manzanas

# manzanas [](https://github.com/BariBariGood/manzanas/releases) [](https://www.npmjs.com/package/manzanasd-client) [](https://github.com/BariBariGood/manzanas/actions/workflows/ci.yml) [](https://allmcps.com/mcp/manzanas?verify=cc5ceeeb-24c5-4ac5-9327-f57ad5eb1165) A Mac daemon for multi-agent iOS simulator fleet orchestration: leases, actions, streaming, deterministic state, and an exportable run journal for AI agents (and humans) sharing simulators. **The 90% story: lease a simulator, run a YAML spec, get evidence.** Everything else, fleets, physical phones, mirroring, is an opt-in chapter you can ignore until you need it. https://github.com/user-attachments/assets/983b0548-df1a-41a3-812c-f0f39cfaa01c *1 orchestrator, 7 Codex agents, 7 simulators across 3 Macs, leases mean nobody trips over anybody. Real time, no edits.* `manzanasd` runs on each Mac host and owns everything stateful, the simulator registry, the lease table, the warm pool, action backends, streamers, golden images, and the run journal. Clients (`manzanas` CLI, MCP facade, SDKs) are thin and cross-platform, speaking a versioned JSON protocol over HTTP + WebSocket. **Website: [manzanas.dapsdev.dev](https://manzanas.dapsdev.dev)** (source in [`site/`](site/)). ## Five-minute quickstart No flags to read, no config to write. Four layers, start at whichever matches your machine: ### 0. One-liner (macOS/Linux): npx ```sh npx manzanasd-client@latest doctor # downloads the release binary and runs the setup diagnosis ``` The npm wrapper fetches the right `manzanasd`/`manzanas` binary for your platform on install, then proxies every command to it. Use it as the CLI, or point your agent's MCP config at `manzanas mcp`. ### 1. Anywhere (no Mac): mock mode ```sh make build # writes bin/manzanasd, bin/manzanas, bin/manzanas-broker ./bin/manzanasd --mock # full daemon + fake fleet + mock action backend ``` In another terminal, run the whole lease → boot → act → evidence loop as one declarative YAML run: ```yaml # hello.yaml, drives the mock login screen (docs/mock.md) name: hello target: labels: [ios26] steps: - action: type_into_element with: {id: username, text: agent} - action: type_into_element with: {id: password, text: pw} - action: tap_element with: {label: "Sign In"} - action: wait_for_element with: {label: "Welcome, agent!", timeout_ms: 5000} ``` ```sh ./bin/manzanas run hello.yaml -o evidence.md cat evidence.md # PR-ready markdown evidence of every step ``` That's the product: one spec, one command, a journaled evidence trail. The same spec runs unchanged against real simulators, and against physical phones, because every target speaks the same actions API. ### 2. On a Mac with Xcode: real simulators ```sh brew tap baribarigood/tap https://github.com/BariBariGood/homebrew-tap brew trust baribarigood/tap # Homebrew >= 6 requires trusting third-party taps brew install manzanasd # daemon (+ pulls in the manzanas CLI) brew services start manzanasd # launchd service on port 7433 manzanas doctor # one-shot setup diagnosis; every failure names its fix ``` `manzanasd` needs **zero flags** for a working single-Mac daemon: sensible defaults for the journal, template library, and element map, simulators enumerated from `simctl`, physical devices and the mirror off until you opt in. The same `manzanas run spec.yaml` now drives real simulators. Step-by-step walkthrough (lease, tap, screenshot, release by hand): [docs/quickstart.md](docs/quickstart.md). ```sh manzanas targets # list simulators manzanas lease acquire --labels ios26 --agent me --wait # claim one manzanas tap 200 400 --lease lse_... # drive it manzanas mcp # or hand the tools to an agent ``` ### 3. Optional chapters (you probably don't need these yet) - **Physical iPhones** (WebDriverAgent): [docs/devices.md](docs/devices.md) - **XCTest-hostile apps** via iPhone Mirroring: [docs/mirror-onboarding.md](docs/mirror-onboarding.md) - **Multiple Macs behind one endpoint**: [docs/broker.md](docs/broker.md) ## Why Agents driving simulators over raw SSH + CLI tools trip over each other and pay huge fixed costs. manzanasd removes both, with measured numbers (M3 Pro, macOS 26.5, Xcode 26.5; reproduce with `make bench`): - **Leases, not locks**: TTL-bounded