#4848th of 52 in Agent platforms
mission-control
Control plane for dispatching and reviewing work across AI agent runtimes
- Stars
- 6.4k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Jul 2026
- Language
- TypeScript
3,682 on 4 Apr 20266,424 on 31 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Mission Control is a Next.js control plane that sits above agent runtimes such as OpenClaw, Claude Code and Codex. It tracks tasks through assignment, execution and review, and shows agent presence, activity, token use and cost. State is stored in SQLite, and it exposes a web UI, CLI, MCP server, REST/OpenAPI, WebSocket and SSE. The README labels it alpha software.
Who it is for: Operators running several agents who need task review and cost tracking
Strengths
- SQLite-only state with WAL mode, no separate database server to run
- Web UI, CLI, MCP server and OpenAPI REST API cover the same control plane
- Task board with an Aegis review gate requiring an approval record before done
- Gateway-free REST loop for registering agents and claiming task queues
Weaknesses
- Alpha: APIs, schemas and configuration may change between releases
- Adapter depth varies by runtime; feature parity is not guaranteed
- Live session messaging needs a connected runtime gateway
- Network exposure needs a TLS reverse proxy, MC_ALLOWED_HOSTS and hardening
What it needs
- no GPU
- Docker + Compose
- Needs Node.js 22+, pnpm, SQLite (better-sqlite3), Agent runtime gateway (optional)
- Models: OpenClaw, Claude Code, Codex, CrewAI, LangGraph
- port 3000
Quick answers
Is mission-control open source?
Yes. Its code is on GitHub under the MIT license.
Can you run mission-control with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does mission-control need a GPU?
No, it runs without one.
Also in Agent platforms
See all 52| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 94 out of 100 |
| 2 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 93 out of 100 |
| 3 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 93 out of 100 |
| #4 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |
| #5 | open-designDesign workspace that drives your coding agent to build prototypes, decks and video | 92 out of 100 |