[{"data":1,"prerenderedAt":151},["ShallowReactive",2],{"seo-verification":3,"marketplace-category-fr-ia":6},{"google":4,"bing":5},"EycwPY2XMyTkVzas3n1ygeNJFGAH513qrMjfDljzsMQ","",{"key":7,"data":8},"marketplace-category-fr-ia",{"key":9,"slug":9,"slugs":10,"name":14,"objective":15,"icon":16,"color":17,"apps":18},"ia",{"fr":9,"en":11,"ar":12,"es":13},"artificial-intelligence","الذكاء-الاصطناعي","inteligencia-artificial","Intelligence Artificielle","Créer, héberger et exploiter des solutions IA.","ai","text-purple-400 bg-purple-500\u002F10",[19,29,37,45,53,61,69,77,83,91,99,107,113,119,125,131,137,143],{"name":20,"slug":21,"phase":22,"unavailableReason":23,"description":24,"tagline":25,"docsUrl":26,"github":27,"logo":28},"Open WebUI","open-webui",1,null,"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","https:\u002F\u002Fgithub.com\u002Fopen-webui\u002Fopen-webui","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fopen-webui.svg",{"name":30,"slug":31,"phase":22,"unavailableReason":23,"description":32,"tagline":33,"docsUrl":34,"github":35,"logo":36},"Ollama","ollama","Servez des LLM open source depuis votre propre serveur. Récupérez Llama 3, Mistral, Qwen ou DeepSeek en une commande, derrière une API compatible OpenAI et sans coût au jeton.","Servez des LLM open source depuis votre VPS — API compatible OpenAI, aucun coût au jeton.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fheberger-ollama-vps","https:\u002F\u002Fgithub.com\u002Follama\u002Follama","https:\u002F\u002Fcdn.simpleicons.org\u002Follama",{"name":38,"slug":39,"phase":22,"unavailableReason":23,"description":40,"tagline":41,"docsUrl":42,"github":43,"logo":44},"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","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fdify.svg",{"name":46,"slug":47,"phase":22,"unavailableReason":23,"description":48,"tagline":49,"docsUrl":50,"github":51,"logo":52},"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","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fopenclaw.svg",{"name":54,"slug":55,"phase":22,"unavailableReason":23,"description":56,"tagline":57,"docsUrl":58,"github":59,"logo":60},"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","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F134168893",{"name":62,"slug":63,"phase":22,"unavailableReason":23,"description":64,"tagline":65,"docsUrl":66,"github":67,"logo":68},"LiteLLM","litellm","Passerelle d'API auto-hébergée pour plus de 100 fournisseurs de LLM : un point d'entrée unique compatible OpenAI qui route vers Ollama, Anthropic, Azure et les autres, avec clés virtuelles, quotas et suivi des dépenses.","Passerelle LLM auto-hébergée — un seul point d'entrée compatible OpenAI qui route vers Ollama, Anthropic et plus de 100 fournisseurs.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fself-host-litellm-vps","https:\u002F\u002Fgithub.com\u002FBerriAI\u002Flitellm","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F132372032",{"name":70,"slug":71,"phase":22,"unavailableReason":23,"description":72,"tagline":73,"docsUrl":74,"github":75,"logo":76},"Qdrant","qdrant","Self-hosted vector database for semantic search and RAG. Store, index and query high-dimensional embeddings with HNSW indexing — 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\u002Fheberger-qdrant-vps","https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fqdrant.svg",{"name":78,"slug":79,"phase":22,"unavailableReason":23,"description":80,"tagline":81,"docsUrl":82,"github":23,"logo":23},"Weaviate","weaviate","Base de données vectorielle open source pour la recherche sémantique et le RAG multimodal. Combinez texte, images et métadonnées avec les vectorizers intégrés ou vos propres embeddings sur votre VPS.","Base de données vectorielle multimodale auto-hébergée — GraphQL, RAG et vectorizers intégrés sur votre VPS.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fheberger-weaviate-vps",{"name":84,"slug":85,"phase":22,"unavailableReason":23,"description":86,"tagline":87,"docsUrl":88,"github":89,"logo":90},"LocalAI","local-ai","Faites tourner des LLM open source sur processeur, sans carte graphique. API compatible OpenAI, plus de 200 modèles (Llama, Mistral, Phi), entièrement auto-hébergée sur votre VPS.","Des LLM open source sur processeur, sans GPU — API compatible OpenAI, plus de 200 modèles, auto-hébergés en une commande.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fheberger-localai-vps","https:\u002F\u002Fgithub.com\u002Fmudler\u002FLocalAI","https:\u002F\u002Fraw.githubusercontent.com\u002Fmudler\u002FLocalAI\u002Fmaster\u002Fcore\u002Fhttp\u002Fstatic\u002Flogo.png",{"name":92,"slug":93,"phase":22,"unavailableReason":23,"description":94,"tagline":95,"docsUrl":96,"github":97,"logo":98},"AnythingLLM","anything-llm","Workspace IA open-source : RAG sur vos documents, agents automatisés, multi-modèles. Alternative self-hosted à ChatGPT Teams — vos données ne quittent jamais votre serveur.","Espace de travail IA privé : vos documents deviennent une base de connaissance interrogeable, avec RAG intégré, agents sans code et le modèle de langage de votre choix.