by bfly123
Real-time multi-AI collaboration: Claude, Codex & Gemini with persistent context, minimal token overhead
# Add to your Claude Code skills
git clone https://github.com/bfly123/claude_code_bridgeMulti-Model Collaboration via Split-Pane Terminal Claude · Codex · Gemini · OpenCode · Droid Lightweight async messaging — full CLI power, every interaction visible
<p> <img src="https://img.shields.io/badge/Every_Interaction_Visible-096DD9?style=for-the-badge" alt="Every Interaction Visible"> <img src="https://img.shields.io/badge/Every_Model_Controllable-CF1322?style=for-the-badge" alt="Every Model Controllable"> </p>English | Chinese

Introduction: Multi-model collaboration avoids model bias, cognitive blind spots, and context limits. Unlike MCP or API-based approaches, ccb gives you a WYSIWYG split-pane terminal where every interaction is visible and every model is controllable.
| Feature | Benefit | | :--- | :--- | | | Multiple AI models in split-pane CLI. See everything, control everything. | | | Each AI maintains its own memory. Close and resume anytime ( flag). | | | Sends lightweight prompts instead of full file history. | | | Integrates directly into (recommended) or tmux. No complex servers required. |
<h2 align="center">🚀 What's New</h2> <details open> <summary><b>v5.2.6</b> - Async Communication & Gemini 0.29 Compatibility</summary>No comments yet. Be the first to share your thoughts!
-r🔧 Gemini CLI 0.29.0 Support:
ccb-ping and ccb-mounted gain --autostart flag to launch offline provider daemonsccb-cleanup utility for removing zombie daemons and stale state files🔗 Async Communication Fixes:
CCB_DONE even when req_id doesn't match exactlyopencode_comm.py now matches both old hex and new timestamp-based formatsCCB_DONE marker...