FleetQ
**AI Agent Mission Control** — orchestrate AI agents, experiments, workflows, crews, and more through 200+ MCP tools across 31 domains.
## Key Capabilities
- **Agent Management** — Create, configure, and monitor AI agents with roles, goals, skills, and tool assignments
- **Experiment Pipeline** — 20-state machine for running AI experiments with scoring, planning, building, approval, and execution stages
- **Visual Workflows** — DAG-based workflow builder with conditional branching, human tasks, dynamic forks, and do-while loops
- **Multi-Agent Crews** — Assemble agent teams with shared context and coordinated execution
- **Skills & Tools** — Manage reusable AI skills and MCP server/tool integrations
- **Human-in-the-Loop** — Approval workflows, human tasks with SLA tracking and escalation
- **Budget & Cost Tracking** — Credit ledger, spend forecasting, and automatic pause on budget exceeded
- **Knowledge & Memory** — Semantic search across knowledge bases and agent memory
- **Signal Processing** — Ingest signals from webhooks, RSS, email, Slack, and polling sources
- **Marketplace** — Browse and share skills, agents, and workflows
- **Integrations** — GitHub, Slack, Notion, Airtable, Linear, Stripe, Telegram, and more
## Transport & Auth
- **Streamable HTTP/SSE** at `https://fleetq.net/mcp`
- **OAuth 2.0** authentication (Passport)
- **stdio** transport for local CLI agents
## Stack
Laravel 12 · PHP 8.4 · PostgreSQL 17 · Redis 7 · Self-hosted · Open-source (AGPL-3.0)
[GitHub](https://github.com/escapeboy/agent-fleet-o) · [Website](https://fleetq.net)