Agent Teams AI

v1.0.0Coding Agentsstable

You're the CTO, 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(200+ models, 75+ LLM providers, free models no

agent-teamsaiai-agentsai-assistantai-tools
Share:
966
Stars
0
Downloads
0
Weekly
0/5

What is Agent Teams AI?

Agent Teams AI is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to you're the cto, 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/openc...

You're the CTO, 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(200+ models, 75+ LLM providers, free models no

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • You're the CTO, agents are your team. They handle tasks on t

Use Cases

Autonomous team task delegation and review
Multi-model support with team coordination
777genius

Maintainer

LicenseAGPL-3.0
Languagetypescript
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx agent-teams-ai

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Agent Teams AI

Agent Teams AI is a desktop application that lets you act as a CTO while autonomous AI agents execute software development tasks as your engineering team. Agents powered by Claude Code, Codex, or OpenCode communicate with each other, review each other's work, and report progress on a built-in kanban board—supporting 200+ models across 75+ LLM providers including free tiers. The application handles worktree isolation per agent, git branch strategy, and task delegation so you can give high-level commands and observe results without managing individual AI sessions.

Prerequisites

  • macOS (Apple Silicon or Intel), Windows, or Linux operating system
  • Node.js 24.16.0 LTS and pnpm 10+ (for development builds)
  • At least one AI runtime: Claude Code subscription, OpenAI Codex access, or a supported OpenRouter model
  • Git installed for worktree isolation features
  • An MCP client or the Agent Teams AI desktop app itself
1

Download the desktop application

Download the prebuilt installer for your platform from the GitHub releases page.

# macOS Apple Silicon
curl -L https://github.com/777genius/agent-teams-ai/releases/latest/download/Agent.Teams.AI-arm64.dmg -o Agent.Teams.AI.dmg

# macOS Intel
curl -L https://github.com/777genius/agent-teams-ai/releases/latest/download/Agent.Teams.AI-x64.dmg -o Agent.Teams.AI.dmg

# Linux AppImage
wget https://github.com/777genius/agent-teams-ai/releases/latest/download/Agent.Teams.AI.AppImage
2

Install and launch the application

Install the downloaded package for your platform. On Windows, allow SmartScreen if prompted. On Linux, make the AppImage executable before running.

# Linux AppImage
chmod +x Agent.Teams.AI.AppImage
./Agent.Teams.AI.AppImage
3

Connect your AI runtime(s)

The setup wizard detects installed runtimes (Claude Code, Codex, OpenCode). Authenticate with your chosen provider(s) or select a free model via OpenRouter—no API key required for free models.

4

Create a project and spawn agents

Open or create a project directory. The app creates separate git worktrees per agent to prevent conflicts. Assign roles (e.g., frontend, backend, reviewer) from the team panel.

5

Issue high-level commands from the kanban board

Type commands as if briefing an engineering team. Agents will break down tasks, assign subtasks to each other, and post status updates to the board.

6

Enable debug mode for development

To observe agent inter-communication in tmux panes during development or troubleshooting, set the teammate mode environment variable.

CLAUDE_TEAM_TEAMMATE_MODE=tmux pnpm dev

Agent Teams AI Examples

Client configuration for Agent Teams AI MCP server

Configure Claude Desktop to use the Agent Teams AI built-in MCP server for external tool integration.

{
  "mcpServers": {
    "agent-teams-ai": {
      "command": "npx",
      "args": ["agent-teams-ai"],
      "env": {
        "AGENT_TEAMS_DISABLE_GPU": "0"
      }
    }
  }
}

Prompts to try

Example high-level CTO commands to issue to your agent team.

- "Build a REST API for user authentication with JWT tokens, tests included"
- "Refactor the payment module to support multiple currencies—frontend agent handles UI, backend agent handles logic"
- "Review the PR in branch feature/search and fix any issues the reviewer finds"
- "Create a full-stack todo app with React frontend and Express backend, deploy to local Docker"
- "Run the test suite, identify all failing tests, and fix them"

Troubleshooting Agent Teams AI

Application crashes or GPU errors on RDP or headless Linux sessions

Set AGENT_TEAMS_DISABLE_GPU=1 before launching: AGENT_TEAMS_DISABLE_GPU=1 ./Agent.Teams.AI.AppImage

Agents conflict on the same files or branches

Agent Teams AI uses git worktrees to isolate agent workspaces. Ensure the project is a git repository before assigning tasks to multiple agents simultaneously.

No AI runtimes detected during setup

Install at least one supported runtime (Claude Code via npm install -g @anthropic-ai/claude-code, or Codex via npm install -g @openai/codex) and restart the application.

Frequently Asked Questions about Agent Teams AI

What is Agent Teams AI?

Agent Teams AI is a Model Context Protocol (MCP) server that you're the cto, 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(200+ models, 75+ llm providers, free models no It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Agent Teams AI?

Follow the installation instructions on the Agent Teams AI GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Agent Teams AI?

Agent Teams AI works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Agent Teams AI free to use?

Yes, Agent Teams AI is open source and available under the AGPL-3.0 license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "agent-teams-ai": { "command": "npx", "args": ["-y", "agent-teams-ai"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Agent Teams AI?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides