[{"data":1,"prerenderedAt":109},["ShallowReactive",2],{"seo-verification":3,"marketplace-app-en-hermes":6},{"google":4,"bing":5},"EycwPY2XMyTkVzas3n1ygeNJFGAH513qrMjfDljzsMQ","",{"slug":7,"slugs":8,"categorySlugs":9,"name":13,"description":14,"phase":15,"unavailableReason":16,"docsUrl":17,"logo":18,"github":19,"tagline":20,"longDescription":21,"features":22,"useCases":29,"steps":39,"faq":58,"specs":74,"compatibleOs":80,"relatedApps":82,"relatedPosts":103,"category":106},"hermes",{"fr":7,"en":7,"ar":7},{"fr":10,"en":11,"ar":12},"ia","artificial-intelligence","الذكاء-الاصطناعي","Hermes Agent","The self-learning open-source AI agent from Nous Research. Self-hosted on your VPS, it learns from every exchange and remembers you. MIT license.",1,null,"https:\u002F\u002Fservorbit.com\u002Fblog\u002Fhost-hermes-agent-on-a-vps","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F134168893","https:\u002F\u002Fgithub.com\u002Fnousresearch\u002Fhermes-agent","The open-source AI agent from Nous Research that learns from you — self-hosted, MIT, sovereign.","Hermes Agent is the open-source AI agent from Nous Research, launched in early 2026 and now one of the fastest-growing agent projects on GitHub. Its distinctive trait: it \"grows with you\" — it creates skills from experience, refines them through use, searches its own past conversations and builds a model of who you are across sessions.\n\nUnder the MIT license, Hermes Agent self-hosts on a simple VPS. All of its memory and learning live within your infrastructure (`~\u002F.hermes` volume), and you connect the LLM provider of your choice. It's a sovereign alternative to proprietary cloud AI agents: no dollar subscription, no memory of your exchanges stored with a third party.",[23,24,25,26,27,28],"Self-learning agent: creates and refines its skills from experience","Persistent memory: remembers your exchanges from one session to the next","Searches its past conversations to respond better","LLM provider of your choice, local models possible","Lightweight: runs on an entry-level VPS","Open source (MIT), by Nous Research",[30,33,36],{"title":31,"body":32},"An assistant that knows you","An agent that retains your preferences, your projects and your context over the weeks, instead of starting from scratch with each conversation.",{"title":34,"body":35},"Automation that improves","Hermes learns from every completed task and builds reusable skills, gaining autonomy over time.",{"title":37,"body":38},"Sovereign and private AI","Memory and learning stay on your VPS; no agent data is entrusted to a proprietary cloud service.",[40,43,46,49,52,55],{"title":41,"body":42},"Order the VPS","Choose a ServOrbit Cloud VPS (4 GB RAM recommended for the build and execution) running Ubuntu 22.04.",{"title":44,"body":45},"Install from source","Hermes Agent is built from the official repository: the script clones the project, builds the Docker image and launches the stack (`docker compose up -d`).",{"title":47,"body":48},"Sign in for the first time","Hermes has no login page: it is a command-line agent. Connect to the VPS over SSH, set your LLM key in `\u002Fopt\u002Fhermes-agent\u002F.env`, restart the stack with `docker compose up -d`, then start the agent with `docker exec -it hermes hermes`.",{"title":50,"body":51},"Configure the LLM provider","Fill in the `.env` file (copied from `.env.example`) with the provider and the key of the model you want to use.",{"title":53,"body":54},"Access the dashboard","The Hermes dashboard only listens locally on the VPS: open an SSH tunnel from your machine (`ssh -L 9119:127.0.0.1:9119 root@\u003Cvps-ip>`), then go to `http:\u002F\u002Flocalhost:9119`. There is no reverse proxy and no certificate for you to install — and that is deliberate: bound to the loopback, this dashboard asks for NO password, yet it grants access to your API keys and to a terminal on the VPS. Never publish it on a domain without adding authentication of your own.",{"title":56,"body":57},"Let the agent learn","Over the course of your exchanges, Hermes enriches its memory and its skills (`~\u002F.hermes` volume) — back up this volume to preserve the learning.",[59,62,65,68,71],{"q":60,"a":61},"What is Hermes Agent?","Hermes Agent is an open-source (MIT) AI agent developed by Nous Research. Self-hostable, it stands out for its continuous learning: it creates skills from experience and remembers your exchanges from one session to the next.",{"q":63,"a":64},"Is Hermes Agent open source?","Yes, Hermes Agent is released under the MIT license by Nous Research. You can freely self-host it on your own VPS.",{"q":66,"a":67},"What's the difference from a cloud AI assistant?","Unlike a proprietary cloud assistant, Hermes runs on your own infrastructure: its memory and learning stay within your VPS (`~\u002F.hermes` volume), with no dollar subscription and no data entrusted to a third party.",{"q":69,"a":70},"What VPS configuration does Hermes Agent need?","Plan for 4 GB of RAM to build the image and comfortably run the agent and its dashboard. The project is known to be lightweight and works on small configurations once installed.",{"q":72,"a":73},"How do I preserve what the agent has learned?","All of Hermes's memory and skills are stored in the `~\u002F.hermes` volume. Back up this directory (or mount it on a persistent volume) to retain the learning across redeployments.",{"ram":75,"cpu":76,"stack":77},"4 GB","2 vCPU",[78,79],"Docker","Python",[81],"ubuntu-24.04",[83,91,97],{"name":84,"slug":85,"categorySlug":11,"categoryName":86,"categoryColor":87,"logo":88,"tagline":89,"description":90},"Dify","dify","Artificial Intelligence","text-purple-400 bg-purple-500\u002F10","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fdify.svg","Build LLM applications with drag-and-drop — chatbots, agents, RAG pipelines — no backend required.","Build LLM applications visually: chatbots, RAG agents, pipelines — without writing any backend code.",{"name":92,"slug":93,"categorySlug":11,"categoryName":86,"categoryColor":87,"logo":94,"tagline":95,"description":96},"Open WebUI","open-webui","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fopen-webui.svg","Web interface for your LLMs — Ollama, OpenAI, Mistral — hosted on your own server.","Web interface to interact with your local or remote LLMs. Your data stays on your infrastructure — no third party involved.",{"name":98,"slug":99,"categorySlug":11,"categoryName":86,"categoryColor":87,"logo":100,"tagline":101,"description":102},"OpenClaw","openclaw","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fopenclaw.svg","Your personal AI assistant, self-hosted and reachable on your messaging apps — WhatsApp, Telegram, Discord and 50+ channels.","Your open-source personal AI assistant, reachable from WhatsApp, Telegram, Discord and 50+ messaging apps. Self-hosted on your VPS — your conversations stay with you.",[104,105],"heberger-hermes-agent-vps","heberger-flowise-vps",{"key":10,"slug":11,"name":86,"objective":107,"icon":108,"color":87},"Build, host and run AI solutions.","ai",1787661757636]