agent-teams-ai
You're the boss, agents are your team. They handle tasks on their own, message each other, and review each other's work. You just watch the kanban board and giv
What is agent-teams-ai?
You're the boss, agents are your team. They handle tasks on their own, message each other, and review each other's work. You just watch the kanban board and give high-level commands. Codex/Claude/OpenCode/Cursor/Grok/GitHub/Kiro/Z.AI/Xiaomi/MiniMax/Kimi(300+ models, 200+ LLM providers, free models no auth) Build your AI company with multiple teams
Overview of agent-teams-ai
What it is
An orchestration layer for AI agent teams that allows users to act as a manager overseeing autonomous agents. The agents handle tasks, communicate and review each other's work, while the user monitors progress on a kanban board and issues high-level commands. It supports 300+ models and 200+ LLM providers, including free models with no authentication required, as well as integration with Codex, Claude, OpenCode, Cursor, Grok, GitHub, Kiro, Z.AI, Xiaomi, MiniMax, and Kimi. The application is a free desktop app available on Windows and macOS, and primarily targets coding and broader project workflows.
Key features
- Assemble agent teams with different roles that work autonomously in parallel using a single prompt - Agents communicate, create and manage their own tasks, review each other's work, and leave comments - Cross-team communication allows agents to collaborate and message each other across separate teams - Built-in review workflow shows how agents review tasks to ensure correctness - Token analytics and budgets track input, output, cache, and reasoning usage across teams, agents, tasks, projects, models, runtimes, sessions, commands, and runs - Organizations and global overview groups teams into departments or squads, tracking status on a live map - Flexible autonomy lets agents run fully autonomous, or require user approval for tool actions - Integrated terminal workspace with visual PTY scoped to each team and project, local shell tabs, persistent history, autocomplete - Supports 29 interface languages - Includes a built-in code editor with Git support - MCP integration for external tools and extensible agent plugins
Use cases
- Software development projects where multiple AI agents collaborate on coding, debugging, and code review - Project management scenarios where agents plan, delegate, and monitor task progress autonomously - Users who want to leverage multiple LLM providers and models in a single orchestrated workflow - Organizations needing structured oversight of AI agent teams across departments or squads
Getting started
No prerequisites - the app can detect installed Claude Code, Codex, and OpenCode runtimes. You can also connect Cursor, SuperGrok, GitHub Copilot, Z.AI, MiniMax, and Kiro from the UI. May trigger SmartScreen on Windows - click 'More info' -> 'Run anyway' to run normally. Administrator mode may be needed only if the app reports a specific OpenCode symlink or permission error. See the repository README for installation binaries and detailed instructions.
License and pricing
Licensed under AGPL-3.0. The pricing type is open source. No cost is mentioned beyond free models that require no authentication.
Based on the project's public README and repository metadata.
