#204 · Primary category: AI Coding Assistants
codeg
Collaborative multi-agent AI coding workspace: aggregate sessions from Claude Code, Codex, OpenCode, Pi, Grok Build, etc. Desktop app, self-hosted server, or Docker.
Project last updated:08/29/26
GitHub Stars
3.1K
Forks
395
Contributors
28
License
Apache-2.0
Why we included this project
Anyone who runs more than one AI coding CLI knows the pain of digging through terminal histories to find what a previous session did. Codeg collects sessions from a dozen agents, including Claude Code and Codex, into one searchable workspace, so past work stays findable. Its most useful trick is delegation: type @, pick another agent, and Codeg starts it as its own session and streams the result back into your current thread, so Claude Code can draft while Codex reviews without you copy-pasting between terminals. It runs as a desktop app, a self-hosted server, or a Docker container, with mobile clients for checking in away from the desk. If your team standardizes on a single agent, this is less useful; if you run two or more, the unified view, live diffs, and shared git client are worth the setup.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.