agent-teams-ai
Agent Teams is a desktop app that orchestrates teams of AI agents across Claude, Codex and OpenCode. You create a team with different roles, and the agents work in parallel, create and manage their own tasks, message each other (including across teams) and review each other's work, while you watch tasks move across a kanban board. You can review the code changes each task made and approve, reject or comment, read task-specific logs and token usage, message any agent directly, and choose between full autonomy and approving each action. A solo mode runs a single agent to save tokens. The README says you can start immediately with a free model with no sign-up, or use the Claude, Codex or OpenCode access you already have.
Install by downloading the desktop app for your platform; the README says there are no prerequisites and that the app detects supported runtimes and guides setup. It stresses that the desktop app is the primary product and that the browser path lacks the full runtime and terminal. On Windows it may trigger SmartScreen and the README says to launch as Administrator when using OpenCode runtimes. The README includes a comparison table against other tools such as Cursor and the Claude Code CLI, which reflects the author's own assessment. The project is AGPL-3.0 licensed.
Features
Why choose it
Trade-offs
Maintenance check
- Last commit
- 2026-10-22
- Commits, last 90 days
- 100+
- Releases, last 90 days
- 11
- Latest release
- v2.17.10 (2026-10-09)
- Open issues
- 38
- Recent issues with at least one comment
- —
Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.
Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.
Most discussed open issues
- #205 [FEAT] Optionally (maybe even by default): each team has a unique context in each project8 comments · 2026-06-05
- #668 [FEAT] Multiple Claude Accounts6 comments · 2026-09-16
- #133 [FEAT] run with local ai6 comments · 2026-05-20
- #778 [FEAT] oMo native support4 comments · 2026-09-30
- #684 [BUG]Anthropic Compatible Endpoint Connection Failure (v2.14.1+)4 comments · 2026-09-18
Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.
Compatibility
Quick start
Use cases
Alternatives
Comments
No comments yet. Be the first!