Back to directory

Hermes Agent Control Room

A starter template for organizing and documenting a growing set of Hermes AI agents, from a single agent on one VPS up to specialist teams coordinated by an orchestrator.

Hermes Agent Control Room

Hermes Agent Control Room is a public template repository for setting up a control room before scaling up a set of Hermes agents. The Control Room is a sidecar folder that documents and governs the agents; it is not an agent itself, but a system map, operating manual, registry, runbook library and recovery notebook.

It provides a control-plane folder structure, templates for agent runbooks, Docker notes, secret maps and backups, and a level-based architecture for growing from one agent to a specialist team with an orchestrator and a task-bus pattern for delegation. Bundled setup and operations skills let an agent build or manage the system itself.

The intended path is to set up the Control Room first, then register agents into it, adding specialists and automation only as the operator's needs grow.

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.