LpcPaul

LpcPaul / FeishuCodexBridge

Public

Bridge Feishu/Lark bot messages to local Codex CLI with lightweight topic context management

bridge codex feishu lark launchd
16
1
75% credibility
Found Jun 01, 2026 at 16 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

FeishuCodexBridge is a connector that brings an AI coding assistant into the Feishu workplace messaging app. Once installed on a Mac, it listens for messages sent to a bot in private chats or group channels, forwards those messages to the AI assistant, and sends the responses back to the original conversation. The bridge supports interactive features like buttons and forms, manages conversation topics over time, and can automatically create Feishu documents for longer AI-generated content.

How It Works

1
💬 You want AI help inside Feishu

You use Feishu for work chat and wish you could ask an AI assistant questions without leaving the app.

2
🔧 You install the bridge on your Mac

The setup script guides you through connecting your Feishu workspace and your Codex assistant account.

3
🤖 Your AI assistant joins Feishu

A bot appears in your Feishu chats, ready to answer questions and help with tasks whenever you need it.

4
You can ask questions in different ways
👤
Private chat with the bot

Send direct messages and get instant AI responses back in the same conversation.

👥
Group chat with a mention

Type @Codex in a group channel and the AI joins the conversation to help everyone.

5
✨ The AI understands context

It remembers your conversation and can continue working on previous tasks without starting over.

6
📝 Long answers become documents

When the AI generates detailed explanations, it automatically creates a Feishu document so you can read and share them easily.

🎉 You get help without switching apps

Your AI coding assistant is now available right where your team communicates, making it effortless to get expert help anytime.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 16 to 16 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is FeishuCodexBridge?

This project connects Feishu/Lark messaging to OpenAI's Codex CLI, letting you chat with Codex directly from Feishu. The bot receives your messages, forwards them to Codex, and sends responses back as Feishu messages. It handles conversation context automatically, switching topics when you go idle and letting you resume previous threads by clicking card buttons. The bridge runs as a macOS background service using launchd, persists conversation state in SQLite, and supports interactive cards, Feishu docs creation, and group chat scenarios.

Why is it gaining traction?

The appeal is natural: you get Codex-powered coding help without leaving your chat app. The topic management is the standout feature -- it intelligently tracks conversation threads, auto-switches after idle periods, and preserves context across card button clicks. Long-running tasks get progress updates, and the bot acknowledges requests immediately before Codex even starts working. For teams already living in Feishu, this removes the friction of context-switching to a terminal.

Who should use this?

Feishu users who want Codex coding assistance without leaving their messaging workflow. Developers comfortable with macOS-only tooling and willing to set up a Feishu developer app. Not suitable for Windows or Linux environments, and you need Codex CLI installed and authenticated first.

Verdict

At 16 stars, this is experimental-stage software with a credibility score of 0.75%. The test coverage is solid and the feature set shows careful thought, but the macOS-only constraint and minimal documentation make it a risky production choice. Worth exploring if you specifically need Feishu integration and can tolerate early-stage rough edges, but most teams should wait for more maturity.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.