{"slug": "anythingllm", "name": "AnythingLLM", "category": "ai", "category_name": "AI tools and apps", "description": "", "recommenders": 5, "commenters": 7, "warners": 0, "score": 4.961, "rising": -0.64, "first": "2025-11-03", "latest": "2026-08-06", "why": "AnythingLLM + qwen2.5:14b is what I use \u2014 good for pattern recognition across metrics", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 6, "neutral": 2, "compare": 0, "warn": 0}, "spark": [1, 0, 0, 0, 1, 0, 1, 0, 2, 1, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "AnythingLLM + qwen2.5:14b is what I use \u2014 good for pattern recognition across metrics", "kind": "", "icon": true, "domain": "anythingllm.com", "github_repo": null, "official_url": "https://anythingllm.com", "pricing": "", "aliases": ["AnythingLLM"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 787235568, "item_id": 49202223, "url": "https://news.ycombinator.com/item?id=49202223", "by": "syntaxing", "date": "2026-08-06", "version": null, "stance": "recommend", "quote": "For personal stuff, I use it with AnythingLLM. It replaced any Google search for me.", "excerpt": "For personal stuff, I use it with AnythingLLM. It replaced any Google search for me. For coding, I run opencode though I have been debating switching to Pi. I would argue it\u2019s at Sonnet 3 level.", "context": "", "use_case": "personal local LLM search", "switched_from": "Google Search", "story": "Qwen3.8 Max now ranked as the best overall model by agentic index"}, {"id": 781456129, "item_id": 48841008, "url": "https://news.ycombinator.com/item?id=48841008", "by": "karmakaze", "date": "2026-07-08", "version": null, "stance": "recommend", "quote": "There's some info for AnythingLLM[0] which supports RAG.", "excerpt": "I learned a solution is to turn the documents into vectors in say PostgreSQL (with pgvector) and do a cosine similarity search with a search vector. Doing a search for embed models on HuggingFace shows nomic-ai/nomic-embed-text-v1.5 and Qwen/Qwen3-Embedding-0.6B. I might have used a larger one like Qwen/Qwen3-Embedding-4B. There's some info for AnythingLLM[0] which supports RAG. AnythingLLM has LanceDB out of the box", "context": "", "use_case": "Document RAG chat", "switched_from": "", "story": "Turning a pile of documents into a searchable useable knowledge base"}, {"id": 780895650, "item_id": 48805978, "url": "https://news.ycombinator.com/item?id=48805978", "by": "syntaxing", "date": "2026-07-06", "version": null, "stance": "recommend", "quote": "anythingLLM (in docker) replaced 90%+ of my AI usage", "excerpt": "I have another strix halo that I got for half the price (before this price increase world wide). AMD making lemonade is one of the best reasons to get a strix halo. Lemonade + qwen3.6 35B MTP @ Q8_0 + anythingLLM (in docker) replaced 90%+ of my AI usage. And it\u2019s fully local! Setting everything up took less than 3 hours total, including installing the OS https://lemonade-server.ai/", "context": "", "use_case": "Local AI front-end", "switched_from": "", "story": "AMD Ryzen AI Halo \u2013 $4k AI Dev Kit"}, {"id": 773631360, "item_id": 48351960, "url": "https://news.ycombinator.com/item?id=48351960", "by": "senectus1", "date": "2026-05-31", "version": null, "stance": "recommend", "quote": "so... AnythingLLM?", "excerpt": "so... AnythingLLM? https://anythingllm.com/desktop but with extra steps", "context": "", "use_case": "", "switched_from": "", "story": "Odysseus \u2013 self-hosted AI workspace"}, {"id": 759284816, "item_id": 47455301, "url": "https://news.ycombinator.com/item?id=47455301", "by": "Wewoc", "date": "2026-03-20", "version": null, "stance": "recommend", "quote": "AnythingLLM + qwen2.5:14b is what I use \u2014 good for pattern recognition across metrics", "excerpt": "AnythingLLM + qwen2.5:14b is what I use \u2014 good for pattern recognition