#7979th of 143 in Coding agents and AI editors
agent-teams-ai
Desktop app that runs teams of coding agents on a kanban board
Live demo ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 2.3k
- License
- AGPL-3.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- TypeScript
337 on 31 Mar 20262,288 on 20 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Agent Teams AI is an Electron-style desktop app (TypeScript) that orchestrates multiple AI agents with distinct roles working in parallel on a kanban board. It drives Claude Code, Codex, OpenCode and other providers such as Cursor, GitHub Copilot, Z.AI, MiniMax and Kiro, and includes per-task logs, diff review, a terminal, and token budgets. Agents message each other, including across teams, and can run in separate git worktrees.
Who it is for: Developers coordinating several coding agents from a desktop GUI
Strengths
- Kanban board with per-task logs, comments and agent-to-agent review in one app
- Per-action tool approvals or fully autonomous mode, selectable per team
- Token analytics with monthly token or cost budgets and alerts at 80% and 100%
- Installers for macOS, Windows and Linux (.AppImage, .deb, .rpm, .pacman); free model needs no key
Weaknesses
- AGPL-3.0 license limits use in closed-source derivative services
- Desktop only; no server or web deployment described in the README
- Depends on third-party runtimes and subscriptions for most providers
- Windows installer triggers SmartScreen; OpenCode may need admin rights on symlink errors
What it needs
- no GPU
- Docker + Compose
- Needs Claude Code, Codex or OpenCode runtime (optional), Provider subscription or API key (optional), git
- Models: Claude Code, Codex, OpenCode, Cursor, SuperGrok
Also in Coding agents and AI editors
See all 143| Rank | Project | Score |
|---|---|---|
| 1 | ArchonYAML workflow engine that runs AI coding agents through fixed dev steps | 84 out of 100 |
| 2 | claw-codeRust CLI coding agent harness using Anthropic and OpenAI-compatible APIs | 83 out of 100 |
| 3 | Open SWEAgent that turns issues into pull requests, reviews PRs and monitors CI | 83 out of 100 |
| #4 | piTerminal coding agent with extensions, skills, and an SDK | 80 out of 100 |
| #5 | oh-my-openagentTerminal coding agent with multi-model orchestration and git-backed memory | 80 out of 100 |