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fheberger-anythingllm-vps","https:\u002F\u002Fgithub.com\u002FMintplex-Labs\u002Fanything-llm","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fanythingllm.svg",{"name":100,"slug":101,"phase":22,"unavailableReason":23,"description":102,"tagline":103,"docsUrl":104,"github":105,"logo":106},"Langfuse","langfuse","Plateforme d'observabilité LLM open-source : tracez chaque appel IA, évaluez la qualité des réponses, gérez vos prompts et comparez les coûts de modèles — auto-hébergée sur votre VPS.","Observabilité des applications LLM auto-hébergée : chaque appel tracé, chaque coût mesuré, chaque prompt versionné et évalué — sans envoyer vos traces à un service tiers.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fself-host-langfuse-vps","https:\u002F\u002Fgithub.com\u002Flangfuse\u002Flangfuse","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Flangfuse.svg",{"name":108,"slug":109,"phase":22,"unavailableReason":23,"description":110,"tagline":111,"docsUrl":112,"github":23,"logo":23},"Whisper","whisper","API de transcription audio open source self-hosted : transformez vos enregistrements en texte horodaté via REST, en toute confidentialité sur votre VPS.","API privée de transcription audio sur votre VPS — multilingue, rapide, compatible OpenAI.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fheberger-whisper-vps",{"name":114,"slug":115,"phase":22,"unavailableReason":23,"description":116,"tagline":117,"docsUrl":118,"github":23,"logo":23},"LangFlow","langflow","Construisez des pipelines d'agents IA et de RAG en glisser-déposer. Éditeur visuel open-source de workflows LLM — Python natif, 100+ composants, exposition REST API en un clic.","Construisez des pipelines d'agents IA et de RAG en glisser-déposer — éditeur visuel LLM Python natif, 100+ composants, REST API en un clic.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fheberger-langflow-vps",{"name":120,"slug":121,"phase":22,"unavailableReason":23,"description":122,"tagline":123,"docsUrl":124,"github":23,"logo":23},"LibreChat","librechat","Interface de chat open source multi-fournisseurs : OpenAI, Anthropic, Google et modèles locaux dans une seule UI privée.","Interface de chat IA multi-fournisseurs — OpenAI, Anthropic, Google et modèles locaux sur votre VPS.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fheberger-librechat-vps",{"name":126,"slug":127,"phase":22,"unavailableReason":23,"description":128,"tagline":129,"docsUrl":130,"github":23,"logo":23},"Lobe Chat","lobe-chat","Interface de chat IA open source multi-fournisseurs (OpenAI, Ollama, Anthropic…) avec marché de 200+ plugins, agents personnalisés et synthèse vocale. Licence MIT.","Lobe Chat — interface IA multi-modèles avec 200+ plugins et synthèse vocale, auto-hébergée sur votre VPS.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fheberger-lobe-chat-vps",{"name":132,"slug":133,"phase":22,"unavailableReason":23,"description":134,"tagline":135,"docsUrl":136,"github":23,"logo":23},"PrivateGPT","private-gpt","Assistant RAG documentaire local : posez des questions à vos PDF, contrats et notes — LLM et embeddings tournent sur votre VPS, zéro donnée sortante.","Assistant IA documentaire 100 % local — RAG sur vos fichiers, sans cloud, sans fuite de données.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fheberger-privategpt-vps",{"name":138,"slug":139,"phase":22,"unavailableReason":23,"description":140,"tagline":141,"docsUrl":142,"github":23,"logo":23},"Khoj","khoj","Assistant IA personnel self-hosted AGPL-3.0 : indexez vos notes, documents et PDFs, déclenchez des agents autonomes depuis Obsidian ou votre navigateur.","Khoj — votre assistant IA personnel self-hosted : recherche sémantique sur vos notes et docs, agents autonomes, compatible Obsidian.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fheberger-khoj-vps",{"name":144,"slug":145,"phase":22,"unavailableReason":23,"description":146,"tagline":147,"docsUrl":148,"github":149,"logo":150},"Vane","vane","Moteur de recherche IA self-hosted (ex-Perplexica) — SearXNG intégré + LLM de votre choix (Ollama, OpenAI, Groq…), interface Perplexity-like, zéro données vers un tiers.","Vane — moteur de recherche IA self-hosted : SearXNG + LLM dans un conteneur, sans abonnement cloud.","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fheberger-vane-vps","https:\u002F\u002Fgithub.com\u002FItzCrazyKns\u002FVane","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F95534749",1793820313249]