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 3,567 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!
30 days in the Featured rail · terms & refunds
⚠️ 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.Keep V3 workflow policies out of ordinary V2 projects, preserve Pi request attribution after image-input transformation, and scope cancellation to the active request. Notes.
Reuse verified plugin snapshots, share resolved dependencies, recover interrupted builds and honor startup timeout overrides. Verified with real Pi plugin loading and two-agent cold/warm startup. Notes.
Fix accepted jobs waiting behind native Codex fullscreen status/shortcut rows and ordinary replies mentioning esc to interrupt, while preserving human drafts, busy/menu guards and FIFO. Notes.
Recognize native Claude pasted envelopes and empty Codex composers with newer status bars; preserve draft protection. Notes.
Opening /model or another control-only selector no longer supersedes an
active OMP/Pi ask. CCB now waits for a real provider turn boundary before
classifying different user input as replacement work. See the
verification and upgrade guidance.
Claude and Codex preserve usable local history across account/key/gateway changes. Pi follows manual session switches; OMP accepts its newer history header format. See verified scope and upgrade guidance.
Codex composer detection no longer matches model names. Claude suggestion, accepted-draft and ordered return-delivery regressions accompany real continuous communication verification. Experimental Claude native plugins remain disabled. Install/update onboarding no longer recommends the six V3 preview roles; explicit installation and updates for installed roles remain available. See upgrade guidance and layout limitations.
Fix Codex recovery commands with duplicate resume arguments, abandoned OMP editor sockets, and padded Codex empty-input detection. Queue details now show input-guard waiting reasons. See upgrade guidance and remaining limitations.
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