Pre-release · macOS first

Run coding agents like an engineering team.

AgentCrew is the command center above Claude Code and Codex. Describe the outcome, approve the plan, and get back a draft pull request where every requirement carries its own evidence.

Runs on your MacA worktree per taskEvidence-gated done5 agent runtimesCrash-safe resume
No cloud in the loop.The engine, state and worktrees live on your machine. We never see your repository.
Nothing is "done" on an agent's word.Completion is refused until every requirement has fresh verifier evidence tied to the exact commit.
Built by a studio that runs on it.Seven Hills ships nine products with AgentCrew driving its own coding agents every day.

Plan

A specification before a prompt.

Import the work, keep the source

Paste a brief, drop in a Markdown spec or pull Linear issues. AgentCrew keeps the source IDs, URLs and versions so every requirement is traceable back to who asked for it.

Requirements with stable IDs

Each requirement gets an ID and acceptance criteria. Saves create immutable revisions, so a change mid-mission is a new revision, never a silent overwrite.

A task graph that must validate

Plans cover every requirement, declare dependencies and cannot contain cycles. Invalid or stale plans are rejected before anything runs.

PRD.md · revision 37 requirements
  • REQ-invite-01Owners can generate an invite link
  • REQ-invite-02Links expire after 7 days
  • REQ-invite-03Revoking a link invalidates it immediately
  • REQ-invite-04Accepting joins the correct workspace
  • OPENShould invites be limited per plan tier?
SourceLIN-482 · brief.md

Run

Parallel agents, without the collisions.

A Git worktree for every task

Every task runs in its own worktree with its own provider session. Agents cannot trample each other, and you can inspect any task mid-flight.

An integration branch that grows as tasks land

Finished tasks are committed and merged into the run branch so dependents start from real work. Conflicts are never auto-resolved; the task blocks until you decide.

Any runtime, per task

Assign Claude Code to the model layer and Codex to the API in the same plan. Roles stay stable while the runtime behind them changes.

invite-model · Claude Codeinvite-ui · Claude Codeinvite-api · Codexagentcrew/run-7f3a

Prove

“Done” means verified, not claimed.

Evidence per requirement

A verifier role exercises the behaviour and records test output, logs or reproductions against the requirement ID and the exact commit.

Stale evidence closes the gate

Change the PRD or push new commits and the evidence goes stale. Completion is refused until it is fresh again. No exceptions, no override flag.

A draft PR with the receipts

Delivery prepares a draft pull request whose body carries a per-requirement evidence table. Reviewers see what was proven, not what was promised.

Review package · run 7f3a7 / 7 fresh
RequirementEvidenceCommit
REQ-invite-0112 tests passa41c9e
REQ-invite-02expiry fixturea41c9e
REQ-invite-03revoke reprob02d17
REQ-invite-04e2e join flowb02d17
Completion gate open · Draft PR #412 prepared
Stale after PRD editgate closed

Recover

Crash, sleep, quota, resume.

Automatic recovery on restart

If the engine dies mid-task, the next start checkpoints each interrupted worktree, re-queues the task in place and resumes with a continuation note. No operator ritual.

Steer a running task

Redirect a task in flight with one instruction. The provider is interrupted cleanly, the worktree checkpointed, and the task continues with your note at the top of its prompt.

Quota-aware scheduling

AgentCrew tracks session capacity and provider quota so a burst of parallel tasks never turns into a wall of rate-limit errors at 2 a.m.

  1. 02:14:07Task invite-ui running · Claude Code
  2. 02:16:31Engine process lost (laptop slept)
  3. 07:48:02Engine start · 1 run recovery_required
  4. 07:48:03Provider pid 48122 not alive · checkpointed worktree
  5. 07:48:04Task re-queued in same worktree · continuation note added
  6. 07:48:09Run resumed · 2 tasks remaining
Operator actionnone required

Runtimes

Bring the agents you already pay for.

AgentCrew drives unmodified CLIs through your existing subscriptions. No token resale, no proxy keys, no new bill for model usage.

Claude CodeOpenAI CodexCursor CLIGemini CLIDroidMCP serversSkillsHooksLinear importGitHub draft PRsSQLite stateGit worktreesClaude CodeOpenAI CodexCursor CLIGemini CLIDroidMCP serversSkillsHooksLinear importGitHub draft PRsSQLite stateGit worktrees
0command from intent to draft PR, pausing only for your two approvals
0agent runtimes behind one stable set of crew roles
0tasks per plan, each in its own isolated worktree
0bytes of your code on our servers. There are no servers in the loop.

Figures come from the product's documented limits and architecture, not from projections. Pre-release; runtime coverage outside Claude Code and Codex is marked experimental.

Pricing

Launch pricing, locked for the waitlist.

$29 a month or $299 a year. Every feature, every runtime, unlimited projects. Your model subscriptions are your own.

Monthly

$29/ month

Billed monthly. Cancel anytime.

Join the waitlist

Everything, in both plans

  • Native macOS app, terminal dashboard and CLI
  • Unlimited projects and missions
  • Claude Code, Codex, Cursor, Gemini CLI and Droid runtimes
  • Parallel tasks in isolated Git worktrees
  • Evidence-gated completion and draft PR delivery
  • Crash recovery and steerable tasks
  • MCP servers, skills and hooks per role
  • All updates during your subscription

Waitlist members get first access and the launch price for their first year. Model usage is billed by your provider, never marked up by us.

FAQ

Questions people ask before they trust an agent with their repo.

Does AgentCrew replace Claude Code or Codex?

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.

Does my code leave my machine?

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.

What does "evidence-gated" actually mean?

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.

Which platforms are supported?

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.

Will it auto-merge to main?

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.

Waitlist open

Be first when the crew ships.

Join the waitlist and we will send one email when AgentCrew is ready for your Mac. No drip sequence, no noise.

No spam. One email when it ships, and you can unsubscribe with one click.