by SeemSeam
Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents
# Add to your Claude Code skills
git clone https://github.com/SeemSeam/claude_codex_bridgeGuides for using ai agents skills like claude_codex_bridge.
Last scanned: 5/10/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-10T06:32:58.802Z",
"semgrepRan": false,
"npmAuditRan": true,
"pipAuditRan": true
}See how claude_codex_bridge compares with popular alternatives.
claude_codex_bridge is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by SeemSeam. Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents. It has 3,517 GitHub stars.
Yes. claude_codex_bridge passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/SeemSeam/claude_codex_bridge" and add it to your Claude Code skills directory (see the Installation section above).
claude_codex_bridge is primarily written in Python. It is open-source under SeemSeam on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh claude_codex_bridge against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
A lightweight multi-agent TUI with a stable cross-provider collaboration layer Coordinate Codex, Claude, Gemini, and other CLI agents in visible, controllable workflows you can take over
中文 | English | 日本語 | Français | Deutsch | العربية | Español | Português | 한국어 | Русский
Quick Start · Message Queues · Mobile App · Rich Mode · Configure Agents · User Guide · Developer Guide
A -> B -> C, A,B -> C, and A -> B,C.Click a file or press Enter to open it with the system default application;
folders stay inside the file browser. Both safe and rich profiles use the same
behavior. macOS uses open; Linux prefers gio open, then xdg-open when GIO
is absent; WSL uses wslview from wslu to open with the Windows default app.
WSL requires enabled Windows interop and reports a missing bridge explicitly.
After upgrading CCB, run ccb update rich and reopen the file-browser pane.
See the 8.7.1 notes for validation and limitations.
Incoming agent messages wait while you compose a draft, avoiding interruption or accidental submission of your text together with a returned result. CCB first waits for the target agent's current turn to end, then checks the input box for the message at the front of the queue.
Requests (ask) and returned results (back) share one chronological FIFO
queue per target agent. Each message waits until the target finishes processing
the previous one, including returned results. Later replies cannot interrupt
an earlier reply's processing turn; different agents can still work in parallel.
We recommend testing these queue modes with Claude, Codex and OMP in managed tmux panes. Input protection for other providers will follow; their existing delivery behavior is unchanged and should not be assumed to protect drafts. OMP currently requires its default Status Band input layout and the new managed extension. After upgrading, restart the project when idle to load the new daemon and provider extensions.
This is a first version for testing. Codex/Claude deadline clearing uses Ctrl-C;
a simultaneous user action can still cause interruption. The final screen-check,
paste and Enter sequence is not atomic against typing at that exact instant.
See the 8.7.0 notes for tested
scope, upgrade guidance and the Codex remote-session recovery limitation.
Install or update an npm-managed CCB with npm:
npm install -g @seemseam/ccb@latest
For GitHub release-package or source installs, use CCB's transactional updater:
ccb update
On an npm-managed install, ccb update prints the equivalent npm command and
does not modify npm's vendored payload in place.
The Windows beta artifact is attached to the matching stable CCB GitHub
release. Download ccb-windows-x86_64.zip and its .sha256 sidecar, verify
the digest, extract the ZIP, then run:
.\install.ps1 install -Yes
ccb --print-version
It requires native Windows x64, Python 3.10+, WezTerm, Git Bash, and Herdr
0.8.0 or newer. The installer creates an install-local managed Python runtime.
The binaries are unsigned, and ccb update remains diagnostic-only for this
beta support tier; install a later Windows build by rerunning its validated
install.ps1.
CCB-managed provider panes suppress known provider-native startup update prompts.
After updating CCB—or immediately when CCB is already current—ccb update
checks installed provider CLIs and offers supported updates once. Use
--providers check, --providers all, or --providers none for explicit
report-only, non-interactive update, or skip behavior. Declining prompts again
on the next ccb update; skipping a version hides only that exact version.
CCB never restarts active provider panes during this flow, so an accepted
provider update applies when that pane next starts or is explicitly restarted.
After a release change, the newly installed CCB also retires old
project-scoped Claude/Gemini caches. Manifest-valid caches for deleted projects
are removed immediately. A stopped current project is cleaned immediately;
active or other existing projects are preserved and cleaned after their next
successful ccb kill. Unknown providers, malformed manifests, foreign
symlinks, sessions/auth, and the user-scoped Gemini cache are never removed by
this migration. Use ccb update --no-cache-cleanup to skip it for one update.
To roll back, use the same transactional updater with an older released version,
for example ccb update 8.1.3. CCB rejects a same-version artifact whose build
identity differs from the installed build, and restores the prior local prefix
if the update transaction fails. If restoration itself cannot complete, CCB
retains and reports the external recovery backup path.
If npm is not convenient in your environment, download the matching package from Releases, unpack it, and install:
tar -xzf ccb-*.tar.gz
cd ccb-*
./install.sh install
Source install is intended only for development or temporary fallback:
git clone https://github.com/SeemSeam/claude_codex_bridge.git
cd claude_codex_bridge
./install.sh install
Source install links global ccb / ask back to the checkout. Regular users should prefer the npm package.
Run this from your working directory:
ccb
If startup reports that .ccb cannot be created automatically or that the project anchor is missing, create .ccb manually:
mkdir -p .ccb
A blank project starts light: CCB opens one main window with a single agent named demo, selecting the first supported CLI available on the machine (Codex, Claude, Gemini, then other providers). It no longer mounts a multi-agent team by default.
Click