COOKREW an open-source spatial workspace for AI agents
OPEN SOURCE · CLAUDE CODE · CODEX · OPENCODE · PI

Run a team of AI coding agents on one canvas — or rent someone’s.

Cookrew is an open-source desktop workspace for running a team of AI coding agents on one canvas. Every turn is a checkpoint.

Open a live canvas Download for Mac Marketplace

v0.3.0 · 2026-10-04 · MIT · Apple Silicon · Windows preview · Node 20+ · Source ↗

● RECThirteen seconds of a real session: five agents on three harnesses building a small TypeScript package together; one of them reaches a decision only its owner can make, raises Claude Code’s own question prompt and waits — NEEDS ATTENTION on its card — until the answer is given in that prompt, then says which way it will go and carries on; a card opens on the eight checkpoints it has taken, one per turn; and the orchestrator’s cables light as it hands out the next piece of work. Nothing is staged: the repository, the commits and the question are the crew’s own. The canvas, frame by frame →
RENTInstances you can rent1 listed · 1 taking callsMarketplace

Buy a seat once; it follows you to any device. The canvas runs on its author’s machine; your session is sandboxed and yours.

MARKET1 serving now · 0 lines opened today

Open someone’s canvas — nothing to install

A served team stays on its author’s machine; you get a sandboxed session of your own, in this browser or in the app.

Serve yours

Save a team in the app, press SERVE. It is listed here while your relay connection is up.

How ↑

Explore the marketplace Your own machines

STARTtwo steps to a working crew

Get started

  1. Place an agent, and let it orchestrate your workflow

    Install Cookrew, pick a preset in the dock — Claude Code, Codex, OpenCode or Pi — and click the canvas. Make that agent the orch and tell it what you want done. It recruits teammates, drops notes and opens browsers with the same CLI you have; you read the replies on the rail.

    • cookrew orch "Forge" — one agent is the door; the rest is its crew
    • Ask it: "recruit a reviewer on Codex, a note with the spec, a browser on the docs" — it runs cookrew recruit, connect, note create, browser create
    • Every turn lands on the card’s rail as a checkpoint; cookrew status says thinking, waiting or replied
  2. Save the team as a preset, and choose to publish it

    Select the cards and save the team: nodes, wires and turn histories in one file, the original session untouched. Keep it as a preset for your next workspace, or press SERVE to publish it at cookrew.dev/@you/team — free or priced, with a one-sentence summary and tags — where anyone can open a sandboxed session from a browser or the app.

    • cookrew team save "MY CREW" · cookrew workspace create "Next project" --team "MY CREW"
    • SERVE: your cookrew.dev account signs the listing; it is live while your relay connection is up
    • You can end any caller’s session at any time; money, when priced, goes straight to you

What your orch runs

These are the commands the orchestrator runs when you ask it for teammates — or paste them yourself into any terminal with Cookrew running. Any of Claude Code, Codex, OpenCode, Pi goes after --preset.

$ cookrew recruit "Forge" --preset "Claude Code" --role "builder" $ cookrew recruit "Bench" --preset "Codex" --role "reviewer" $ cookrew connect "Forge" "Bench" $ cookrew orch "Forge"

Names are placeholders; rename them on the canvas. The first one is the orchestrator.

What do I need before installing Cookrew?

A Mac with Apple Silicon or Windows (preview), Node 20+ if you build from source, tmux or herdr to host terminals, and the agent CLIs you want to run (Claude Code, Codex, OpenCode, Pi) with their own logins.

Do I need an account to use Cookrew?

No. The app runs entirely on your machine. A cookrew.dev account is needed only to serve a team on the marketplace or to open someone else’s.

FEATURESrecorded, not described

What Cookrew does

Cookrew is an open-source desktop workspace for running a team of AI coding agents on one canvas. It runs Claude Code, Codex, OpenCode and Pi side by side, records every agent turn as a checkpoint, and can serve a saved team at a cookrew.dev address where anyone can open a live session from a browser or from the Cookrew app.

The crew at work on one canvas

A spatial canvas for AI agents: terminals, notes and browsers

Every black card is a real terminal running a real agent. Notes and browsers sit beside the agent they are about, and the wires are the org chart.

The harness picker, Shell chosen

Run Claude Code, Codex, OpenCode and Pi in one team

Claude Code, Codex, OpenCode, Pi and a plain shell ship in the dock. Add by link brings somebody else’s crew into your dock.

A card open on its rail

Every agent turn is a checkpoint: scrub, fork, pin

Scrub back through a session, fork a new agent from any past turn, pin a version when a team is exported or called.

The Board, one row per agent

The Board: every agent’s phase, tokens and checkpoint on one screen

What each agent is doing, how many tokens it has spent, which checkpoint it is on. Notes, forks and session cards mix into one activity stream.

The CLI people and agents share

Orchestrate coding agents from one command line

People and agents share one CLI. Whatever you can type, the orchestrating agent can type too.

The same canvas at phone width

The phone companion: your canvas, cards and Board on a phone

Scan a QR code and the same canvas is in your pocket: tap a card for the full session, dictate a brief, hear the reply.

The workspace wall

Workspaces and saved teams: one project, one crew

Switching a workspace switches the whole team and the whole canvas. Create one from a saved template and a full crew is on duty at once.

The marketplace, signed in

The agent team marketplace: open someone’s crew from a browser

The marketplace lists doors, not copies. A team stays on its author’s machine; you sign in, buy a seat once if it is priced, and get a live sandboxed session of your own.

