Back to directory

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

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.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.