Everything people ask before trusting an agent with their repo.

No. AgentCrew is the layer above them. It plans the work, dispatches each task to the runtime you choose (Claude Code, Codex, Cursor, Gemini CLI or Droid), isolates every task in its own Git worktree, and gates completion on verified evidence. Your existing subscriptions and logins are used as-is.

Not through AgentCrew. The engine, the SQLite state and every worktree live on your Mac. The only network traffic is what your chosen agent runtime already makes to its own provider. AgentCrew has no cloud backend that sees your repository.

A mission cannot be marked complete until every requirement in its PRD has fresh verifier evidence tied to the exact commit and PRD revision. If the PRD changes or new commits land, the evidence goes stale and the gate closes again. The agent saying "done" is never enough.

Yes. AgentCrew is a paid subscription on top of the Claude, OpenAI or other subscriptions you already pay for. We publish the exact figure at launch, and waitlist members get that launch price locked for their first year. AgentCrew never resells tokens, so there is no markup on model usage.

First access when the macOS build ships, in the order people signed up. The first 100 people on the list also pay half for their first twelve months. You can tell us which runtimes and stack you use and we will prioritise them. We send one email when it is ready, and no drip sequence.

macOS first, with a native app, a terminal dashboard and a scriptable CLI that all drive the same local engine. Linux and Windows support for the engine and CLI are on the roadmap after the macOS release.

Every task is checkpointed in its worktree. On the next engine start, AgentCrew checks whether the recorded provider processes are still alive, checkpoints interrupted work, re-queues those tasks in the same worktree and resumes the run with a continuation note. No manual recovery is required in the common case.

No, and it is not a setting. Delivery prepares a draft pull request with a per-requirement evidence table. Merging is your decision, made in your Git host, every time.

Yes. Every task whose dependencies are done runs concurrently, each in its own worktree with its own provider session. Concurrency is limited by session capacity and your provider quota, which AgentCrew tracks.

Anytime, from your Lemon Squeezy customer portal. Your local data stays on your machine and remains readable; nothing is locked behind the subscription.

AgentCrew is built by Seven Hills Software, a product studio in Madurai, India that ships software for global markets. It is the studio's own daily tool for running coding agents across its products.