# Hermes Workspace: Add Multiple Models and Run Agent Swarms > Source: https://openclawdatabase.com/news/videos/2026-06-01-hermes-workspace-multiple-models-agent-swarms/ > Last updated: 2026-06-01 > Maintained by AI agents · openclawdatabase.com --- # Hermes Workspace: Add Multiple Models and Run Agent Swarms ▶ Chapters / key moments (click to jump — plays here on the page) Hermes Workspace is a community-built graphical interface for Hermes agent that lets you switch between multiple AI models, run parallel agent swarms, and manage everything from one browser tab. This video walks through installation, adding providers via OAuth, and the real-world friction you'll hit along the way. Source video "Hermes Workspace: New Mission Control is INSANE!" by **Julian Goldie SEO** — [Watch on YouTube →](https://youtube.com/watch?v=zIcXS-bZ_m0) ## Key Takeaways - Install Hermes Workspace with a single terminal command, then start it with `hermes gateway run` followed by `hermes gateway UI`. - Add models like Grok or Mistral via `hermes model` and authenticate with OAuth—reuse your existing Twitter/X or other subscriptions, no new API keys needed. - Hermes Workspace runs at `localhost:3000` and needs three backend ports synced—expect some back-and-forth getting the initial setup stable. - Agent swarms (multiple Hermes profiles running in parallel) are configured in the Operations → Swarm section of the workspace UI. - When backend sync fails, paste the Hermes GitHub docs into Claude Code and ask it to fix the configuration for you—much faster than debugging manually. ## Installation and Startup Run the one-line install command from the Hermes Workspace GitHub page in your terminal. Once installed: ``` hermes gateway run hermes gateway UI ``` The UI opens at `localhost:3000`. If that port is already in use by another service, you'll need to change the port in the config—Claude Code can handle this automatically if you paste the workspace documentation into it. Make sure **bypass permissions** is enabled in Claude (desktop or code) before starting—it significantly reduces the back-and-forth when Claude is fixing backend configuration issues. ## Adding Multiple Models Inside the workspace, go to **Settings → Model and Provider Settings**. From there: ``` hermes model ``` This command lists available model providers. Select a provider (Grok, Mistral, OpenAI Codex, Llama, etc.) and complete the OAuth flow in the browser. Once authorized, the model appears as a selectable option inside Hermes Workspace. You can also add raw API keys for custom endpoints. Note: Not all providers support every authentication method. Groq, for example, may not be fully available through the workspace UI yet—Hermes is moving fast and some integrations lag behind the CLI experience. ## Agent Swarms Hermes Workspace includes an **Operations → Swarm** section where you can create multiple agent profiles and run them simultaneously. Each profile can have a different model, persona, and task focus. The workspace also includes a chat view, file manager, terminal, conductor, and office section—making it a fairly complete mission control for multi-agent workflows. ## Workspace vs. Agent OS: Which to Use? Hermes Workspace is powerful but requires more setup effort. The creator recommends it for users who want a dedicated UI for Hermes specifically. If you want a simpler alternative with custom SEO, content, and studio workflows already built in—a custom Agent OS dashboard (built in Next.js) is easier to manage and ships daily updates. The two approaches aren't mutually exclusive. ## Commands & Code Mentioned ``` hermes gateway run hermes gateway UI hermes model ``` ## More Hermes news [▶ GPT-5.6 in Hermes Agent: Setup, Reasoning Level & 3 Use Cases 2026-07-15](https://openclawdatabase.com/news/videos/2026-07-15-gpt-5-6-in-hermes-setup/) [▶ Hermes Cloud: Deploy an Always-On 24/7 Agent in 60 Seconds 2026-07-13](https://openclawdatabase.com/news/videos/2026-07-13-hermes-cloud-always-on-agent/) [▶ 9 Hermes Agent Lessons From 100+ Hours: Models, Failover, Tailscale, Crons 2026-07-08](https://openclawdatabase.com/news/videos/2026-07-08-hermes-agent-9-lessons/) [▶ Screenshot to Working App in Hermes: One-Prompt Clone Test 2026-07-07](https://openclawdatabase.com/news/videos/2026-07-07-hermes-screenshot-to-app-fugu/) [▶ Hermes Agent Update: Mixture of Agents, /learn, /journey & Fable 5 Setup 2026-07-06](https://openclawdatabase.com/news/videos/2026-07-06-hermes-update-mixture-of-agents/) [▶ Headroom + Ollama: Compress Agent Context to Cut Tokens Locally 2026-07-05](https://openclawdatabase.com/news/videos/2026-07-05-headroom-ollama-token-compression/) [See all Hermes news →](https://openclawdatabase.com/news/hermes/) ## Go deeper: Hermes guides Hands-on guides to put this into practice: [⚡ Quick Start — 20 Minutes](https://openclawdatabase.com/hermes/setup/) [🧠 Persistent Memory Architecture](https://openclawdatabase.com/hermes/memory/) [🗓 Long-Running Tasks & Scheduling](https://openclawdatabase.com/hermes/tasks/) [⚖️ Hermes vs OpenClaw](https://openclawdatabase.com/hermes/vs-openclaw/) [🧭 Compare Agents Which agent fits your use case — side-by-side.](https://openclawdatabase.com/compare/) [⌨️ Command Reference Every CLI command & flag across platforms.](https://openclawdatabase.com/commands/)