Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.
This week focused on stabilizing session and daemon ownership through a major refactor that centralizes lifetime management and ensures resources bind correctly to their owners across open, replay, and shutdown cycles. On the feature side, macOS gained a native app backend option alongside XCTest,…
Get this in your inbox every Monday →A deterministic 0–100 hygiene score — README, license, CI, tests, docs, and freshness.
Who ships this repo — author concentration and the bus factor across the last 300 mainline commits.
How welcoming this repo is to contributors — issue throughput, close time, responsiveness, and good-first-issue count.
What this project is built on — dependency count by ecosystem, the license mix, and anything worth a legal look before you adopt it.
Whether this project's CI can be trusted — pass rate, run times, flaky runs, and which workflow is the weak link.
Grounded in agent-device's README, structure, and recent commits — answers won't invent code they haven't seen.
A Monday email with what shipped, in plain English — no account needed.
Showing raw commit titles for the newest commits. Sign in to generate AI summaries.
fix(android): rebind the test IME when its commit went to a stale input session (#3061)
fix(snapshot): stop a SwiftUI toolbar host from covering the sheet it encloses (#3162)
ci(ios): prepare the runner before the fixture E2E so open does not pay its start (#3251)
fix(apple-runner): fence prep spawns behind a start-owned admission (#3239)
test(apple): own the simctl settings plan tests in simctl-settings.test.ts (#3244)
A floor, not a guess: counts only commits whose author, co-author trailer, or message explicitly credits an AI tool (Claude, Copilot, Cursor, aider, Codex…). Based on 30 mainline commits. Unattributed AI code isn't counted here — the full audit estimates that separately.