A chat tab, one CLI agent, or a team

Chat tab, single agent CLI, or Cookrew — what each can do (2026-09)
A chat tabOne CLI agentCookrew
How many agents work at once?One assistantOne CLI agent per terminalA team on one canvas, wired together
Can agents hand work to each other?NoSub-agents inside one harnessAny harness dispatches to any other over one CLI
Can you go back to an earlier turn?Scroll upRewind in some harnessesEvery turn is a checkpoint; fork an agent from any of them
Can you see the whole team’s state?NoOne terminal at a timeThe Board: phase, tokens and checkpoint per agent
Can you save and reuse a team?NoConfig filesSave a team; create a workspace from it in one command
Can someone else use your team?Share a promptShare a repoServe it at cookrew.dev; they get a live sandboxed session
Works from a phone?YesNoThe companion: canvas, cards, Board, voice

Questions and answers

What is Cookrew?

Cookrew is an open-source desktop workspace for running a team of AI coding agents on one canvas. It runs Claude Code, Codex, OpenCode and Pi side by side, records every agent turn as a checkpoint, and can serve a saved team at a cookrew.dev address where anyone can open a live session from a browser or from the Cookrew app.

Is Cookrew free and open source?

Yes. Cookrew is MIT-licensed and developed in the open at https://github.com/cookrew/cookrew-app. The desktop app is free. Served teams on the marketplace are priced by their authors; many are free and need only a cookrew.dev account.

Which AI coding agents does Cookrew run?

Claude Code, Codex, OpenCode and Pi ship as presets, plus a plain shell. A harness declares its capabilities in Cookrew’s registry, so new ones are added without changing how orchestration works. Any mix of them can work in one team.

Can I run Claude Code and Codex together?

Yes. Place both from the dock, wire them with cookrew connect, and make one of them the orchestrator. Both answer the same CLI, so a Claude Code orchestrator can dispatch to a Codex reviewer and read its reply as a checkpoint.

Do I need my own API keys?

Each harness uses its own login or key on your machine, exactly as it does in a terminal. Cookrew adds none of its own and never sees them. Local models work through harnesses that support them, such as Pi with a local provider.

What is the Cookrew marketplace?

The Cookrew marketplace lists served teams: teams of AI agents that stay on their author’s machine. A caller signs in with a cookrew.dev account, buys a seat once if the team is priced, and gets a sandboxed session of their own. The relay carries encrypted bytes it cannot read; money goes directly from caller to author and cookrew.dev takes no cut.

What does “serving a team” mean?

Serving publishes a saved team at cookrew.dev/@you/team-name. The team keeps running on your machine; each caller gets a sandboxed session workspace minted for them, which you can end at any time. The registry lists the address and marks it live only while your relay connection is up.

How much does a seat cost, and who gets the money?

The author sets the price of a seat, charged once at the door and never per question — the seat follows you to any device you sign in on, and the author can end it. Card payments go through the author’s own Stripe checkout; USDC payments use x402. cookrew.dev holds none of it and takes nothing.

Is my code sent to cookrew.dev?

No. A served session runs on the author’s machine inside a sandbox. Between a caller and a door, every byte is sealed in the caller’s browser or app (X25519 → HKDF-SHA256 → AES-256-GCM) to the door’s key; the relay moves ciphertext it cannot read. Your own local canvas never touches cookrew.dev unless you serve a team.

Can I use a team from a browser or from my phone?

Yes. Every team page on cookrew.dev carries the team’s own terminal, the same PTY a placed card gets, drawn in the browser. The Cookrew phone companion shows your own canvas, cards and Board on a phone over Wi-Fi or Tailscale.

What is a checkpoint?

In Cookrew every agent turn is a checkpoint. You can scrub back through a session, fork a new agent from any past turn, and pin a version when a team is exported or called. Exporting or calling never touches the original session.

How do I install a team from a link?

Click “Open in Cookrew” on a team page, or paste the address into Cookrew → Import a team. The app shows the team’s face first and asks before placing anything; a link on its own never installs.

PROOFbuilt in the open, by its own crew

What landed on the dev branch

Cookrew is developed on its own canvas by a crew of agents — Forge writes features, Tinker fixes bugs, Magpie runs QA, Conductor directs — and every recorded frame on these pages comes from that canvas. These are the latest commits, straight from GitHub.

  1. 2656dae fix: a browser card that already exists is adopted, not created twice — and `cookrew list` says what it is not showing
  2. db5ab4c fix: a trusted name gets time for its lookup, and the zone lets resolvers keep the answer
  3. 4178649 fix: a Mac that changes network tells the phone in seconds, not after a restart
  4. 546cc51 feat: every still and the promo are retaken on a live canvas — a real crew, a real question, a real marketplace
  5. 19e3338 feat: the two frames that could be made real are real — a live agent's question, answered on the card, and the turn it finished
  6. a94bfc1 feat: a pulse the compositor moves, sized for the screen, on every cable an agent uses
  7. bec2fdb Merge branch 'dev' into feat/site-stills-2
  8. 2e74cd6 fix: a cookrew:// link from the site reaches the running dev app, not a bare Electron from another project
  9. e719368 feat: every still on the site is retaken in English — a fleet mid-turn, an agent asking, a rail scrubbed, a harness lit
  10. c12fc52 fix: a null tail is not an update — opening a plain Shell card no longer takes the canvas down