across metrics you wouldn't think to look for manually. For everything else the HTML dashboards honestly do a better job. garmin_analysis.html shows your daily values, personal 90-day baseline and age/fitness reference ranges all in one view. Most questions answer themselves just by looking at it.", "context": "", "use_case": "local LLM analysis", "switched_from": "", "story": "Garmin data archive \u2013 local, offline, Ollama-ready"}]}], "caveats": [], "who": [{"by": "jabrotapu", "context": "Full-stack engineer seeking remote role", "url": "https://news.ycombinator.com/item?id=47686916", "date": "2026-04-08"}], "tags": [], "use_cases": ["personal local llm search", "document rag chat", "local ai front-end", "local rag and chat", "local llm analysis", "chat with documents (rag)"], "compared": [{"slug": "qwen", "name": "Qwen", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49200652", "title": "Qwen3.8 Max now ranked as the best overall model by agentic index", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48837110", "title": "Turning a pile of documents into a searchable useable knowledge base", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48805624", "title": "AMD Ryzen AI Halo \u2013 $4k AI Dev Kit", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48346693", "title": "Odysseus \u2013 self-hosted AI workspace", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47601858", "title": "Ask HN: Who wants to be hired? (April 2026)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47453115", "title": "Garmin data archive \u2013 local, offline, Ollama-ready", "mentions": 1}], "sentiment_by_month": {"2025-11": {"neutral": 1, "recommend": 1}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {"recommend": 1}, "2026-04": {"neutral": 1}, "2026-05": {"recommend": 1}, "2026-06": {}, "2026-07": {"recommend": 2}, "2026-08": {"recommend": 1}, "2026-09": {}, "2026-10": {}}, "versions": [], "version_unnamed": 0, "family_ref": null, "runs_on": null, "lines": [], "quotes": [{"id": 787235568, "item_id": 49202223, "url": "https://news.ycombinator.com/item?id=49202223", "by": "syntaxing", "date": "2026-08-06", "version": null, "stance": "recommend", "quote": "For personal stuff, I use it with AnythingLLM. It replaced any Google search for me.", "excerpt": "For personal stuff, I use it with AnythingLLM. It replaced any Google search for me. For coding, I run opencode though I have been debating switching to Pi. I would argue it\u2019s at Sonnet 3 level.", "context": "", "use_case": "personal local LLM search", "switched_from": "Google Search", "story": "Qwen3.8 Max now ranked as the best overall model by agentic index"}, {"id": 781456129, "item_id": 48841008, "url": "https://news.ycombinator.com/item?id=48841008", "by": "karmakaze", "date": "2026-07-08", "version": null, "stance": "recommend", "quote": "There's some info for AnythingLLM[0] which supports RAG.", "excerpt": "I learned a solution is to turn the documents into vectors in say PostgreSQL (with pgvector) and do a cosine similarity search with a search vector. Doing a search for embed models on HuggingFace shows nomic-ai/nomic-embed-text-v1.5 and Qwen/Qwen3-Embedding-0.6B. I might have used a larger one like Qwen/Qwen3-Embedding-4B. There's some info for AnythingLLM[0] which supports RAG. AnythingLLM has LanceDB out of the box", "context": "", "use_case": "Document RAG chat", "switched_from": "", "story": "Turning a pile of documents into a searchable useable knowledge base"}, {"id": 780895650, "item_id": 48805978, "url": "https://news.ycombinator.com/item?id=48805978", "by": "syntaxing", "date": "2026-07-06", "version": null, "stance": "recommend", "quote": "anythingLLM (in docker) replaced 90%+ of my AI usage", "excerpt": "I have another strix halo that I got for half the price (before this price increase world wide). AMD making