# AgentTeams > A desktop workspace where AI agent teams pick up tasks, message each other, and review each other's code — while you watch one kanban board. AgentTeams is a free, open desktop app for orchestrating teams of AI coding agents. Agents self-assign tasks, hand off work, and review each other's diffs on a live kanban board. Works with Claude Code, Codex, OpenCode, Cursor, Copilot and 75+ providers across 200+ models. AgentTeams is free and open source. It runs locally as a desktop app; source code stays on the user's machine unless an agent is pointed at a hosted model. ## Key facts - Current version: 1.4.0 (2026-08-04) - Price: $0. Ships with a free model, so the first run needs no setup. - License: MIT, source at https://github.com/agentdeck/agentdeck - Platforms: macOS, Windows, Linux (macOS Apple Silicon; macOS Intel; Windows x64; Windows ARM64; Linux x64) - 75+ providers, 200+ models, 9 first-class runtimes. ## Features - [Agent teams](https://www.agentteams.online/features/agent-teams): Build a team with real roles. Agents work in parallel, talk to each other, and hand off across teams. - [Kanban board](https://www.agentteams.online/features/kanban-board): Five columns that move on their own. Tasks change status the moment an agent picks them up. - [Code review](https://www.agentteams.online/features/code-review): A diff per task with accept, reject and comment — plus a built-in editor with Git support. - [Token analytics and budgets](https://www.agentteams.online/features/token-analytics): See exactly where tokens go by team, agent, task and model. Set caps and get warned at 80%. - [Organizations and global overview](https://www.agentteams.online/features/organizations): Nest teams into departments and squads, then watch every one of them on a single live map. - [Terminal workspace](https://www.agentteams.online/features/terminal): A real terminal in the app, with team shells, local shells, history and autocomplete. - [Cross-team communication](https://www.agentteams.online/features/cross-team-communication): Agents message each other directly, inside a team or across teams, and you can read all of it. - [Solo mode](https://www.agentteams.online/features/solo-mode): Start with one self-managing agent. Turn it into a full team the moment the work outgrows it. ## Use cases - [Clear a backlog of small tasks overnight](https://www.agentteams.online/use-cases/clear-a-backlog): Point a team at thirty low-risk tickets and wake up to thirty diffs waiting for review. - [Refactor a legacy codebase without breaking it](https://www.agentteams.online/use-cases/legacy-refactor): Split the refactor across agents, block risky work behind tests, and review every diff before it lands. - [Raise test coverage on a project nobody tested](https://www.agentteams.online/use-cases/raise-test-coverage): One agent per module, tests written in parallel, every suite run in the built-in terminal before review. - [Ship a product as one person with a team of agents](https://www.agentteams.online/use-cases/solo-founder): Start in solo mode, promote to a team when the work outgrows one agent, and keep the spend capped. - [Use agents without sending your repo to a vendor](https://www.agentteams.online/use-cases/keep-code-local): Coordination stays on your machine, and you choose which model — including fully local ones — sees any code. - [Run several teams like departments](https://www.agentteams.online/use-cases/run-an-ai-company): Nest teams into an org, watch every board on one map, and route work between departments. ## Comparisons - [AgentTeams vs Claude Code CLI](https://www.agentteams.online/compare/claude-code-cli): Claude Code is an excellent single agent and a great runtime. AgentTeams does not replace it — it runs on top of it and adds the board, the review UI and the multi-team layer the CLI deliberately leaves out. - [AgentTeams vs Cursor](https://www.agentteams.online/compare/cursor): Cursor is a better editor. AgentTeams is a better control room. If your work is you writing code with assistance, use Cursor. If your work is supervising several agents that write the code, the board wins. - [AgentTeams vs Gastown](https://www.agentteams.online/compare/gastown): Gastown is strong on scheduling and recovery, and it is genuinely terminal-native. AgentTeams trades some of that CLI power for a visual board, an in-app review flow and a much shorter setup. - [AgentTeams vs Paperclip](https://www.agentteams.online/compare/paperclip): Paperclip is the closest in spirit — a board, roles and budgets. The difference is where the work happens: Paperclip is a control plane you host, AgentTeams is a local desktop app with the editor, terminal and review built in. ## Answers ### What 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. ### Is it really free? Yes. The app is free and open source, and it ships with a free model that needs no authentication — no account, no API key, no card. Paid providers are entirely optional and only apply if you connect one. ### Which platforms are supported? macOS on both Apple Silicon and Intel, Windows on x64 and ARM64, and Linux via AppImage. The download page detects your platform and puts the right build first. ### How does it actually work? Install the app, open a project, and create a team with a few roles. Give the team an objective. The lead breaks it into tasks and assigns them, builders work in parallel, and the reviewer checks the diffs. You watch the board and step in when a card reaches review. ### Is 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. ### Which models and providers can I use? Claude Code, Codex and OpenCode run as first-class runtimes. Cursor, GitHub Copilot, SuperGrok, Z.AI, MiniMax, Kimi and Kiro connect through supported provider routes, and OpenRouter opens up 200+ models across 75+ providers. Local models work through Ollama. ### Can one team mix different models? Yes, and it is usually the right call. Put a strong reasoning model on the lead and reviewer roles, and a cheaper or faster model on the builders. Cost drops sharply and quality holds because review is where mistakes get caught. ### What stops agents from burning money overnight? Set a monthly ceiling in tokens or currency. You get an alert at 80% and again at 100%, and scheduled runs can hard-stop at the cap rather than continuing. Spend is broken down per team, agent, task and model so you can see what is expensive. ### How many agents should I run at once? Start with three: a lead, a builder and a reviewer. Add builders only when the board shows cards waiting in assigned rather than in review. Most people over-provision builders and end up bottlenecked on review instead. ### What if two agents edit the same file? Give each teammate its own workspace and they never touch the same working tree. For work that genuinely overlaps, link the tasks so one blocks the other and the board enforces the order. ### Can 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. ### Why not just use the CLI agents directly? Use them — AgentTeams runs on top of them. What it adds is the layer the CLIs leave out: parallel agents with roles, a board that shows state, messages between agents, a diff review UI, and budgets. If you only ever run one agent, the CLI is enough. ## Primary pages - [Download](https://www.agentteams.online/download): platform-detected builds and install steps. - [Pricing](https://www.agentteams.online/pricing): why it is free and what can cost money. - [FAQ](https://www.agentteams.online/faq): setup, privacy, models, cost. - [Changelog](https://www.agentteams.online/changelog): release history. - [Search](https://www.agentteams.online/search): full-site search across everything above.