Skip to content

Real-time multi-AI collaboration: Claude, Codex & Gemini with persistent context, minimal token overhead

License

Notifications You must be signed in to change notification settings

HanCheg0812/claude_code_bridge

Β 
Β 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

Claude Code Bridge (ccb) v2.3.9

Silky Smooth Claude & Codex & Gemini Collaboration via Split-Pane Terminal

Build a real AI expert team. Give Claude Code / Codex / Gemini / OpenCode partners that never forget.

δΊ€δΊ’ηš†ε―θ§ ζ¨‘εž‹ηš†ε―ζŽ§

Every Interaction Visible Every Model Controllable

Version License: MIT Python 3.10+ Platform

English | δΈ­ζ–‡

Split-pane collaboration demo

Introduction: Multi-model collaboration effectively avoids model bias, cognitive blind spots, and context limitations. However, MCP, Skills and other direct API approaches have many limitations. This project offers a new solution.

⚑ Why ccb?

Feature Benefit
πŸ–₯️ Visual & Controllable Multiple AI models in split-pane CLI. See everything, control everything.
🧠 Persistent Context Each AI maintains its own memory. Close and resume anytime (-r flag).
πŸ“‰ Token Savings Sends lightweight prompts instead of full file history.
πŸͺŸ Native Workflow Integrates directly into WezTerm (recommended) or tmux. No complex servers required.

πŸš€ Quick Start

Step 1: Install WezTerm (native .exe for Windows)

Step 2: Choose installer based on your environment:

Linux
git clone https://github.com/bfly123/claude_code_bridge.git
cd claude_code_bridge
./install.sh install
macOS
git clone https://github.com/bfly123/claude_code_bridge.git
cd claude_code_bridge
./install.sh install

Note: If commands not found after install, see macOS Troubleshooting.

WSL (Windows Subsystem for Linux)

Use this if your Claude/Codex/Gemini runs in WSL.

⚠️ WARNING: Do NOT install or run ccb as root/administrator. Switch to a normal user first (su - username or create one with adduser).

# Run inside WSL terminal (as normal user, NOT root)
git clone https://github.com/bfly123/claude_code_bridge.git
cd claude_code_bridge
./install.sh install
Windows Native

Use this if your Claude/Codex/Gemini runs natively on Windows.

git clone https://github.com/bfly123/claude_code_bridge.git
cd claude_code_bridge
powershell -ExecutionPolicy Bypass -File .\install.ps1 install

Run

ccb up codex            # Start Codex
ccb up gemini           # Start Gemini
ccb up opencode         # Start OpenCode
ccb up codex gemini     # Start both
ccb up codex gemini opencode  # Start all three
ccb-layout              # Start 2x2 layout (Codex+Gemini+OpenCode)

Flags

Flag Description Example
-r Resume previous session context ccb up codex -r
-a Auto-mode, skip permission prompts ccb up codex -a
-h Show help information ccb -h
-v Show version and check for updates ccb -v

Update

ccb update              # Update ccb to the latest version

πŸͺŸ Windows Installation Guide (WSL vs Native)

Key Point: ccb/cask-w/cping must run in the same environment as codex/gemini. The most common issue is environment mismatch causing cping to fail.

1) Prerequisites: Install Native WezTerm

  • Install Windows native WezTerm (.exe from official site or via winget), not the Linux version inside WSL.
  • Reason: ccb in WezTerm mode relies on wezterm cli to manage panes.

2) How to Identify Your Environment

Determine based on how you installed/run Claude Code/Codex:

  • WSL Environment

    • You installed/run via WSL terminal (Ubuntu/Debian) using bash (e.g., curl ... | bash, apt, pip, npm)
    • Paths look like: /home/<user>/... and you may see /mnt/c/...
    • Verify: cat /proc/version | grep -i microsoft has output, or echo $WSL_DISTRO_NAME is non-empty
  • Native Windows Environment

    • You installed/run via Windows Terminal / WezTerm / PowerShell / CMD (e.g., winget, PowerShell scripts)
    • Paths look like: C:\Users\<user>\...

3) WSL Users: Configure WezTerm to Auto-Enter WSL

Edit WezTerm config (%USERPROFILE%\.wezterm.lua):

local wezterm = require 'wezterm'
return {
  default_domain = 'WSL:Ubuntu', -- Replace with your distro name
}

Check distro name with wsl -l -v in PowerShell.