exclusive claims with FIFO queues, no two agents ever drive the same sim. - **Park/thaw warm pool**: idle sims are SIGSTOPped (a parked tree is unschedulable, ~0 idle host CPU no matter what the sim's daemons are doing) and thawed on lease grant: **~0.28 s lease-to-live vs ~7 s for a cold boot** (~29 s first boot). The thaw itself is a cached-PID SIGCONT and takes under a millisecond. - **Warm actions**: a resident per-sim helper makes an end-to-end tap **~36 ms vs ~950 ms** cold (per-action AXe spawn), ~3 s cold on Intel. - **Deterministic state**: snapshots, fixtures, per-lease auto-reset, and golden images that stamp out slimmed sims in seconds (**~0.75 GB vs ~5 GB stock**, via [simslim](https://github.com/MobAI-App/simslim)), how one Mac runs a dozen sims. - **Evidence**: every mutating op under a lease is journaled, with content-addressed artifacts and a PR-ready markdown export. | | | |---|---| | Leases | TTL-bounded exclusive claims, labels, FIFO queues, auto-reset, pause/resume for human handoff | | Warm pool | park/thaw (SIGSTOP) pool sims: ~0.28 s lease-to-live, ~0 idle CPU | | Actions | cold (AXe) + warm (resident helper) taps/swipes/typing, composite `tap_element` with a structured predicate DSL, list-scrolling composites (`scroll_until`/`scroll_collect`), pixel templates (`save_template`/`tap_template`), batches | | Verification | `assert_text`/`assert_template` postconditions, opt-in pixel-verified taps, `wait_for_stable` pixel settle, run verdicts + replay drift detection | | Runs | one-call YAML runs: lease → boot → app → steps → evidence → release ([docs/runs.md](docs/runs.md)) | | Audit | deterministic UI checks (touch targets, clipping, alignment, spacing, safe area, missing labels) → findings + annotated screenshot in the journal | | Streaming | MJPEG fan-out, browser [`/view` page](docs/assets/live-view.png), WS frames | | Video | per-lease `simctl` recordings that land in the journal | | State | snapshots, fixtures, per-lease auto-reset, golden images | | Journal | append-only evidence per run, artifacts, `export.md`, replayable spec export | | Dashboard | read-only [web dashboard](docs/assets/dashboard.png) at `/dash`: fleet, leases, multiview, journal browser | | Doctor | `manzanas doctor`: one-shot host diagnosis, every failing check carries its fix | | Devices | physical iPhones via devicectl + WebDriverAgent, or iPhone Mirroring for XCTest-hostile apps | | Fleet | `manzanas-broker` federates N Macs behind one endpoint | | Clients | `manzanas` CLI, MCP tools over stdio, npm wrapper, GitHub Action | |  |  | |---|---| | the browser `/view` MJPEG live page | the built-in `/dash` fleet dashboard | ## MCP (Claude Code, Cursor, Codex) `manzanas mcp` serves the whole toolset over the Model Context Protocol (stdio), so any MCP-capable agent can lease and drive simulators, with per-session auto-release of leases and self-describing tool errors. Ready-to-paste client configs and troubleshooting: [docs/mcp.md](docs/mcp.md). ```sh claude mcp add manzanas -e MANZANASD_ADDR=mac-host:7433 -- /path/to/manzanas mcp ``` ## Architecture ``` ┌ Linux / CI / anywhere ────────────┐ ┌ each Mac host ─────────────────────────────┐ │ manzanas (thin client, Go) │ WS │ manzanasd (Go daemon) :7433 │ │ - CLI: lease/tap/observe/... │◄──────►│ registry ── warm pool (park/thaw, gates) │ │ - MCP facade (stdio) │ HTTP │ leases (TTL, labels, FIFO, auto-reset) │ │ - eval harness (manzanas-eval) │ │ actions ── cold AXe / warm simbridge │ ├───────────────────────────────────┤ │ streams (MJPEG fan-out, browser view) │ │ manzanas-broker :7440 │ │ state (snapshots, fixtures, golden images)│ │ fleet-wide placement: leases are │───────►│ journal (evidence, artifacts, export.md) │ │ scheduled across N daemons, then │ probe/ └────────────────────────────────────────────┘ │ clients talk to the owning │ lease × one daemon per Mac in the fleet │ daemon directly (host_addr) │ └───────────────────────────────────┘ ``` One orchestration core, transports as thin backends: the same YAML spec, leases, journal, and evidence pipeline run against simulators (AXe/simctl), physical iPhones (WebDriverAgent), and XCTest-hostile apps (iPhone Mirroring). What manzanas is *not*, a generic OCR automation