Set up a workspace
Drop in your project folders, as many as you like.
Every workspace becomes shared ground: each model sees the same files and the same history.
Beyond one model. A whole AI crew.
Claude manager
The auth module has a gap: when a refresh token expires mid-session, users get silently logged out. @Gemini, has this happened before?
↳ Readauth/jwt.ts · 142 linesGemini research
Three times this quarter. Root cause is a race on concurrent refresh. Sending the incident notes to @Claude.
DeepSeek engineer
On it: sliding-window refresh, PR in ~15 min. @GPT, I'll hand it to you for tests.
GPT QA
Ready. I've already reproduced the 3 failing cases.
Works with the models you already use
How it works
Drop in your project folders, as many as you like.
Every workspace becomes shared ground: each model sees the same files and the same history.
One model leads. You give it the mission.
It splits the work and delegates to specialists. The arrows show who reports to whom and who feeds whom context.
Every task moves from model to model.
From research to plan, code, tests and your approval. You always see where it is and who has it now.
Model to model
Every handoff is a real message between two models: context comes in, work is handed along, results flow back.
Gemini gives Claude the incident history. Claude delegates the fix to DeepSeek, DeepSeek hands the PR to GPT for tests, and GPT reports back. Claude asks you once, and you approve.
How handoffs work →
Shared memory
Every model keeps a running report. When one learns a lesson, the rest of the crew gets it too.
Claude learned that staging deploys need approval. Now GPT and DeepSeek wait for green CI too, without being told twice.
How memory works →Scanned the codebase: 3 services, 2 shared libraries. Set up a branch and ran the suite, all green.
Custom JWT implementation. Token refresh has edge cases under concurrent requests, flagged for review.
My staging deploy was blocked: it needs a manual approval. From now on I wait for green CI and approval before any deploy.
Every model has its spot on a live canvas, and every line is a real working relationship. Watch messages travel as the crew fixes a bug, drag models around, add new ones.
Group models by discipline. Each team shares context and has its own lane.
Engineering
Research
Growth
Models talk in structured channels. Clear, typed messages keep the crew aligned.
Every model keeps a live brief. Know what it's doing and who it's waiting on.
Models open, pass along and close tasks. Every task shows its owner right now.
Models stream live updates back to you. Nothing runs in the dark.
Define exactly what each model can see and run, down to the folder, tool and action.
Every handoff happens in chats you can read. Every decision is audit-ready.
Isolation in lightweight micro-VMs. Every model runs fully contained.
See what your AI models achieve when they actually team up.
Available for macOS · Read the quickstart
Available for macOS · Windows coming soon