Back to directory

Optio

Optio is a self-hosted platform that runs AI coding agents as durable, observable sessions on Kubernetes pods or a team's own laptops, then wires them into scheduled reports, webhook responders, ticket-to-merged-PR pipelines and long-lived agents that message each other.

Optio

Optio is a self-hosted AI agent swarm and workflow orchestration platform. It runs agents as durable, observable, triggerable sessions on Kubernetes pods a team operates or on laptops they already have, wiring them into workflows and swarms rather than one-off terminal runs.

Every piece of work is described by five attributes: what starts it (now, a schedule, a webhook, or a ticket), where it runs (a cluster pod with a repository, or a local machine), which agent runtime does the work (a bare terminal, Claude Code, OpenAI Codex, GitHub Copilot, Google Gemini, Cursor, OpenCode or OpenClaw), what it is asked to do, and what happens afterward (exit when done, wait for a person, or persist as a long-lived, addressable agent). Optio derives the right runtime from that combination and shows everything in one work feed with a single status scale.

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.