[{"data":1,"prerenderedAt":66},["ShallowReactive",2],{"seo-verification":3,"marketplace-category-fr-ia":6},{"google":4,"bing":5},"EycwPY2XMyTkVzas3n1ygeNJFGAH513qrMjfDljzsMQ","",{"key":7,"slug":7,"name":8,"objective":9,"icon":10,"color":11,"apps":12},"ia","Intelligence Artificielle","Créer, héberger et exploiter des solutions IA.","ai","text-purple-400 bg-purple-500\u002F10",[13,22,30,37,44,51,59],{"name":14,"slug":15,"phase":16,"description":17,"tagline":18,"docsUrl":19,"github":20,"logo":21},"Open WebUI","open-webui",1,"Interface web pour interagir avec vos LLMs locaux ou distants. Vos données restent sur votre infrastructure — aucun tiers impliqué.","Interface web pour vos LLMs — Ollama, OpenAI, Mistral — hébergée sur votre propre serveur.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fheberger-open-webui-vps","https:\u002F\u002Fgithub.com\u002Fopen-webui\u002Fopen-webui",null,{"name":23,"slug":24,"phase":16,"description":25,"tagline":26,"docsUrl":27,"github":28,"logo":29},"Ollama","ollama","Run open-source LLMs locally via a dead-simple API. Pull Llama 3, Mistral, Qwen or DeepSeek in one command — OpenAI-compatible, zero per-token cost.","Run open-source LLMs on your VPS — OpenAI-compatible API, zero per-token cost.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fheberger-ollama-vps","https:\u002F\u002Fgithub.com\u002Follama\u002Follama","https:\u002F\u002Fcdn.simpleicons.org\u002Follama",{"name":31,"slug":32,"phase":16,"description":33,"tagline":34,"docsUrl":35,"github":36,"logo":21},"Dify","dify","Créez des applications LLM visuellement : chatbots, agents RAG, pipelines — sans écrire de code backend.","Créez des applications LLM en drag-and-drop — chatbots, agents, pipelines RAG — sans backend.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fdeployer-dify-vps","https:\u002F\u002Fgithub.com\u002Flanggenius\u002Fdify",{"name":38,"slug":39,"phase":16,"description":40,"tagline":41,"docsUrl":42,"github":43,"logo":21},"OpenClaw","openclaw","Votre assistant IA personnel open source, joignable depuis WhatsApp, Telegram, Discord et 50+ messageries. Auto-hébergé sur votre VPS — vos conversations restent chez vous.","Votre assistant IA personnel, auto-hébergé et joignable sur vos messageries — WhatsApp, Telegram, Discord et 50+ canaux.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fheberger-openclaw-vps","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw",{"name":45,"slug":46,"phase":16,"description":47,"tagline":48,"docsUrl":49,"github":50,"logo":21},"Hermes Agent","hermes","L'agent IA open source auto-apprenant de Nous Research. Auto-hébergé sur votre VPS, il apprend de chaque échange et se souvient de vous. Licence MIT.","L'agent IA open source de Nous Research qui apprend de vous — auto-hébergé, MIT, souverain.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fheberger-hermes-agent-vps","https:\u002F\u002Fgithub.com\u002Fnousresearch\u002Fhermes-agent",{"name":52,"slug":53,"phase":16,"description":54,"tagline":55,"docsUrl":56,"github":57,"logo":58},"LiteLLM","litellm","Self-hosted OpenAI-compatible API gateway for 100+ LLMs — route between Ollama, Anthropic, Azure and more from a single endpoint, with per-key rate limits and spend tracking.","Self-hosted LLM API gateway — route between Ollama, Anthropic and 100+ providers from a single OpenAI-compatible endpoint.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fself-host-litellm-vps","https:\u002F\u002Fgithub.com\u002FBerriAI\u002Flitellm","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F132372032",{"name":60,"slug":61,"phase":16,"description":62,"tagline":63,"docsUrl":64,"github":65,"logo":21},"Qdrant","qdrant","Self-hosted vector database for semantic search and RAG. Store, index and query high-dimensional embeddings at sub-millisecond latency — the missing infrastructure layer for your LLM stack.","Self-hosted vector database for semantic search and RAG — the missing infrastructure layer for your LLM stack.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fself-host-qdrant-vps","https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant",1784126253465]