[{"data":1,"prerenderedAt":109},["ShallowReactive",2],{"seo-verification":3,"marketplace-app-en-librechat":6},{"google":4,"bing":5},"EycwPY2XMyTkVzas3n1ygeNJFGAH513qrMjfDljzsMQ","",{"slug":7,"slugs":8,"categorySlugs":9,"name":13,"description":14,"phase":15,"unavailableReason":16,"docsUrl":17,"logo":16,"github":16,"tagline":18,"longDescription":19,"features":20,"useCases":27,"steps":37,"faq":56,"specs":72,"compatibleOs":80,"relatedApps":81,"relatedPosts":102,"category":106},"librechat",{"fr":7,"en":7,"ar":7},{"fr":10,"en":11,"ar":12},"ia","artificial-intelligence","الذكاء-الاصطناعي","LibreChat","Open-source multi-provider chat interface: OpenAI, Anthropic, Google and local models in a single private UI.",1,null,"https:\u002F\u002Fservorbit.com\u002Fblog\u002Fhow-to-host-librechat-on-a-vps","Private multi-LLM chat — OpenAI, Anthropic, Google and local models on your own server.","LibreChat is an open-source chat interface that unifies multiple AI providers behind a single, polished UI. Deployed on your VPS, it gives your team a private alternative to ChatGPT: conversations, API keys and history stay in your own MongoDB — no data sent to third parties.\n\nIt supports multi-user management with admin roles, per-user API key storage, built-in RAG for document-based conversations, and a flexible `librechat.yaml` for custom endpoints (Ollama, Groq, Mistral). One server, every model, your data.",[21,22,23,24,25,26],"Unified interface for OpenAI, Anthropic, Google Gemini and local Ollama models","Multi-user management with admin roles and access control","Conversation history persisted in your own MongoDB","Built-in RAG: chat with your PDF documents and knowledge bases","Per-user or shared API keys at server level","Extensible via librechat.yaml: custom endpoints, plugins, tool integrations",[28,31,34],{"title":29,"body":30},"Team AI assistant","Deploy a shared ChatGPT alternative for your team. One API key per provider, internal accounts you control, all history in your MongoDB.",{"title":32,"body":33},"Multi-model comparison","Test GPT-4, Claude, Gemma and Mistral side by side in the same interface before integrating one into your product.",{"title":35,"body":36},"Zero-cloud RAG","Combine LibreChat with a local Ollama on the same VPS: your documents, your models, no data leaving the server.",[38,41,44,47,50,53],{"title":39,"body":40},"Order your VPS","From your ServOrbit dashboard, order a Cloud VPS with at least 2 vCPU and 4 GB RAM (8 GB if you add a local Ollama model). Choose Ubuntu 24.04.",{"title":42,"body":43},"Deploy LibreChat","In your client area, click **Install** on the LibreChat card. The automated provisioning deploys LibreChat, MongoDB and all dependencies via Docker Compose.",{"title":45,"body":46},"Create your admin account","Open the app URL in your browser. The first user to register automatically becomes administrator — no setup wizard needed.",{"title":48,"body":49},"Connect your first AI provider","Go to **Settings → API Keys**, enter your OpenAI, Anthropic or Google key, and start chatting. For a fully local setup, point a custom endpoint to your Ollama instance.",{"title":51,"body":52},"Attach a domain (optional)","Attach a domain from your client area to get HTTPS automatically. Without a domain, access via `ssh -L 3080:127.0.0.1:3080 root@your-vps` then `http:\u002F\u002Flocalhost:3080`.",{"title":54,"body":55},"Invite your team","As admin, go to **Admin Panel → Users** to invite team members. You control which AI providers and models each user can access.",[57,60,63,66,69],{"q":58,"a":59},"What is LibreChat?","LibreChat is a self-hosted, open-source chat interface that lets you use OpenAI, Anthropic, Google, and local Ollama models from a single UI — like ChatGPT, but on your own server.",{"q":61,"a":62},"How is LibreChat different from Open WebUI?","Both are multi-model chat interfaces. LibreChat focuses on multi-provider unification (OpenAI + Anthropic + Google + local) with advanced user management and RAG. Open WebUI is optimised for Ollama and local models. Choose LibreChat if you need to manage multiple cloud providers.",{"q":64,"a":65},"Does LibreChat require a domain?","No. LibreChat works on a plain IP:port or via SSH tunnel. A domain is recommended for HTTPS and is required for OAuth social logins.",{"q":67,"a":68},"How do I add my OpenAI or Anthropic key?","Go to Settings → API Keys in the LibreChat UI. You can add keys per user or configure shared server-level keys in the environment variables.",{"q":70,"a":71},"Can I use LibreChat with local models only?","Yes. Configure a custom endpoint pointing to your Ollama instance at http:\u002F\u002Flocalhost:11434\u002Fv1 in librechat.yaml, and you get a fully local, no-cloud setup.",{"ram":73,"cpu":74,"stack":75,"port":79},"2 GB (4 GB recommended)","2 vCPU",[76,77,78],"Docker","Node.js","MongoDB 8","3080",[],[82,90,96],{"name":83,"slug":84,"categorySlug":11,"categoryName":85,"categoryColor":86,"logo":87,"tagline":88,"description":89},"Open WebUI","open-webui","Artificial Intelligence","text-purple-400 bg-purple-500\u002F10","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":91,"slug":92,"categorySlug":11,"categoryName":85,"categoryColor":86,"logo":93,"tagline":94,"description":95},"AnythingLLM","anything-llm","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fanythingllm.svg","Private AI workspace with RAG and agents — your documents, your models, your server.","Open-source AI workspace with built-in RAG, AI agents, and multi-model chat. Connect your own documents, use any LLM — hosted privately on your VPS.",{"name":97,"slug":98,"categorySlug":11,"categoryName":85,"categoryColor":86,"logo":99,"tagline":100,"description":101},"Dify","dify","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.",[103,104,105],"heberger-anythingllm-vps","deployer-dify-vps","heberger-openclaw-vps",{"key":10,"slug":11,"name":85,"objective":107,"icon":108,"color":86},"Build, host and run AI solutions.","ai",1787661757746]