oboard/

claude-code-rev

GitHub

A restored Claude Code source tree (TypeScript) that is runnable locally via Bun. It provides a multi-provider CLI with GitHub Models and Copilot-backed endpoints, plus documented run/install commands.

3.3kstars

3.8kforks

10issues

2026since

Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap

Egonex-AI/

Understand-Anything

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

77k6.5kTypeScriptgiant

ruvnet/

ruflo

▲ 629/wk

🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

67k8.0kTypeScript

CherryHQ/

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

49k4.7kTypeScriptgiant

chatboxai/

chatbox

Powerful AI Client

41k4.2kTypeScriptgiant

diegosouzapw/

OmniRoute

▲ 6.3k/wk

Never stop coding. Free MIT AI gateway: one endpoint, 290+ providers (90+ free), 500+ models — Kimi, Claude, GPT, OpenAI, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 500+ contributors

39k5.2kTypeScript

Yeachan-Heo/

oh-my-claudecode

▲ 190/wk

Teams-first Multi-agent orchestration for Claude Code

38k3.4kTypeScript

Compareclaude-code-rev vs Understand-Anything claude-code-rev vs ruflo claude-code-rev vs cherry-studio

Reviewgenerated from repository data · Aug 5, 2026

What it is

Runnable ClaudeCode source code restored from source maps and missing modules. It aims to be a usable, runnable restored workspace rather than the original upstream state.

How it works

The restored CLI runs through a bootstrap path and provides a multi-provider runtime. Providers currently supported:

github-models: OpenAI-compatible GitHub Models endpoint
github-copilot: Copilot-backed endpoint for Claude models Authentication lookup order:
provider-specific env var
GH_TOKEN
GITHUB_TOKEN
gh auth token

Getting started

Requirements:

Bun 1.3.5 or newer
Node.js 24 or newer

Install dependencies:

bun install

Run the restored CLI:

bun run dev

Print the restored version:

bun run version

gh auth login

Use GitHub Models with the restored Claude Code runtime:

bun run dev --settings '{"provider":"github-models"}'

Specify a GitHub Models model:

bun run dev --settings '{"provider":"github-models"}' --model "openai/gpt-4.1"

Use GitHub Copilot with the restored Claude Code runtime:

bun run dev --settings '{"provider":"github-copilot"}'

Interactive provider switching:

/provider

Common commands:

/provider to open provider picker
/provider info to show current provider and environment overrides
/provider github-copilot to switch provider
/model to continue model selection for the active provider Switch to a Copilot Claude model:

bun run dev --settings '{"provider":"github-copilot"}' --model "claude-opus-4.6"

Copilot models validated with Claude Code runtime:

claude-sonnet-4.6
claude-opus-4.6
claude-haiku-4.5
claude-sonnet-4.5
claude-opus-4.5
claude-sonnet-4 Current limitations:
Copilot-hosted Claude models run through the existing Claude Code agent/runtime path.
Copilot-hosted GPT/Grok models not fully wired yet due to needing Copilot's /responses API instead of the current chat/messages path.

中文说明

(同上，中文版本提供相同信息，包含运行方式与 Provider 支持说明)

SharePost on X LinkedIn