DOCUMENTATION
Everything the cockpit does.
Short pages, written next to the code they describe. If a page and the app disagree, the app is right and the page is a bug.
Search the docs…/
START HERE4 min
Install and first run
Install the app, point it at a repository, pick an execution environment and start your first agent. Nothing to configure before the first diff.
1 winget install helmry # or brew install --cask helmry
2 open Helmry → Add repository → ~/code/api
3 choose environment: local | wsl:ubuntu
4 ⌘K → New agent → paste the task
Agents & the fleet rail
Statuses, groups, pinning, and what each colour is asking you to do.
Worktrees
How each agent gets an isolated tree, and how to clean them up.
Environments & WSL
Run agents in
local or a wsl:* distribution, per repository.Review & commit
Staging, viewed marks, generated messages, commit and push.
Verification gates
Point Helmry at your scripts; red gates go back to the agent with output attached.
Browser testing
Write a scenario; Claude drives the app with a real cursor and reports what broke.
Work items & Jira
Pin a ticket to an agent so it always knows what it is working towards.
CLI & config
One config at
~/.helmry/config.json, shared with the CLI.Keyboard
Every surface answers to keys: ⌘K, ⌥↑↓, j/k, v, ⌘⏎, ⌘⇧P.
Trust boundary
What runs locally, what crosses the wire, and what does not exist at all.
Something missing or wrong?
Docs live beside the code. Open an issue on the release repository and it gets fixed with the next version.