framework, an app-botting tool, is written down in [docs/non-goals.md](docs/non-goals.md), along with why the repo stays one repo. ## Documentation **Start here** (the 90% path): - [docs/quickstart.md](docs/quickstart.md), zero to a passing run on one Mac: install → doctor → lease → tap → screenshot → YAML run. - [docs/runs.md](docs/runs.md), the one-call YAML run: schema, verdicts, drift detection, record → replay. - [docs/mock.md](docs/mock.md), the full daemon anywhere (Linux/CI), no Mac needed. - [docs/journal.md](docs/journal.md), the evidence trail: run journal format, artifacts, markdown export, replayable spec export. - [docs/mcp.md](docs/mcp.md), handing the tools to an agent (Claude Code, Cursor, Codex). - [docs/troubleshooting.md](docs/troubleshooting.md), `manzanas doctor` first, then symptoms → causes → fixes. **Going deeper** (read when you hit the subsystem): - [proto/PROTOCOL.md](proto/PROTOCOL.md), the v0 wire protocol: targets, leases, actions, streams, state, journal, runs, WS surface. The tables in §5 are the authoritative list of action kinds and payloads. - [docs/architecture.md](docs/architecture.md), components, interface contracts, and the product boundary. - [docs/agent-qa.md](docs/agent-qa.md), a worked end-to-end agent QA session, plus driving animated (React Native) apps. - [docs/resolver-ladder.md](docs/resolver-ladder.md), how element resolution works: map/ax/ocr/template rungs, provenance, escalation. - [docs/elementmap.md](docs/elementmap.md), the learned element map (fast-path resolution across runs). - [docs/templates.md](docs/templates.md), the pixel-template library (`save_template` / `tap_template` / `assert_template`). - [docs/warm-pool.md](docs/warm-pool.md), park/thaw warm pool, footprint watchdog, host safety gates. - [docs/actions-warm.md](docs/actions-warm.md), warm vs cold action paths; the resident `simbridge` helper. - [docs/state.md](docs/state.md), snapshots, fixtures, per-lease auto-reset, quarantine. - [docs/images.md](docs/images.md), golden images: slim once, stamp N sims in seconds. - [docs/streaming.md](docs/streaming.md), MJPEG streaming and the browser view page. - [docs/dashboard.md](docs/dashboard.md), the built-in read-only web dashboard at `/dash`. - [docs/recording.md](docs/recording.md), per-lease video capture into the journal. - [docs/eval.md](docs/eval.md), the scenario-driven determinism benchmark harness. - [clients/README.md](clients/README.md), `manzanas` CLI + MCP quickstarts; [clients/npm/](clients/npm/README.md); GitHub Action in [action/](action/README.md). **You probably don't need these yet** (opt-in surfaces; each page opens with who it's for): - [docs/non-goals.md](docs/non-goals.md), the product boundary: what manzanas is, what it deliberately is not, and the one future split candidate. - [docs/devices.md](docs/devices.md), physical iPhones as leasable targets (devicectl + WebDriverAgent), and the mirror backend reference. - [docs/mirror-onboarding.md](docs/mirror-onboarding.md), the guided setup path for driving XCTest-hostile apps through iPhone Mirroring. - [docs/broker.md](docs/broker.md), multi-Mac federation. - [docs/fleet.md](docs/fleet.md), running a multi-Mac fleet (topology, Tailscale, day-2 ops). - [docs/install.md](docs/install.md), launchd install, releases, Homebrew formula. The physical fleet this runs on (machines, locks, build caching) is site-specific; [docs/fleet.md](docs/fleet.md) covers the daemon's part. ## Status Everything above is implemented and running on the fleet, leases + queues (incl. pause/resume), warm pool with safety gates, cold (AXe) + warm (simbridge) action backends, composite/batch/assert actions, the resolver ladder with element map and pixel templates, one-call YAML runs with verdicts and drift detection, MJPEG streaming, video capture, snapshots/fixtures/auto-reset, golden images, journal, dashboard, doctor, physical-device support (WDA + mirror), broker, eval harness, CLI + MCP. Verify with `go build ./... && go vet ./... && go test ./...` (Linux-safe; simctl paths are mocked). ## License Apache-2.0, see [LICENSE](LICENSE). Releases up to and including v0.6.0 (and their existing tags) were published under MIT and remain MIT; later releases are Apache-2.0.