Claude Code Session Bridge

session-bridge

    Peer-to-peer communication between Claude Code sessions

    Quick Start ·
    Commands ·
    How It Works ·
    Limitations

When you're working across multiple repos — a shared library and its consumer app, a backend and frontend, microservices — each Claude Code session is isolated. session-bridge lets them talk to each other.

The Library agent answers questions about breaking changes. The Consumer agent asks what API replaced a deprecated function. The agent responds with its full context — no approximation, no extra API cost.

https://github.com/user-attachments/assets/ce893322-5749-42be-9973-e36e60b969a6

Getting Started

1. Install

Alternative: install via git clone

Then start Claude with:

Or add to ~/.claude/settings.json for permanent loading:

2. Use it

Open two terminals — one for each project.

Terminal 1 (the project that has the answers):

Terminal 2 (the project that needs answers):

That's it. The Library agent responds with its full session context — it knows what it changed, why, and how. No extra API calls, no approximation.

Commands

Tip: You don't always need explicit commands. Just tell your agent "ask the library about X" in natural language and it will use the bridge automatically.

How It Works

Listen mode

The key innovation: /bridge listen puts the agent into a continuous listening loop. When a query arrives, the agent itself responds — with its full conversation context, not an approximation.

- No background process — the agent IS the responder
- No claude -p calls — zero extra API cost for responses
- Full context — the agent that made the changes answers questions about them
- Includes real code — responses contain actual file contents, not just descriptions

Design principles:
- No shared…