Back to directory

PortOS

A self-hosted dashboard for a developer's own machine that manages running apps, orchestrates AI agents, and tracks personal knowledge and health, all reachable from any device over Tailscale.

PortOS

PortOS is a self-hosted dashboard for a single developer's own dev machine, reachable from a phone, tablet or any device over Tailscale. It brings together process management for running apps, orchestration of AI agents that can work autonomously, and a second-brain layer that captures notes and auto-classifies them.

The author describes it as highly opinionated and personal software built for one specific way of working, where pull requests are welcome but the project prioritizes the author's own needs and may introduce breaking changes without warning; after an update, a user is expected to ask their own coding agent to read the changelog and migrate their data. It is built with Express, React and Three.js, runs under PM2, and is MIT licensed.

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.