README
¶
The fastest workflow for every AI coding agent.
Claude Code, Codex, OpenCode, Grok, and Gemini CLI run side by side, each in its own tmux session, so they keep working after you quit the manager.
Instead of hunting through terminal tabs to see which agent is done and which is stuck, every session shows up in one list with live status, grouped into a project tree you can fold and reorder. You answer any of them without attaching: space sends a prompt straight into a session's pane, or spawns a new agent in the selected group. A dead session revives on its own conversation with v. And ctrl+r opens a full-file diff of what an agent changed, syntax-highlighted, where the comments you leave on lines go back to the agent's pane as one review prompt when you press C.
Not here yet: worktree creation, cost tracking, mouse-driven navigation, and agents that can talk to each other.
Jump to: Install · Usage · Keys · Diff review · Configuration
Supported tools
Status detection currently supports Claude Code, OpenCode, Codex, Grok Build, and Gemini CLI out of the box. Any other CLI tool can run as a session; add a [tools.<name>] block with status rules to get live status for it (see Configuration).
Install
Homebrew (macOS / Linux)
brew install yoanwai/tap/agent-manager
Installs tmux with it if missing. The tap ships a cask, so an install from the older formula switches over with brew uninstall agent-manager followed by the command above.
Install script (macOS / Linux)
curl -fsSL https://raw.githubusercontent.com/YoanWai/agent-manager/main/install.sh | sh
Downloads the latest release for your platform, verifies it against the published checksums, and installs it to ~/.local/bin. Set AGENT_MANAGER_INSTALL_DIR for another directory and AGENT_MANAGER_VERSION to pin a version. Install tmux with your own package manager.
Arch Linux, mise, go install, prebuilt binaries, Windows (WSL2), and updating: docs/install.md.
Usage
agent-manager
Sessions run inside tmux (am_* namespace), so they survive the manager quitting. Inside a session, Ctrl+Q detaches back to the manager and Ctrl+R opens its diff review. agent-manager --version prints the version.
Agent sessions live on a private tmux server named agentmgr, so they never mix with the tmux you run yourself and a kill-server on your own socket leaves them alone. To reach one from a plain shell, name that server: tmux -L agentmgr ls, then tmux -L agentmgr attach -t am_<id>.
The full reference, every key, the quick prompt, killing and reviving, diff review, groups, status detection, stats, and themes, lives in docs/usage.md. The short version:
| Key | Action |
|---|---|
n |
New session (name, tool, directory, optional starting prompt, group) |
space |
Quick prompt: answer the selected session, or spawn an agent in the selected group |
enter |
Focus the session in place; keys go to the agent while the list stays |
ctrl+r |
Review the session's changes as full-file diffs; c comments a line, C sends the comments to the agent |
x / v |
Kill a session to free its RAM / revive it on its own conversation |
s |
Settings (default tool, theme, list density, review layout) |
? |
Help with every binding |
Configuration (adding your own tools, status rules, revive commands) is in docs/configuration.md.
Development
go run .
env -u TMUX TMUX_TMPDIR=/tmp/amtest go test ./... # end-to-end tests drive a real tmux server
See CONTRIBUTING.md for the checks CI runs, and AGENTS.md if you point a coding agent at this repo.
Contributing
Bug reports, feature ideas, and pull requests are welcome. See CONTRIBUTING.md for setup and the checks CI runs. Questions and setups worth sharing go in Discussions. Security reports go through a private advisory; see SECURITY.md.
License
Documentation
¶
There is no documentation for this package.
Source Files
Directories
¶
| Path | Synopsis |
|---|---|
|
internal
|
|
|
agentsession
Package agentsession reads back the conversation id an agent CLI minted for a session the manager launched, for tools that do not accept a chosen id at launch (codex, opencode).
|
Package agentsession reads back the conversation id an agent CLI minted for a session the manager launched, for tools that do not accept a chosen id at launch (codex, opencode). |
|
clipboard
Package clipboard reads image data off the OS clipboard so the quick prompt can attach a pasted screenshot to an agent session.
|
Package clipboard reads image data off the OS clipboard so the quick prompt can attach a pasted screenshot to an agent session. |
|
diff
Package diff builds whole-file line models for changed files: every line of the new file with deletions interleaved, ready to render with changed lines highlighted in full context.
|
Package diff builds whole-file line models for changed files: every line of the new file with deletions interleaved, ready to render with changed lines highlighted in full context. |
|
git
Package git shells out to the git CLI to read diff data for a repo.
|
Package git shells out to the git CLI to read diff data for a repo. |
|
hooks
Package hooks wires Claude Code hook events into status files: each managed session gets AGENT_MANAGER_STATUS_FILE in its environment, and the generated settings file makes Claude Code write its lifecycle state there.
|
Package hooks wires Claude Code hook events into status files: each managed session gets AGENT_MANAGER_STATUS_FILE in its environment, and the generated settings file makes Claude Code write its lifecycle state there. |
|
mcpreg
Package mcpreg registers the agent-manager MCP server into the sessions the manager spawns, per tool.
|
Package mcpreg registers the agent-manager MCP server into the sessions the manager spawns, per tool. |
|
mcpserver
Package mcpserver exposes agent-manager's session commands as MCP tools over stdio, so any MCP-capable agent discovers and calls them natively.
|
Package mcpserver exposes agent-manager's session commands as MCP tools over stdio, so any MCP-capable agent discovers and calls them natively. |
|
sessioncmd
Package sessioncmd implements the session-scoped commands an agent uses to talk to its running manager: naming the session and declaring review targets.
|
Package sessioncmd implements the session-scoped commands an agent uses to talk to its running manager: naming the session and declaring review targets. |
|
update
Package update checks GitHub Releases for a newer agent-manager and caches the result so the TUI can show an unobtrusive "vX available" badge.
|
Package update checks GitHub Releases for a newer agent-manager and caches the result so the TUI can show an unobtrusive "vX available" badge. |
|
tools
|
|
|
badges
command
Command badges publishes the one header figure GitHub will not serve anonymously.
|
Command badges publishes the one header figure GitHub will not serve anonymously. |