# OpenMake

A self-hosted AI workspace that orchestrates local and OpenAI-compatible models, agents, MCP tools and deep research through one installer, aimed at coordinating work rather than just chatting with a model.

OpenMake is a self-hosted AI workspace and agent runtime for local, open-weight and OpenAI-compatible models. It coordinates specialized models, agents, MCP tools, web research and sandboxed code execution through a single self-hosted install, rather than only providing a chat interface to one model.

A one-line installer sets up Node.js, Docker and PM2 dependencies, generates secrets, starts PostgreSQL and Redis, and brings up a LiteLLM gateway, SearXNG search, sandbox images and internal HTTPS; a minimal mode installs only the app itself. It connects to a local vLLM or Ollama server or any OpenAI-compatible endpoint, and runs on Linux, macOS, or Windows through WSL2.

Website: https://openmake.cc/en/