escapeboy/agent-fleet-o
by Various
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. Wor
MCP
escapeboy/agent-fleet-o
Added 1 June 2026
Overview
An open-source platform for orchestrating autonomous multi-agent AI systems. It provides self-hosted mission control with visual DAG workflows, 450+ MCP tools, and human-in-the-loop approvals. Supports Claude, GPT-4o, Gemini, Ollama, and Codex.
Best for
Best for
Developers who need a self-hosted multi-agent orchestration platform with visual workflow design and human oversight
Use cases
- Orchestrating multi-agent workflows for complex automation tasks
- Integrating human approval steps into autonomous agent processes
- Combining multiple LLMs and MCP tools in a single visual pipeline
How to use
Tools exposed
MCP Tool
Tested with
Claude Desktop, Cursor, ChatGPT, Claude Code
Notes
An open-source platform for orchestrating autonomous multi-agent AI systems. It provides self-hosted mission control with visual DAG workflows, 450+ MCP tools, and human-in-the-loop approvals. Supports Claude, GPT-4o, Gemini, Ollama, and Codex.
30 stars on GitHub. Last updated 2026-06-01. Licensed AGPL-3.0.
Use cases
- Orchestrating multi-agent workflows for complex automation tasks
- Integrating human approval steps into autonomous agent processes
- Combining multiple LLMs and MCP tools in a single visual pipeline
Pros
- Self-hosted gives full control over data and infrastructure
- Visual DAG workflows simplify designing agent interactions
- Supports a wide range of LLMs and 450+ MCP tools
Cons
- Small community with only 30 GitHub stars, limiting support
- Built in PHP, which may reduce appeal for developers preferring Python or JavaScript
- Requires self-hosting and ongoing maintenance effort
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Self-hosted gives full control over data and infrastructure
- Visual DAG workflows simplify designing agent interactions
- Supports a wide range of LLMs and 450+ MCP tools
Cons
- Small community with only 30 GitHub stars, limiting support
- Built in PHP, which may reduce appeal for developers preferring Python or JavaScript
- Requires self-hosting and ongoing maintenance effort
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.