Install
You need a Mac (Apple silicon or Intel, macOS 12 or newer) and an AI coding
agent you are logged in to: Claude Code or
Codex.
Homebrew
brew install perpeer/tap/lazychat
Homebrew builds lazychat on your Mac, along with Lazy's menu bar app, so
macOS opens both without a warning. Then run lazychat; lazychat doctor
says what else is ready. Lazy starts with lazychat; brew services start lazychat keeps it in the menu bar from every login.
To update:
brew update && brew upgrade lazychat
lazychat comes from our own tap for now. Homebrew's own list takes it at
225 stars, and then it is just brew install lazychat. If it saves you a
few tabs, star it: every
star helps lazychat reach more people.
From the source
git clone https://github.com/perpeer/lazychat
cd lazychat
./install.sh
It checks your Mac, says what is missing, and builds
~/.local/bin/lazychat and Lazy's menu bar app. To update, run
git pull && ./install.sh in the same folder.
Updates
When a release is out, a green new box shows on the rail. Click it or
press U: with Homebrew Enter upgrades and restarts lazychat; from the
source it shows the command to run. To remove lazychat: brew uninstall lazychat, or ./uninstall.sh. Your workspaces and projects stay.
How it works
1. A workspace. Run lazychat and name one: the set of projects you
work on. ctrl+w switches between workspaces.
2. A project. Press o and pick a folder. Every tab — Chat, Git,
Terminal — lists the same projects.
3. Sessions. Press n to start Claude Code or Codex in the project,
Enter to type to it and ctrl+q to come back. A project holds as many
sessions as you like, each its own agent in its own terminal, working on
its own: start one on a feature and another on a bug, side by side, and
see which one works, which one asks you something and which one is done.
┌ [1] projects ──────────┐┌ [2] session │ [3] details ───────────┐
│ garden-shed ││ ❯ paint the shed blue │
│ ⎇ main ││ │
│ ├─ ◐ north-wall ││ ● Starting with the north wall. │
│ │ claude · 42s ││ Reading paint.go… │
│ ├─ ? blue-door ││ │
│ │ claude · 3m 18s ││ > ▌ │
│ └─ ✓ fence ││ │
│ codex · 1m 05s ││ │
└────────────────────────┘└──────────────────────────────────────┘
session: (enter) continue · (n) new · (x) close · (d) delete · (?) help
The rest you meet as you go: Git to stage, diff and commit, Terminal for
shells and SSH, the details of each prompt, Settings. ? lists every key
where you are, and the reference has every screen.
lazychat doctor tells you which agents are ready.
Sponsor Lazy
Lazy watches your agents all day and has never asked for anything.
lazychat is free and stays free; if it saves you time, keep Lazy going
(the ♥ line under the AI tools in Chat opens this page too):
Inspiration
lazychat follows lazygit and
lazydocker by Jesse
Duffield: terminal UIs where everything is one key away. lazychat does the
same for AI coding agents.
License
lazychat is source-available under the
PolyForm Shield License 1.0.0: read it, use it, change it for
yourself, also at work, for free. What it does not allow is offering a
product that competes with lazychat, paid or free — selling it, or
shipping a renamed copy. Keep NOTICE with any copy.
The name lazychat, the mascot Lazy, its drawings and its sounds are not
part of the licence: see TRADEMARKS.md.
Your workspaces, sessions and settings stay on your Mac, in ~/.lazychat;
lazychat sends none of them anywhere.
Contributing
Bug reports, ideas and pull requests are welcome: open an
issue and tell us which agent
lazychat should support next. CONTRIBUTING.md explains
how the code fits together and how it is tested.
