777genius/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 Copilot/Kiro/Z.AI/MiniMax/Kimi(200+ models, 75+ LLM providers, free models no auth). Build your AI company with multiple teams

What it solves

Agent Teams AI provides an orchestration layer for managing multiple AI agents as a coordinated team. It solves the problem of fragmented AI tools by allowing users to assemble teams with different roles that work autonomously in parallel, communicate with each other, and manage their own tasks via a visual interface, rather than managing single-agent chats or disparate CLI tools.

How it works

The software acts as a desktop application that integrates with various AI runtimes and providers (such as Claude Code, Codex, OpenCode, Cursor, and GitHub Copilot). It organizes work into a hierarchical structure of organizations, teams, and tasks. Agents are assigned roles and can operate in a Kanban board environment where they move tasks through different statuses, delegate work, and perform code reviews. The system includes a built-in terminal, code editor, and a monitoring system for token usage and costs.

Who it’s for

It is designed for developers and project managers who want to automate complex coding and project work using a team of autonomous AI agents, while maintaining high-level oversight and the ability to intervene through direct messaging or task comments.

Highlights

  • Multi-Provider Orchestration: Connects to a wide array of providers including Claude Code, Codex, OpenCode, Cursor, SuperGrok, and GitHub Copilot.
  • Visual Management: Features a real-time Kanban board, organization maps, and a built-in code editor with Git support.
  • Autonomous Collaboration: Agents can communicate across teams, create and manage their own tasks, and review each other's work.
  • Comprehensive Analytics: Detailed tracking of token usage, costs, and reasoning usage with the ability to set monthly budgets and alerts.
  • Flexible Control: Offers a range of autonomy levels, from fully autonomous execution to per-action human approvals.
  • MCP Integration: Supports the Model Context Protocol (MCP) for integrating external tools and plugins.

Related

  • Project
    agent-tower/core

    A command center for managing multiple AI agents, featuring a Kanban dashboard, automatic Git Worktree isolation for conflict-free coding, and multi-agent collaboration.

  • Project
    saltbo/agent-kanban

    A mission-control board for autonomous software agents that enables human oversight and task coordination through agent-native interfaces and mandatory review gates.

  • Project
    BloopAI/vibe-kanban

    A management layer for AI coding agents that combines kanban planning with dedicated workspaces for agent execution, review, and app previewing.

  • Project
    Untrivial-ai/agent-orchestrator

    Agent Orchestrator is a cross‑platform desktop app that lets you run multiple LLM‑based coding agents as isolated Git‑backed workers, coordinate them via a project‑level orchestrator, and monitor everything on a live Kanban board.

  • Project
    cline/kanban

    A specialized IDE replacement for orchestrating multiple AI agents in parallel, using ephemeral worktrees and linked task cards to automate complex coding workflows.