{"slug": "show-hn-hermes-webtop-experience-hermes-agent-without-hassle", "title": "Show HN: Hermes WebTop ~ Experience Hermes Agent without Hassle", "summary": "Hermes-WebTop launches a browser-based Linux desktop with a pre-configured Hermes AI assistant that runs entirely through GitHub Codespaces, eliminating the need for local hardware or GPU. The tool provides a complete Ubuntu MATE environment, VSCode integration, and free LLM support via ModelRelay, allowing users to deploy a personal AI agent in under 10 minutes. This removes the primary barrier to using Hermes—a dedicated machine with a GPU—making the framework accessible for testing, student projects, and budget-conscious users.", "body_md": "*Run Hermes-Agent inside a browser-based VSCode + Linux desktop with free LLM support through ModelRelay.*\n\n**She will grow with you ...**\n\n**Hermes-WebTop** gives you a **fully functional Hermes AI assistant** in your browser in under 10 minutes — no powerful PC, no Docker on your machine, no GPU required.\n\nJust open this repo in a GitHub Codespace and you get:\n\n- A complete Ubuntu MATE desktop (WebTop) for computer use\n- CodeServer at port 8888 with Hermes Extension installed and preconfigured\n- Ollama server pre-installed and auto-started\n- ModelRelay pre-installed, auto-started and pre-configured as default model\n- Hermes gateway accessible via desktop launcher\n[Mnemon](https://github.com/mnemon-dev/mnemon)as your Hermes default[memory provider](https://github.com/gitricko/hermes-plugin-mnemon)- Persistent volume for your config and settings\n\nWhen you're ready to go production, simply move the same Docker setup to your own machine or VPS.\n\nHermes is an AI agent framework that connects LLMs directly to your communication platforms (WhatsApp, Telegram, Slack, Discord, etc.) and can run cron jobs, spawn sub-agents, speak/listen, and give you a beautiful dashboard.\n\nThe only catch? You normally need a dedicated machine with GPU.\n**Hermes-WebTop removes that catch completely.**\n\nPerfect for:\n\n- Trying Hermes-Agent risk-free\n- Free LLM APIs through\n[ModelRelay](https://github.com/ellipticmarketing/modelrelay)or[OmniRoute](https://github.com/diegosouzapw/OmniRoute) - Students / hackers / evaluators\n- Anyone who wants a personal AI assistant without breaking the bank\n\n-\n**Open this repository in a GitHub Codespace**(big green \"Code\" button → Codespaces → New)It is recommended that you use 4 cpu core and 16G codespace.\n\n-\nIn the Codespace terminal run:\n\n```\nmake start\n```\n\n-\nWait ~60 seconds after first launch. It takes about 5-7 minutes if docker image is not loaded yet. When the web desktop URL appears in the Codespace Ports tab, click it.\n\n**Demo on pre-installed WebApps** -\nUse VSCode on Web (Code-Server) to interact wit your agents:\n\n- Interact with files system using VSCode on the browser\n- Interact with Hermes Agent using VSCode Extension OR via hermes-cli in the VSCode Terminal\n- Claude Code + Hermes (both using Terminal-Cli or VSCode Extension) shared the persistent memory via\n[mnemon](https://github.com/mnemon-dev/mnemon)so that Hermes remembers what you did in Claude and vice-versa. - Use WebTop interface in port 3000 when you need to do computer-use\n\n-\nConfigure your Hermes with your favourite messaging app !\n\n- Recommendation: Watch Youtube ;-)\n\n-\nLast NOTE:\n\n- For localhost install.. just use\n[http://localhost:[3000,8888,9119,7352,20128]](http://localhost:%5B3000,8888,9119,7352,20128%5D)\n\n- For localhost install.. just use\n\n**Zero local install**— everything runs in browser via GitHub Codespaces** Free-tier friendly**— uses ModelRelay, Ollama daily cloud credits or NVIDIA Build API fallback** Persistent config**— docker volume backup and restore after Codespace recreation** Easy backup/restore**—`make backup`\n\n/`make restore`\n\n**One-command everything**— powerful Makefile + clean`docker-compose.yml`\n\n**Auto-start ModelRelay**— Default configuration for Free LLM API to Hermes** Auto-start OmniRoute**— You need some configuration before it work but it is flexible and powerful** Auto-start Ollama**— custom init script on WebTop boot** Colima / local Docker support**ready** Built-in code-server IDE**— browser-based VS Code on port`8888`\n\n**Multiple AI VSCode Extension preinstall/config with ModelRelay**- Cline, Hermes and ClaudeCode** Mnemon as default memory provider**- a knowledge store for Hermes with intent-aware recall, importance decay, and auto-deduplication\n\nThis image includes `code-server`\n\nand exposes it on port `8888`\n\n.\n\n`code-server`\n\nis installed automatically in the container.- The desktop launcher\n`CodeServer`\n\nstarts it inside the WebTop environment. - In Codespaces, use the forwarded private port\n`8888`\n\n. - Locally, open\n`http://localhost:8888`\n\n.