Is the agent-bridge MCP server actively maintained?

The agent-bridge MCP server was last committed 29d ago and has 3 contributors. Issue health: 40% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

agent-bridge MCP Server

Name: raysonmeng/agent-bridge
Rating: 3.8 (1 reviews)
Author: raysonmeng

raysonmeng/agent-bridge

Score: 71.0 Rank #3840 Agent Framework

[![AgentRank](https://agentrank-ai.com/api/v1/badge/raysonmeng--agent-bridge)](https://agentrank-ai.com/tool/raysonmeng--agent-bridge/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

Are you the maintainer of raysonmeng/agent-bridge? Claim this listing →

A local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。

Add AgentRank to Claude Code Discover and compare tools like raysonmeng/agent-bridge — your AI finds the right one automatically

Get API Access →

claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

raysonmeng/agent-bridge is a TypeScript tool licensed under MIT. A local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。 Topics: agent-collaboration, claude-code, cli, codex, developer-tools, local-first, mcp, model-context-protocol, multi-agent, ai, anthropic, bun, llm, mcp-server, openai, plugin, typescript.

Ranked #3840 out of 24846 indexed tools.

Ecosystem

TypeScript MIT

agent-collaborationclaude-codeclicodexdeveloper-toolslocal-firstmcpmodel-context-protocolmulti-agentaianthropicbunllmmcp-serveropenaiplugintypescript

Score Breakdown

Stars 15% 385

385 stars → growing community

Freshness 25% 29d ago

Last commit 29d ago → recently updated

Issue Health 25% 40%

34/84 issues closed → many open issues

Contributors 10% 3

3 contributors → small team

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads N/A

Forks 63

Description Good

License MIT

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

Issue Health high impact

You have 50 open vs 34 closed issues — triaging stale issues improves health

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

Markdown

[![AgentRank](https://agentrank-ai.com/api/v1/badge/raysonmeng--agent-bridge)](https://agentrank-ai.com/tool/raysonmeng--agent-bridge/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

HTML

<a href="https://agentrank-ai.com/tool/raysonmeng--agent-bridge/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/raysonmeng--agent-bridge" alt="AgentRank"></a>

Embed Widget docs →

HTML

<script src="https://agentrank-ai.com/embed.js" data-tool="raysonmeng/agent-bridge"></script>

Details

Stars: 385
Forks: 63
Open Issues: 50
Closed Issues: 34
Contributors: 3
Dependents: —
Language: TypeScript
License: MIT
Last Commit: 29d ago

Matched Queries

topic:mcptopic:mcp-servertopic:model-context-protocol

From the README

<p align="center"></p>

# AgentBridge

[中文文档](README.zh-CN.md)

**🌐 Website: [raysonmeng.github.io/agent-bridge](https://raysonmeng.github.io/agent-bridge/)**, with an animated replay of a real session.

> Discussed on [LINUX DO](https://linux.do) — the developer community. / 在 [LINUX DO](https://linux.do) 开发者社区交流。

Local bridge for bidirectional communication between Claude Code and Codex inside the same working session.

<p align="center">
  
  <br />
  <sub>A real session, replayed — Codex's review is pushed into Claude's live session, no human relay. <a href="https://raysonmeng.github.io/agent-bridge/">Full animated demo →</a></sub>
</p>

What that buys you, concretely:

- **Cross-review** — Codex implements; Claude reviews the diff *inside the same session* and pushes change requests straight back into Codex's thread. Two providers check each other's work without copy-paste.
- **Task splits from one prompt** — ask either agent to propose a division of labor with the other, and th

Read full README on GitHub →