Back to directory

Hermes Studio

An open-source, self-hosted web dashboard for Hermes Agent that adds multi-agent crews, cron-based task scheduling, execution approvals, MCP server management and a visual memory graph.

Hermes Studio

Hermes Studio is a self-hosted web workspace for Hermes Agent by NousResearch, built with React, TypeScript and TanStack. It works with Ollama, OpenAI, Anthropic and any OpenAI-compatible backend, and adds a cron job manager for scheduling and monitoring autonomous agent tasks without a terminal.

Beyond chat, it supports named crews of specialized agents with live activity feeds, per-profile isolated workspaces, an interactive force-directed graph of the agent's memory and wiki-link relationships, execution approvals for shell commands with resolved receipts shown inline, installable skills, and a mobile-first PWA reachable over Tailscale.

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.