agent-manager
The fastest workflow for developing with AI
95 followers
The fastest workflow for developing with AI
95 followers
Run Claude Code, Codex, OpenCode, Gemini CLI, Grok and Pi in one tmux list with live status per session. space answers a blocked agent without attaching, f forks the conversation into a named sibling, T pins a plain shell next to the agents, and ctrl+r opens whole-file diffs where line comments go back as one review prompt. Sessions can spawn into their own git worktrees. Ordinary tmux sessions survive quitting the manager. One Go binary, Apache-2.0. macOS, Linux, Windows via WSL2.
Products used by agent-manager
Explore the tech stack and tools that power agent-manager. See what products agent-manager uses for development, design, marketing, analytics, and more.
Design & Creative 1
Design & Creative 1
Engineering & Development 7
Engineering & Development 7
CodeRabbitTransforming code reviews with AI
4.9 (15 reviews)
Every PR to the repo goes through a CodeRabbit round before I read it. Most contributions are written by coding agents, so a reviewer that never tires of nitpicks catches a lot before the human pass.
GitHub ActionsAutomate your workflow from idea to production
5.0 (29 reviews)
Every push and pull request runs the Go test suite and a gitleaks secret scan before a human looks at it. With most contributions written by agents, a gate that runs first keeps review about design.
opencodeYour terminal's AI agent, with any model you want
5.0 (47 reviews)
One of the agents the manager runs. Its config merge is how the manager registers itself as an MCP server inside a session, so an agent can rename itself and declare the repo it is working in.
Codex 3.0 by OpenAICodex can now build, test & debug on autopilot
5.0 (96 reviews)
The other agent I keep running next to Claude Code, which is the reason the manager is tool-agnostic: status comes from reading the pane, so a new CLI is a few regex lines in a toml file.
LLMs 1
LLMs 1
