Use agents without sending your repo to a vendor
Coordination stays on your machine, and you choose which model — including fully local ones — sees any code.
Plenty of teams cannot paste their codebase into a hosted product, which rules out most agent tooling before the evaluation starts.
An agent workflow your security review can actually approve, because the default is local.
The team to build first
Copy this composition, then add builders only once cards start waiting in assigned instead of review.
- LeadRuns on a local model, never leaves the machine
- BuilderPoints at a local runtime or an approved provider
- ReviewerReviews locally so diffs are never uploaded
Bump deps to latest minor
Add rate limit to /api/sync
Extract auth into a module
Write tests for parser
Fix null deref in session
Migrate config loader
How the run goes
- 01
Keep state local
Tasks, boards, messages and history are stored on your machine, not in a vendor account.
- 02
Choose the model
Point agents at a local runtime for sensitive repos, or at an approved provider per team.
- 03
No account required
The app starts with a free model and no signup, so nothing is tied to an identity.
- 04
Audit what happened
Every tool call, message and diff is logged locally and readable after the fact.
- 01
Agent teams
Build a team with real roles. Agents work in parallel, talk to each other, and hand off across teams.
- 07
Cross-team communication
Agents message each other directly, inside a team or across teams, and you can read all of it.
- 03
Code review
A diff per task with accept, reject and comment — plus a built-in editor with Git support.
- 04
Token analytics and budgets
See exactly where tokens go by team, agent, task and model. Set caps and get warned at 80%.
- AnswerIs my code private?Coordination state, task history and app data stay on your machine. Code only leaves your machine if you point an agent at a hosted model — and you choose that per team, so you can keep sensitive repos on a local runtime.
- AnswerCan I use one agent instead of a team?Yes. Solo mode gives you a single agent that writes and works its own task list on the same board. When the work outgrows it, add roles and that agent becomes the team lead without losing any history.
- AnswerWhat is AgentTeams?A desktop app for running teams of AI coding agents. It brings its own local coordination layer, so agents can hold roles, claim tasks, message each other and review each other's diffs. You supervise all of it from one kanban board instead of several terminal windows.
Run this workflow tonight.
Install, copy the team above, and give it the objective. Free, no account.