\n\nNote: this setup may use\n\n`code-server --auth none`\n\nin development, so keep port`8888`\n\nprivate. For local production use, secure it with an authenticated reverse proxy or firewall.\n\n- Hermes Agent's Extension is preinstalled and configured in VSCode\n- Cline Extension is also preinstall and configured to ModelRelay\n- Start Hacking away in VSCode, use WebTop if you need to monitor agent do desktop-use operations. eg: Non-Headless Chrome debugging for instance / Linux Computer-Use\n\n**The WebTop URI is automatically protected — no one else can reach it.**\n\nGitHub Codespaces forwards ports **privately by default** (this is the setting the `make start`\n\ncommand uses). According to official [GitHub documentation](https://docs.github.com/en/enterprise-cloud@latest/codespaces/reference/security-in-github-codespaces):\n\n\"All forwarded ports are private by default, which means that you will need to authenticate before you can access the port.\" \"Privately forwarded ports: Are accessible on the internet, but\n\nonly the codespace creator can access them, after authenticating to GitHub.\"\n\n- The URL you click in the\n**Ports** tab (`https://<your-codespace>-3000.app.github.dev`\n\n) is guarded by**GitHub authentication cookies**. - These cookies expire every\n**3 hours**— you'll simply be asked to log in again (super quick). - If someone tries to open the link in an incognito window, via curl, or from another computer without being logged into\n**your** GitHub account, they are redirected to the GitHub login page or blocked. - You (and only you) can access the full Ubuntu desktop, the browser inside it, Ollama, Hermes, and everything else.\n\n- The entire environment runs in an\n**isolated GitHub-managed VM**— not on your laptop. - Codespaces are\n**ephemeral**: delete the codespace and everything disappears (except the backed-up volume you control). - TLS encryption is handled automatically by GitHub.\n- The\n`GITHUB_TOKEN`\n\ninside the codespace is scoped only to this repo and expires when you stop/restart. - We never set the port to \"Public\" or even \"Private to Organization\" — it stays strictly private to you.\n\n**Bottom line**: This is actually **more secure** for experimentation than running Docker locally on your personal machine (no accidental exposure, no firewall holes, no persistent processes on your hardware).\n\n**For production use** we still recommend moving the same Docker image to your own VPS or server with additional hardening (firewall, HTTPS reverse proxy, strong secrets, etc.). This Codespace version is perfect for safe testing and development.\n\nYour configuration and settings are persisted in a Docker volume.\nThe project includes convenient `make`\n\ntargets to back up and restore this data in codespace:\n\n```\nmake backup          # creates backup/hermes_config_backup.tar.gz\nmake restore         # restores from backup/hermes_config_backup.tar.gz\n```\n\n- Migrating from GitHub Codespaces to a local machine or VPS\n- Testing experimental changes without risking your current setup\n- Quickly cloning your working environment into a fresh Codespace or container\n\n- In your current environment, run\n`make backup`\n\n. - Download the generated file:\n`backup/hermes_config_backup.tar.gz`\n\n. - Place the file in the\n`backup/`\n\nfolder of the new environment. - Run\n`make restore`\n\n.\n\n**💡 Tip:** Always back up before making significant changes. The restore process will overwrite the existing volume data, so test in a separate environment first if you're unsure.\n\nRun locally (no Codespaces)\n\n```\nmake build-local             # especially if you modified the ./docker/Dockerfile\nmake start-locally-baked     # start from your local baked image\n```\n\nThis is a community project — every star, issue, or PR helps enormously! Feel free to open issues for bugs or feature requests.\n\nMIT — see [LICENSE](/gitricko/hermes-webtop/blob/main/LICENSE)", "url": "https://wpnews.pro/news/show-hn-hermes-webtop-experience-hermes-agent-without-hassle", "canonical_source": "https://github.com/gitricko/hermes-webtop", "published_at": "2026-05-29 09:53:28+00:00", "updated_at": "2026-05-29 10:17:40.400362+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "ai-infrastructure", "large-language-models", "artificial-intelligence"], "entities": ["Hermes", "Hermes-WebTop", "ModelRelay", "OmniRoute", "Mnemon", "GitHub Codespace", "Ollama", "CodeServer"], "alternates": {"html": "https://wpnews.pro/news/show-hn-hermes-webtop-experience-hermes-agent-without-hassle", "markdown": "https://wpnews.pro/news/show-hn-hermes-webtop-experience-hermes-agent-without-hassle.md", "text": "https://wpnews.pro/news/show-hn-hermes-webtop-experience-hermes-agent-without-hassle.txt", "jsonld": "https://wpnews.pro/news/show-hn-hermes-webtop-experience-hermes-agent-without-hassle.jsonld"}}