Back to directory

OpenAgent

A self-hostable personal AI assistant combining an LLM, a user's own knowledge base and autonomous agent loops, so agents can browse the web, run code and call MCP-compatible tools.

OpenAgent

OpenAgent ships as a single binary with no separate installation step, connecting to more than 30 model providers and letting a user switch between them per conversation without code changes. It builds a retrieval-augmented knowledge base from a user's own documents.

It supports computer-use, browser-use and coding-agent modes, and includes usage analytics, activity monitoring, tool management and detailed logs. It installs with a shell or PowerShell script, with Docker Compose, or by building the Go backend and the Node.js/Yarn frontend from source, and runs on port 14000 by default.

It is written in Go with a Node.js frontend and is licensed under Apache-2.0.

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.