Back to directory

Agentlas OS

An agent operating system that keeps a hub of specialist AI agents and assembles a temporary team of them for a task, running locally alongside Claude Code, Codex, Cursor or Gemini.

Agentlas OS

Agentlas OS is a local-first platform for running teams of specialist AI agents. Instead of one general agent, it keeps specialist agents in a shared hub and assembles a temporary orchestrator to bring the right specialists to a given task, with the caller supplying their own model and API access. It works inside Claude Code, Codex, Cursor and Gemini.

A web hub lets people browse and publish public agents, with per-agent release files, discussion, and compatible add-ons, and follows the A2A protocol for agent cards and calling conventions. A desktop app and a CLI-only installer are both available, and the desktop client is open source.

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.