{"slug": "sqlite-vec", "name": "sqlite-vec", "category": "databases", "category_name": "Databases", "description": "", "recommenders": 3, "commenters": 6, "warners": 0, "score": 3.177, "rising": -0.98, "first": "2025-11-28", "latest": "2026-07-08", "why": "SQLite + sqlite-vec + Tantivy + a tiny embedding model will stay as my go to.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 1, "compare": 2, "warn": 0}, "spark": [1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "SQLite + sqlite-vec + Tantivy + a tiny embedding model will stay as my go to.", "icon": true, "domain": null, "github_repo": "github.com/luoxiaojian/sqlite-vec", "official_url": "https://github.com/asg017/sqlite-vec", "pricing": "", "aliases": ["sqlite-vec", "SQLite-vec"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 781322550, "item_id": 48832659, "url": "https://news.ycombinator.com/item?id=48832659", "by": "brainless", "date": "2026-07-08", "stance": "recommend", "quote": "SQLite + sqlite-vec + Tantivy + a tiny embedding model will stay as my go to.", "excerpt": "I have a project on very similar lines, https://github.com/brainless/dwata, which I have not been developing for the past few months. I have been meaning to get back to it and I really like what I see on your project page. My aim is to build a truly local app using only tiny/small models. I have had really good results from Qwen 3.5 1B, 4B, etc. Also, Gliner or similar models for different uses. SQLite + sqlite-vec +", "context": "", "use_case": "vector search", "switched_from": "", "story": "Show HN: Rowboat \u2013 Open-source, local-first alternative to Claude Desktop"}, {"id": 752381137, "item_id": 47023821, "url": "https://news.ycombinator.com/item?id=47023821", "by": "anvevoice", "date": "2026-02-15", "stance": "recommend", "quote": "SQLite + sqlite-vec keeping things simple is underrated", "excerpt": "Nice architecture choices \u2014 SQLite + sqlite-vec keeping things simple is underrated. The kernel/adapter pattern is smart for multi-channel support. One area worth exploring: voice as a channel. We've been building voice AI agents for hospitality and service businesses, and the data is striking \u2014 voice interactions convert at ~47% higher rates than text chatbots for things like booking confirmations and upsells. Guest", "context": "", "use_case": "vector search", "switched_from": "", "story": "Show HN: [Jack The Butler] Open-source, self-hosted AI chatbot for hotels"}, {"id": 737317330, "item_id": 46082333, "url": "https://news.ycombinator.com/item?id=46082333", "by": "mijoharas", "date": "2025-11-28", "stance": "recommend", "quote": "I used sqlite-vec, and was very happy with it.", "excerpt": "I'm interested in the embeddings models suggested. I had some good results with nomic in a small embedding based tool I built. I also heard a few good things about qwen3-embedding, though the latency wasn't great for my usecase so I didn't pursue it much further. Similarly, I used sqlite-vec, and was very happy with it. (if I were already using postgres I'd have gone with that, but this was more of a cli tool). If th", "context": "", "use_case": "vector storage in CLI tool", "switched_from": "", "story": "So you wanna build a local RAG?"}]}], "caveats": [], "who": [], "tags": [], "use_cases": ["vector search", "embedded vector search", "benchmark comparison", "semantic vector search", "vector storage in cli tool"], "compared": [{"slug": "sqlite", "name": "SQLite", "co": 3, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=48819808", "title": "Show HN: Rowboat \u2013 Open-source, local-first alternative to Claude Desktop", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47048731", "title": "Sub-Millisecond RAG on Apple Silicon. No Server. No API. One File", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47000535", "title": "zvec: embedded vector database", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47013583", "title": "Show HN: [Jack The Butler] Open-source, self-hosted AI chatbot for hotels", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46616529", "title": "Ask HN: How are you doing RAG locally?