Agent Fleet
Open-source AI agent orchestration platform — self-hosted mission control for autonomous multi-agent systems. Visual DAG workflows, 450+ MCP tools, human-in-the-loop approvals. Works with Claude, GPT-4o, Gemini, Ollama, Codex.
What is Agent Fleet?
Agent Fleet is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to open-source ai agent orchestration platform — self-hosted mission control for autonomous multi-agent systems. visual dag workflows, 450+ mcp tools, human-in-the-loop approvals. works with claude, gpt-...
Open-source AI agent orchestration platform — self-hosted mission control for autonomous multi-agent systems. Visual DAG workflows, 450+ MCP tools, human-in-the-loop approvals. Works with Claude, GPT-4o, Gemini, Ollama, Codex.
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Open-source AI agent orchestration platform — self-hosted mi
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx agent-fleet-oConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Agent Fleet
Agent Fleet is a self-hosted, open-source AI agent orchestration platform that provides a visual DAG-based workflow editor and mission control dashboard for running autonomous multi-agent systems. It ships with 675+ MCP tools across 45 domains and supports human-in-the-loop approval gates, SSH execution, outbound delivery to 8+ chat channels, and budget management — all from a single web UI. Teams who need to deploy, monitor, and govern complex multi-step AI agent pipelines across Claude, GPT-4o, Gemini, and local models like Ollama without relying on third-party cloud platforms will find it a comprehensive solution.
Prerequisites
- Docker and Docker Compose installed on your host machine
- Git for cloning the repository
- At least one LLM provider API key: ANTHROPIC_API_KEY, OPENAI_API_KEY, or GOOGLE_AI_API_KEY (or a local Ollama/LM Studio instance)
- PostgreSQL and Redis (provided via Docker Compose in the repo)
- An MCP-compatible client or the built-in Agent Fleet web UI
Clone the repository
Clone the Agent Fleet repository to your server or local machine.
git clone https://github.com/escapeboy/agent-fleet-o.git
cd agent-fleet-oRun the installation wizard
Run make install to execute the setup wizard, which initializes the PostgreSQL database, Redis, and creates your admin account automatically.
make installConfigure LLM provider keys
Set your LLM API keys either by editing the .env file generated during installation or through the web UI at Settings → AI Provider Keys after logging in.
# In .env:
ANTHROPIC_API_KEY=sk-ant-...
OPENAI_API_KEY=sk-...
GOOGLE_AI_API_KEY=AIza...
# For local models:
LOCAL_LLM_ENABLED=true
LOCAL_LLM_SSRF_PROTECTION=falseStart the platform
Start all services using Docker Compose. The web UI will be available at http://localhost on the default port.
docker compose up -dCreate your first agent and workflow
Log in to the web UI, navigate to Agents, create a new agent with your chosen LLM provider, then use the visual DAG editor to build a multi-step workflow connecting agents and MCP tools.
Agent Fleet Examples
Client configuration
Environment configuration for Agent Fleet with Anthropic and OpenAI keys plus PostgreSQL and Redis.
{
"DB_CONNECTION": "pgsql",
"DB_HOST": "postgres",
"DB_DATABASE": "agent_fleet",
"REDIS_HOST": "redis",
"ANTHROPIC_API_KEY": "sk-ant-...",
"OPENAI_API_KEY": "sk-...",
"LOCAL_LLM_ENABLED": "false",
"APP_AUTH_BYPASS": "false"
}Prompts to try
Agent tasks you can configure and trigger through the Agent Fleet web UI or API.
- "Monitor a GitHub repository for new issues and post a summary to Slack every hour"
- "Run a multi-agent research workflow: one agent searches the web, another summarizes, a third formats a report"
- "Execute a deployment pipeline: pull latest code via SSH, run tests, notify on Slack with results"
- "Analyze customer feedback from a CSV file and categorize by sentiment, then email the report"
- "Orchestrate a DAG workflow where agent A generates code, agent B reviews it, and agent C deploys it"Troubleshooting Agent Fleet
Database connection errors during or after make install
Ensure Docker is running before executing make install. The wizard starts PostgreSQL in a container — if it fails, check 'docker compose ps' to see container state and 'docker compose logs postgres' for database errors.
Agents fail to execute with LLM provider errors
Verify your API keys are correctly set in Settings → AI Provider Keys in the web UI. For local models (Ollama), set LOCAL_LLM_ENABLED=true and LOCAL_LLM_SSRF_PROTECTION=false if Ollama runs on a LAN IP.
Cannot log in after installation
The make install wizard creates an admin account and displays the credentials at the end of setup. If you missed them, check the installation output or logs. Never set APP_AUTH_BYPASS=true in production as it disables all authentication.
Frequently Asked Questions about Agent Fleet
What is Agent Fleet?
Agent Fleet is a Model Context Protocol (MCP) server that open-source ai agent orchestration platform — self-hosted mission control for autonomous multi-agent systems. visual dag workflows, 450+ mcp tools, human-in-the-loop approvals. works with claude, gpt-4o, gemini, ollama, codex. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Agent Fleet?
Follow the installation instructions on the Agent Fleet GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Agent Fleet?
Agent Fleet works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Agent Fleet free to use?
Yes, Agent Fleet is open source and available under the AGPL-3.0 license. You can use it freely in both personal and commercial projects.
Agent Fleet Alternatives — Similar Coding Agents Servers
Looking for alternatives to Agent Fleet? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
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.
Set Up Agent Fleet in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Agent Fleet?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.