# Codex
7 tools tagged
showing 7 of 7 tools
AI agent dev environment with parallel git worktrees, magic git commands, and Linear integration.
Jean is an open-source desktop dev environment for AI agents from coolLabs (the team behind Coolify). It runs multiple coding agents — Claude Code, Codex, and others — in parallel inside isolated git worktrees, each with its own chat session and terminal. Magic git commands handle commits, PR descriptions, code reviews, and merge conflicts with AI assistance, while built-in Linear and GitHub integrations load issue context into every session.
Open-source managed agent platform: run durable agents on any model and machine through one API
Omnara is an open-source (Apache-2.0) managed agent platform, positioned as a self-hostable alternative to Claude Managed Agents and the OpenAI Agents API. You launch durable agents through a REST API, TypeScript SDK or CLI; Omnara runs the agent loop, stores state in a durable event log, and handles sandboxes or your own machines, secrets, tool approvals, RBAC and audit history. Use any compatible model endpoint, host it on Omnara Cloud or self-host with Docker Compose.
Session reports for Claude Code and Codex runs
Spotlight by Backplanes turns completed Claude Code and Codex sessions into concise reports for engineering, security, and spend review. The CLI installs on macOS, Linux, or WSL 2, watches sessions after they finish, redacts PII and credentials locally before upload, then summarizes files touched, commands run, external domains reached, scope drift, risky actions, and next-session improvements.
Cross-agent messaging for CLI coding agents
agmsg is an MIT-licensed Bash and SQLite messaging layer for CLI coding agents. It lets Claude Code, Codex, Gemini CLI, GitHub Copilot CLI, Antigravity, OpenCode, Hermes, and other terminal agents exchange messages through a shared local database instead of relying on a human copy-paste relay. It is intentionally not MCP, not a broker, and not a subagent framework.
One local gateway that lets any coding agent use any model or subscription
Open-source (MIT) menu bar app and local gateway by yetone that lets you pick any model for any coding agent: Claude Code on Kimi, Codex on DeepSeek, Gemini CLI on GLM or OpenCode on a ChatGPT plan. It translates between OpenAI, Anthropic and Gemini APIs, reuses API keys, local models and signed-in subscriptions, and fails over between accounts when a quota runs out. Free; anonymous daily usage stats are on by default.
OpenAI's official GitHub Action that runs Codex in CI
OpenAI's official GitHub Action for running Codex CLI in GitHub Actions workflows with filesystem/network permission profiles and runner-level privilege controls. This is the CI/CD Action, not the terminal Codex agent; current Codex exec enables analytics by default, so telemetry policy needs review.
Shared, git-backed long-term memory and handoffs for AI coding agents
Open-source (MIT) long-term memory server for AI coding agents by Fabio Akita. Lifecycle hooks capture sessions from Claude Code, Codex, Cursor, Gemini CLI, OpenCode and many other coding agents into a git-backed markdown wiki, so you can quit one agent mid-task and continue in another with a typed handoff. One self-hosted Rust binary; default features need no LLM API key and it has no telemetry.