Claude Codex Bridge (CCB) 🤖 Agent Freemium
Multi-agent terminal UI that coordinates Claude, Codex, Gemini and other CLI agents in one workspace
- GitHub stars
- 3.5k
- Stars this week
- +18
- Forks
- 347
- Licence
- –
- Last push
- 2026-09-30
- Maintainer
- SeemSeam
npm install -g @seemseam/ccb@latestThird-party subagents & agents run with your permissions. Read the source before installing, and prefer pinned versions.
Works with
About Claude Codex Bridge (CCB)
What it does
Claude Codex Bridge (CCB) is a multi-agent terminal UI that runs several coding-agent CLIs — Claude, Codex, Gemini, Cursor, GitHub Copilot, Kimi, Qwen and others — side by side in one workspace, and lets them hand work to each other in defined graphs through an in-terminal /ask command. Each provider keeps its own real, native CLI pane rather than being reimplemented, and a background daemon keeps project state alive when the UI is closed.
What is inside
A visual or TOML-based window/pane-splitting config, a shared project-memory file (.ccb/ccb_memory.md) for cross-agent context, an "Agent Roles Spec" system for packaging specialist agents as installable role packs, an Android app for remote voice/text/terminal control, and built-in control skills (ask, ccb-clear, ccb-compact, ccb-diagnose) for managed agents.
Works with
Codex, Claude, Gemini, Kimi, Qwen, Cursor, GitHub Copilot, Pi, OpenCode, Grok CLI and other CLI agent families (16 provider families as documented).
How to install or connect
npm install -g @seemseam/ccb@latest
Source and release-package fallbacks are documented for Linux/macOS/Windows-beta.
Maintenance and safety
Very actively developed with detailed versioned release notes and commits within days of review. It is unusually explicit about its safety model: the mobile/config gateway binds to loopback by default, LAN exposure requires an explicit private-interface flag (wildcard/public binds are rejected), tokens are read from environment variables or restrictive-permission files rather than stored in config, Windows binaries ship with published checksums, and command execution through the tool window requires explicit approval.
Who should use it
Developers already running multiple CLI coding agents who want one visible workspace to coordinate and hand off work between them, and who are comfortable with AGPL's copyleft terms and a fairly large, fast-changing surface area.
Pros
- Unusually transparent safety model for a cross-CLI bridge: loopback-only network defaults, explicit private-interface opt-in for LAN, restrictive token-file per
- Very actively developed with detailed, versioned release notes and commits within days of review, orchestrating a genuinely large set of real CLI agents (Claude
Cons
- AGPL-3.0: free to use, but any modified/hosted derivative must also be open-sourced, and closed-source commercial use needs a separate paid license from the mai
- Large, fast-moving surface area (desktop app + Android mobile gateway + many provider integrations + Windows beta) that makes it harder to fully audit any singl
Similar subagents & agents
All agent workflows & frameworks →Spec Kit 🤖 AgentFree
GitHub's toolkit for spec-driven development with AI coding agents
Task Master 🤖 AgentFree
AI task management that turns a PRD into tasks your coding agent works through
Fast Agent 🤖 AgentOpen source
Python framework for building, orchestrating and evaluating MCP-native AI agents
OpenSpec 🤖 AgentFree
Lightweight spec-driven development: agree on changes before the agent codes
CC Safety Net 🤖 AgentOpen source
Pre-execution guard that blocks destructive commands and secret access for coding agents
BMAD Method 🤖 AgentFree
Agile AI-driven development with analyst, PM, architect, developer and UX agents