lemonade is one of the best reasons to get a strix halo. Lemonade + qwen3.6 35B MTP @ Q8_0 + anythingLLM (in docker) replaced 90%+ of my AI usage. And it\u2019s fully local! Setting everything up took less than 3 hours total, including installing the OS https://lemonade-server.ai/", "context": "", "use_case": "Local AI front-end", "switched_from": "", "story": "AMD Ryzen AI Halo \u2013 $4k AI Dev Kit"}, {"id": 773631360, "item_id": 48351960, "url": "https://news.ycombinator.com/item?id=48351960", "by": "senectus1", "date": "2026-05-31", "version": null, "stance": "recommend", "quote": "so... AnythingLLM?", "excerpt": "so... AnythingLLM? https://anythingllm.com/desktop but with extra steps", "context": "", "use_case": "", "switched_from": "", "story": "Odysseus \u2013 self-hosted AI workspace"}, {"id": 762990658, "item_id": 47686916, "url": "https://news.ycombinator.com/item?id=47686916", "by": "jabrotapu", "date": "2026-04-08", "version": null, "stance": "neutral", "quote": "Self-hosted AI infrastructure: Ollama, Open WebUI, AnythingLLM, ComfyUI", "excerpt": "Location: Ahmedabad, Gujarat, India Remote: YES Willing to relocate: No Technologies: TypeScript, JavaScript, Python Node.js, Express, Nest, Next.js, GraphQL, React Native, Microservices, WebSockets React SQL and NoSQL databases LLM agents with LangGraph, LangChain, and RAG pipelines Self-hosted AI infrastructure: Ollama, Open WebUI, AnythingLLM, ComfyUI Vision and video diffusion models: Flux, Wan 2.1, Stable Diffus", "context": "Full-stack engineer seeking remote role", "use_case": "Local RAG and chat", "switched_from": "", "story": "Ask HN: Who wants to be hired? (April 2026)"}, {"id": 759284816, "item_id": 47455301, "url": "https://news.ycombinator.com/item?id=47455301", "by": "Wewoc", "date": "2026-03-20", "version": null, "stance": "recommend", "quote": "AnythingLLM + qwen2.5:14b is what I use \u2014 good for pattern recognition across metrics", "excerpt": "AnythingLLM + qwen2.5:14b is what I use \u2014 good for pattern recognition across metrics you wouldn't think to look for manually. For everything else the HTML dashboards honestly do a better job. garmin_analysis.html shows your daily values, personal 90-day baseline and age/fitness reference ranges all in one view. Most questions answer themselves just by looking at it.", "context": "", "use_case": "local LLM analysis", "switched_from": "", "story": "Garmin data archive \u2013 local, offline, Ollama-ready"}, {"id": 736987520, "item_id": 46061720, "url": "https://news.ycombinator.com/item?id=46061720", "by": "rao-v", "date": "2025-11-26", "version": null, "stance": "recommend", "quote": "I ended up fiddling a bit more with anythingllm which, while having fewer features, understands the workflows a bit more.", "excerpt": "Hey - good response! I'm sure you guys are thinking about this, but please just go through the steps of setting up via docker, uploading say a grad student's worth of papers and docs, scrape a small topic off wikipedia, try and use it for three days and take a look at the ergonomics. It's not easy to regroup sets of documents, get results that link to the document to view post indexing for RAG etc. etc. etc. In gener", "context": "", "use_case": "Chat with documents (RAG)", "switched_from": "", "story": "Launch HN: Onyx (YC W24) \u2013 Open-source chat UI"}, {"id": 732802066, "item_id": 45800129, "url": "https://news.ycombinator.com/item?id=45800129", "by": "bdhtu", "date": "2025-11-03", "version": null, "stance": "neutral", "quote": "https://github.com/Mintplex-Labs/anything-llm", "excerpt": "GitHub links: - https://github.com/janhq/jan - https://github.com/danny-avila/LibreChat - https://github.com/Mintplex-Labs/anything-llm", "context": "", "use_case": "", "switched_from": "", "story": "OSS Alternative to Open WebUI \u2013 ChatGPT-Like UI, API and CLI"}]}