLM providers like OpenAI Codex, Kimi, Grok, and Cursor Agent by translating Anthropic API traffic.

  • Project
    claude-code-best/claude-code

    An open-source recreation and extension of Anthropic's Claude Code, providing a CLI agent with multi-model support and advanced orchestration tools.

  • Project
    MadAppGang/claudish

    Claudish is a CLI that lets you run Claude Code with any LLM—cloud or local—by proxying requests through a local Anthropic‑compatible server. It supports 580+ OpenRouter models, Gemini, OpenAI, Ollama, and many others, using a simple `provider@model` syntax, and works both online and fully offline.