outsourc-e/hermes-workspace

Native web workspace for Hermes Agent — chat, terminal, memory, skills, inspector.

What it solves

Hermes Workspace provides a centralized command center for AI agents, moving beyond simple chat interfaces to a full workspace. It solves the problem of fragmented agent management by integrating chat, file browsing, memory management, skill libraries, and terminal access into a single interface.

How it works

It acts as a frontend UI that pairs with the Hermes Agent (the "brain"). The two communicate via HTTP services: a gateway for core functions like chat and jobs, and a dashboard for configuration, sessions, and skills. It can run in "Portable Mode" (direct connection to OpenAI-compatible backends) or "Enhanced Mode" (routed through the Hermes Agent gateway to unlock full memory and skill features).

Who it’s for

Developers and AI power users who want to orchestrate multiple agents, manage persistent agent memory, and control their AI environment through a professional-grade dashboard and terminal.

Highlights

  • Swarm Mode: A multi-agent control plane using tmux-backed workers for role-based dispatch and autonomous task execution.
  • Integrated Tooling: Includes a Monaco-powered file browser, cross-platform PTY terminal, and a Kanban TaskBoard for planning.
  • ** uma Memory & Skills**: Dedicated interfaces to browse, search, and edit agent memory and a marketplace for over 2,000 skills.
  • MCP Support: Full Model Context Protocol (MCP) integration for cataloging and managing sources.
  • Flexible Deployment: Supports Docker Compose, one-line installers, and remote access via Tailscale.

Related

  • Project
    EKKOLearnAI/hermes-studio

    A desktop app and web console that provides a visual interface and local runtime for managing Hermes Agent, featuring visual workflows, multi-platform deployment, and local model management.

  • Project
    NousResearch/hermes-agent

    A self-improving AI agent with a built-in learning loop that creates and refines skills from experience and maintains persistent user memory across sessions.

  • Project
    johnson7788/MultiUserClaw

    MultiUserClaw is a Docker‑based SaaS framework that lets you run isolated AI assistants (Hermes agents) for many users. It includes a React front‑end, a FastAPI gateway for auth, container management and LLM proxying, per‑user Hermes containers, PostgreSQL storage, and features like knowledge bases, skill store, cron jobs, multi‑channel bots, and multi‑model support.

  • Project
    nesquena/hermes-webui

    A lightweight, self-hosted web interface for the Hermes Agent, providing full parity with the CLI experience for managing autonomous AI agents, files, and sessions.

  • Project
    kyegomez/swarms

    A production-ready multi-agent orchestration framework that provides pre-built architectures for coordinating multiple AI agents in sequential, concurrent, or hierarchical workflows.