claude-squad: A terminal app for managing multiple AI agents in separate workspaces.
What problem it solves
Working with several terminal agents across different tasks requires a way to organize sessions and keep their code changes isolated. Without that separation, multiple active tasks can conflict and become difficult to review and manage.
Key features
Isolated task workspaces — Each task runs in its own git workspace, allowing several agents to work concurrently without sharing the same working tree.
Source: README
Centralized session management — A terminal interface provides creation, navigation, attachment, pausing, resuming, and deletion of agent sessions from one window.
Source: README, ui
Review before applying changes — The interface can preview and diff changes, check them out, commit branches, and push them to GitHub.
Source: README
Support for multiple local agents — Claude Squad can launch Claude Code, Codex, Gemini, Aider, and other local agents, with named profiles for switching between program configurations.
Source: README, config
Quick start
Copied verbatim from the project's README.
brew install claude-squad
ln -s "$(brew --prefix)/bin/claude-squad" "$(brew --prefix)/bin/cs"csWho it may suit
Inference: This project may suit developers and terminal-focused teams that want to coordinate multiple AI-assisted development tasks concurrently.
Topics to discuss
Which additional local agents should be supported directly?
How should isolated workspaces handle shared configuration and dependencies?
Which session and diff-management workflows would be most useful to improve?
Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.
Read the original README https://github.com/smtg-ai/claude-squad#readme
ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.
Comments
…