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46080364", "title": "So you wanna build a local RAG?", "mentions": 1}], "sentiment_by_month": {"2025-11": {"recommend": 1}, "2025-12": {}, "2026-01": {"neutral": 1}, "2026-02": {"recommend": 1, "compare": 2}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {"recommend": 1}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 781322550, "item_id": 48832659, "url": "https://news.ycombinator.com/item?id=48832659", "by": "brainless", "date": "2026-07-08", "stance": "recommend", "quote": "SQLite + sqlite-vec + Tantivy + a tiny embedding model will stay as my go to.", "excerpt": "I have a project on very similar lines, https://github.com/brainless/dwata, which I have not been developing for the past few months. I have been meaning to get back to it and I really like what I see on your project page. My aim is to build a truly local app using only tiny/small models. I have had really good results from Qwen 3.5 1B, 4B, etc. Also, Gliner or similar models for different uses. SQLite + sqlite-vec +", "context": "", "use_case": "vector search", "switched_from": "", "story": "Show HN: Rowboat \u2013 Open-source, local-first alternative to Claude Desktop"}, {"id": 752874064, "item_id": 47054629, "url": "https://news.ycombinator.com/item?id=47054629", "by": "threecheese", "date": "2026-02-17", "stance": "compare", "quote": "when I have access to SQLite-vec, qdrant and other embedded friends?", "excerpt": "Tell us more. I had Codex port this to Python so I could wrap my head around it, it\u2019s quite interesting. Why would I use this WAL-check pointing thingamajig when I have access to SQLite-vec, qdrant and other embedded friends?", "context": "", "use_case": "embedded vector search", "switched_from": "", "story": "Sub-Millisecond RAG on Apple Silicon. No Server. No API. One File"}, {"id": 752502961, "item_id": 47031435, "url": "https://news.ycombinator.com/item?id=47031435", "by": "luoxiaojian", "date": "2026-02-15", "stance": "compare", "quote": "I've actually added basic zvec tests to my fork of sqlite-vec", "excerpt": "You're right that we didn't include sqlite-vec in our initial benchmarks\u2014apples-to-apples comparisons are always better. I've actually added basic zvec tests to my fork of sqlite-vec (https://github.com/luoxiaojian/sqlite-vec), so feel free to give it a try. We'll also be publishing a more complete performance comparison in an upcoming blog post\u2014stay tuned!", "context": "", "use_case": "benchmark comparison", "switched_from": "", "story": "zvec: embedded vector database"}, {"id": 752381137, "item_id": 47023821, "url": "https://news.ycombinator.com/item?id=47023821", "by": "anvevoice", "date": "2026-02-15", "stance": "recommend", "quote": "SQLite + sqlite-vec keeping things simple is underrated", "excerpt": "Nice architecture choices \u2014 SQLite + sqlite-vec keeping things simple is underrated. The kernel/adapter pattern is smart for multi-channel support. One area worth exploring: voice as a channel. We've been building voice AI agents for hospitality and service businesses, and the data is striking \u2014 voice interactions convert at ~47% higher rates than text chatbots for things like booking confirmations and upsells. Guest", "context": "", "use_case": "vector search", "switched_from": "", "story": "Show HN: [Jack The Butler] Open-source, self-hosted AI chatbot for hotels"}, {"id": 746121953, "item_id": 46632622, "url": "https://news.ycombinator.com/item?id=46632622", "by": "theahura", "date": "2026-01-15", "stance": "neutral", "quote": "we use SQLite + vec0 + fts5 for semantic and word search", "excerpt": "SQLite works shockingly well. The agents know how to write good queries, know how to chain queries, and can generally manipulate the DB however they need. At nori (https://usenori.ai/watchtower) we use SQLite + vec0 + fts5 for semantic and word search", "context": "", "use_case": "semantic vector search", "switched_from": "", "story": "Ask HN: How are you doing RAG locally?"}, {"id": 737317330, "item_id": 46082333, "url": "https://news.ycombinator.com/item?id=46082333", "by": "mijoharas", "date": "2025-11-28", "stance": "recommend", "quote": "I used sqlite-vec, and was very happy with it.", "excerpt": "I'm interested in the embeddings models suggested. I had some good results with nomic in a small embedding based tool I built. I also heard a few good things about qwen3-embedding, though the latency wasn't great for my usecase so I didn't pursue it much further. Similarly, I used sqlite-vec, and was very happy with it. (if I were already using postgres I'd have gone with that, but this was more of a cli tool). If th", "context": "", "use_case": "vector storage in CLI tool", "switched_from": "", "story": "So you wanna build a local RAG?"}]}