4) Troubleshooting: cping Not Working

  • Most common: Environment mismatch (ccb in WSL but codex in native Windows, or vice versa)
  • Codex session not running: Run ccb up codex first
  • WezTerm CLI not found: Ensure wezterm is in PATH
  • Terminal not refreshed: Restart WezTerm after installation

🍎 macOS Installation Guide

Command Not Found After Installation

If ccb, cask, cping commands are not found after running ./install.sh install:

Cause: The install directory (~/.local/bin) is not in your PATH.

Solution:

# 1. Check if install directory exists
ls -la ~/.local/bin/

# 2. Check if PATH includes the directory
echo $PATH | tr ':' '\n' | grep local

# 3. Check shell config (macOS defaults to zsh)
cat ~/.zshrc | grep local

# 4. If not configured, add manually
echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.zshrc

# 5. Reload config
source ~/.zshrc

WezTerm Not Detecting Commands

If WezTerm cannot find ccb commands but regular Terminal can:

  • WezTerm may use a different shell config
  • Add PATH to ~/.zprofile as well:
echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.zprofile

Then restart WezTerm completely (Cmd+Q, reopen).


πŸ—£οΈ Usage

Once started, collaborate naturally. Claude will detect when to delegate tasks.

Common Scenarios:

  • Code Review: "Have Codex review the changes in main.py."
  • Second Opinion: "Ask Gemini for alternative implementation approaches."
  • Pair Programming: "Codex writes the backend logic, I'll handle the frontend."
  • Architecture: "Let Codex design the module structure first."
  • Info Exchange: "Fetch 3 rounds of Codex conversation and summarize."

🎴 Fun & Creative: AI Poker Night!

"Let Claude, Codex and Gemini play Dou Di Zhu (ζ–—εœ°δΈ»)! You deal the cards, everyone plays open hand!"

πŸƒ Claude (Landlord) vs 🎯 Codex + πŸ’Ž Gemini (Farmers)

Note: Manual commands (like cask, cping) are usually invoked by Claude automatically. See Command Reference for details.


πŸ“ Command Reference

Codex Commands

Command Description
/cask <msg> Background mode: Submit task to Codex, free to continue other tasks (recommended)
/cask-w <msg> Foreground mode: Submit task and wait for response, faster but blocking
cpend [N] Fetch Codex conversation history, N controls rounds (default 1)
cping Test Codex connectivity

Gemini Commands

Command Description
/gask <msg> Background mode: Submit task to Gemini
/gask-w <msg> Foreground mode: Submit task and wait for response
gpend [N] Fetch Gemini conversation history
gping Test Gemini connectivity

πŸ–₯️ Editor Integration: Neovim + Multi-AI Review

Neovim integration with multi-AI code review

Combine with editors like Neovim for seamless code editing and multi-model review workflow. Edit in your favorite editor while AI assistants review and suggest improvements in real-time.


πŸ“‹ Requirements

  • Python 3.10+
  • Terminal: WezTerm (Highly Recommended) or tmux

πŸ—‘οΈ Uninstall

./install.sh uninstall

Windows fully supported (WSL + Native via WezTerm)


Join our community

πŸ“§ Email: bfly123@126.com πŸ’¬ WeChat: seemseam-com

WeChat Group

Version History

v2.3.9

  • Fix oask session tracking bug - follow new session when OpenCode creates one

v2.3.8

  • Simplify CCA detection: check for .autoflow folder in current directory
  • Plan mode enabled for CCA projects regardless of -a flag

v2.3.7

  • Per-directory lock: different working directories can run cask/gask/oask independently

v2.3.6

  • Add non-blocking lock for cask/gask/oask to prevent concurrent requests
  • Unify oask with cask/gask logic (use _wait_for_complete_reply)

v2.3.5

  • Fix plan mode conflict with auto mode (--dangerously-skip-permissions)
  • Fix oask returning stale reply when OpenCode still processing

v2.3.4

  • Auto-enable plan mode when CCA (Claude Code Autoflow) is installed

v2.3.3

  • Simplify cping.md to match oping/gping style (~65% token reduction)

v2.3.2

  • Optimize skill files: extract common patterns to docs/async-ask-pattern.md (~60% token reduction)

v2.3.1

  • Fix race condition in gask/cask: pre-check for existing messages before wait loop

About

Real-time multi-AI collaboration: Claude, Codex & Gemini with persistent context, minimal token overhead

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Python 84.4%
  • Shell 9.9%
  • PowerShell 5.7%