{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "oriveo-oriveo--chat-with-local-model-on-own-machine",
 "repo": "oriveo/oriveo",
 "repo_url": "https://github.com/oriveo/oriveo",
 "repo_slug": "oriveo-oriveo",
 "title": "Chat with a local model server through a relay endpoint",
 "page_title": "How to chat with a local model server through a relay endpoint with Oriveo",
 "summary": "Point Oriveo at Ollama, LM Studio, llama.cpp or vLLM on your own network and chat with local models.",
 "who": "A privacy-focused user or developer who runs open models on their own machine or LAN and wants one chat app for local and hosted models.",
 "problem": "Local model servers expose their own APIs, so each one needs a separate client or a manual setup for every device.",
 "outcome": "A chat session answered by a local model served from your machine, with the same conversation list as your hosted providers.",
 "steps": [
  "Start a local server such as Ollama, LM Studio, llama.cpp or vLLM on your machine and load a model in it.",
  "Complete the web quickstart with `cd web`, `npm install`, and `npm run dev:app`.",
  "In the app, add a Relay endpoint that points at your local server address (inferred: the relay settings screen is where this is entered).",
  "On iOS or Android, let the app find the server on the local network by mDNS where the engine advertises itself, or by probing usual ports.",
  "Select the local model and send a message to confirm it replies."
 ],
 "agent_prompt": "In the oriveo/oriveo repository, start a local model server, run the web client with npm run dev:app, and add a relay endpoint for the local server address <local-server-url>. Expected output: a reply from the local model in the chat. Verify that the request is sent to <local-server-url> and that no Oriveo account is requested.",
 "agents": [
  "any"
 ],
 "difficulty": "Intermediate",
 "time": "30 minutes",
 "basis": "readme",
 "caveat": "The README says the web client can call relays on your own network directly, while most provider APIs need the Next.js route handler on the machine serving the app.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "swift",
 "requirements": [
  "Node 22.22.2 or a later 22.x for the web client (Node 23+ is not supported)",
  "At least one provider API key you created yourself, or a local model server such as Ollama, LM Studio, llama.cpp or vLLM",
  "For iOS: a Mac with Xcode 26 and an iPhone on iOS 18 or later, plus a free Apple Developer account",
  "For Android: JDK 21 and the Android SDK",
  "For subscription sign-in: a ChatGPT or Grok subscription you already hold"
 ],
 "risk": "sensitive",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.9,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/oriveo-oriveo/chat-with-local-model-on-own-machine/",
 "md": "https://dedupedai.com/use-cases/oriveo-oriveo/chat-with-local-model-on-own-machine/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/oriveo-oriveo--chat-with-local-model-on-own-machine.json",
 "api_version": "v1"
}