warden leases iOS simulators, Android emulators, ports and app builds across every worktree on your Mac, so parallel agents build, run and test your app without stepping on each other.
$ npm i -g @delacour/warden && warden installInstalls the CLI and the skill for every agent it finds.
warden batch salient-e2e37 Salient e2e specs · 5 iPhone 17 simulators · 3m25s (13m55s on one) · 37/37 passed · shown at 5× speed
Claude Code+hook
Codex+hook
Cursor
GitHub Copilot
Gemini CLI
OpenCode
Windsurf
ZedEvery agent the skills CLI supports gets the warden skill. Claude Code and Codex also get a SessionEnd hook that releases what the session leased.
Each agent works in its own worktree. warden hands each one a simulator, a Metro port and the build for its fingerprint, and never hands the same one to two owners.
Every agent, worktree, CI job and shell on your Mac claims from one lease registry. Two agents asking at the same instant are served in turn, never both.
Leases live in one sqlite db at ~/.warden/warden.db. Every claim is a transaction, so there are no lockfiles to go stale.
A device warden didn't create or lease is read-only: never handed to an agent, shut down, erased or installed on.
When a session ends, the hook shuts down the simulators it booted and releases its leases.
Pool devices clone from a settled golden image: 3.7 s clone plus 11.9 s boot, instead of 146–239 s.
Claims queue by host RAM, CPU and priority, so ten agents don't boot ten simulators at once.
Builds are cached by native fingerprint and shared by every worktree of the repo. A native change builds once.
Once it holds a simulator, your agent runs the app, drives it, reads what went wrong and keeps what it checked as a test. Every step stays on its own device.
Run it
# worktree 1: feature/checkout$ warden dev ios --json# worktree 2: fix/login-crash, at the same time$ warden dev ios --json# each gets its own simulator and Metro port,# and the cached build for its native fingerprintDrive it
# your agent, on its own simulator$ warden claim ios --json$ warden ui open com.example.app$ warden ui snapshot -i@e1 [textbox] "Add a todo" id=todo-input value="" enabled hittable@e2 [button] "Add" id=todo-add enabled hittable$ warden ui fill @e1 "Write e2e specs"$ warden ui press @e2 --settle$ warden ui wait text="Write e2e specs"Debug it
# what broke, from the running app$ warden dev logs --kind bundle_failed,error$ warden ui exceptions$ warden ui network --status 4xx# why it is slow$ warden perf record --all --duration 15s --udid $UDID# or all of it over MCP$ claude mcp add warden -- warden mcpKeep it
import { expect, test } from "@delacour/warden-e2e"; test("add a todo", async ({ screen }) => { await screen.getByTestId("todo-input").fill("Write e2e specs"); await screen.getByTestId("todo-add").tap(); await expect(screen.getByText("Write e2e specs")).toBeVisible(); await expect(screen.getByTestId("remaining")).toHaveText("2 left");});Run the suite
Paste this into Claude Code, Codex, Cursor or any agent in your app's directory. The warden skill tells it the rest.
Install warden (npm i -g @delacour/warden && warden install) and set this Expo app up with warden init. Run the app from this worktree with warden dev, then drive it with warden ui and check the home screen renders. Save what you checked as an e2e spec under e2e/, run it with warden e2e, and release the simulator when you're done.
The jobs agents get asked to do on a mobile app, and the warden command behind each.
Five agents, five worktrees, five simulators and five Metro ports, side by side on one Mac.
The agent changes a screen, opens it on its own simulator and checks it before it says done.
Walk the steps from the issue on a clean device, then keep the repro as a failing spec.
Only the specs a diff reaches run, in CI or a pre-push hook, across leased simulators.
Short answers. The docs have the long ones.
An open-source CLI and e2e framework that gives every coding agent its own iOS simulator or Android emulator, Metro port and app build, so agents in parallel worktrees never collide. On that device the agent runs, drives and debugs the app, saves what it verified as a test, and runs suites in parallel.
npm i -g @delacour/warden && warden install. The second command wires the skill and hooks for the agents it finds, showing a diff and asking first.
No. Every claim is a transaction in one registry on the Mac, so a device or port has one owner at a time.warden ui checks the lease on every call.
Yes. warden leases Android emulators (launched -read-only), and warden ui and specs drive them. iOS needs macOS with Xcode.
Any agent the skills CLI installs into gets the warden skill: Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf, Zed and more. Claude Code and Codex also get the SessionEnd cleanup hook.
Yes. warden mcp serves a warden dev session's Metro output, console, exceptions, network, eval, logpoints and profiles over stdio. Devices, specs and suites stay on the CLI.
Build, dev-client and Metro handling target Expo and React Native. warden ui and specs drive any installed app by bundle id; elements are found by testID, label, text or role.
No. A booted device warden didn't create or lease is read-only. It is never handed to an agent unless you pass --adopt.
Nothing. warden is MIT-licensed and runs on your own Mac or CI runner. No account, no cloud.
$ npm i -g @delacour/warden && warden install