{"slug": "lancedb", "name": "LanceDB", "category": "databases", "category_name": "Databases", "description": "", "recommenders": 5, "commenters": 13, "warners": 0, "score": 6.416, "rising": -0.31, "first": "2025-12-30", "latest": "2026-08-20", "why": "the embedded lancedb is convenient and has benchmarks", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 5, "neutral": 7, "compare": 1, "warn": 0}, "spark": [0, 0, 2, 0, 1, 0, 0, 0, 1, 1, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "the embedded lancedb is convenient and has benchmarks", "kind": "", "icon": true, "domain": null, "github_repo": "github.com/lancedb/lancedb", "official_url": "https://lancedb.com", "pricing": "", "aliases": ["LanceDB"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 790095232, "item_id": 49380952, "url": "https://news.ycombinator.com/item?id=49380952", "by": "60secs", "date": "2026-08-20", "stance": "recommend", "quote": "Check out https://github.com/lancedb/lancedb too", "excerpt": "Check out https://github.com/lancedb/lancedb too", "context": "", "use_case": "database", "switched_from": "", "story": "I Analyzed 163K Lines of Kuzu's Codebase. Here's Why Apple Wanted It"}, {"id": 781752144, "item_id": 48859509, "url": "https://news.ycombinator.com/item?id=48859509", "by": "laminarflow027", "date": "2026-07-10", "stance": "recommend", "quote": "Very cool, gotta try this out!", "excerpt": "Very cool, gotta try this out! Curious, how does it handle blob data (e.g., images) -> Is there a way to display the image blobs in the widget too? Kind of like how Hugging Face displays Lance blobs in their dataset viewer: https://huggingface.co/datasets/lance-format/handwriting-ocr Either way, thanks for sharing!", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: LanceDB VS Code Extension"}, {"id": 755526113, "item_id": 47220382, "url": "https://news.ycombinator.com/item?id=47220382", "by": "auvira_systems", "date": "2026-03-02", "stance": "recommend", "quote": "Have you looked into adding a local vector DB (like LanceDB or similar)", "excerpt": "I love seeing more 'Local-First' tools hitting the front page. We\u2019ve been moving our own project (a financial IDE) toward a purely local-first architecture, and the biggest challenge is always balancing zero-cloud with useful features. Using Claude Code as the base is a clever move because it already has the context of the filesystem. Have you looked into adding a local vector DB (like LanceDB or similar) to give 'pa", "context": "building a financial IDE", "use_case": "local long-term memory", "switched_from": "", "story": "Show HN: I turned Claude Code into a personal assistant"}, {"id": 746151344, "item_id": 46634459, "url": "https://news.ycombinator.com/item?id=46634459", "by": "someguyiguess", "date": "2026-01-15", "stance": "recommend", "quote": "I am doing something very similar also using lancedb", "excerpt": "Woah. I am doing something very similar also using lancedb https://github.com/nicholaspsmith/lance-context Mine is much more basic than yours and I just started it a couple of weeks ago.", "context": "", "use_case": "Vector database for RAG", "switched_from": "", "story": "Ask HN: How are you doing RAG locally?"}, {"id": 746065649, "item_id": 46629103, "url": "https://news.ycombinator.com/item?id=46629103", "by": "autogn0me", "date": "2026-01-14", "stance": "recommend", "quote": "the embedded lancedb is convenient and has benchmarks", "excerpt": "https://github.com/ggozad/haiku.rag/ - the embedded lancedb is convenient and has benchmarks; uses docling. qwen3-embedding:4b, 2560 w/ gpt-oss:20b.", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: How are you doing RAG locally?"}]}], "caveats": [], "who": [{"by": "auvira_systems", "context": "building a financial IDE", "url": "https://news.ycombinator.com/item?id=47220382", "date": "2026-03-02"}], "tags": [], "use_cases": ["vector storage", "database", "vector similarity search", "vector database", "local long-term memory", "embedding index"], "compared": [{"slug": "duckdb", "name": "DuckDB", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "claude-code", "name": "Claude Code", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [{"id": 758198432, "item_id": 47387402, "url": "https://news.ycombinator.com/item?id=47387402", "by": "BillCorOnBass", "date": "2026-03-15", "stance": "neutral", "quote": "LanceDB long-term memory", "excerpt": "Three weeks ago I brought two AI entities online. They've been running continuously since \u2014 observing, thinking, acting, reflecting, writing journals, running experiments. They share a long-term memory commons, a \"corpus callosum\" built in code, so what one learns the other can recall. The part I think is actually novel: a Portable Identity Document (.pid) format that separates an entity's mind from its body. The min", "context": "", "use_case": "Agent long-term memory", "switched_from": "", "story": "Show HN: I built two AI entities with shared memory and a portable identity spec"}], "threads": [{"url": "https://news.ycombinator.com/item?id=46616529", "title": "Ask HN: How are you doing RAG locally?", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=49319011", "title": "I Analyzed 163K Lines of Kuzu's Codebase. Here's Why Apple Wanted It", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49233423", "title": "Ask HN: What are you working on? (August 2026)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48859354", "title": "Show HN: LanceDB VS Code Extension", "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=47966254", "title": "Full-Text Search with DuckDB", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {"compare": 1}, "2026-01": {"neutral": 2, "recommend": 2}, "2026-02": {"neutral": 2}, "2026-03": {"recommend": 1}, "2026-04": {"neutral": 1}, "2026-05": {}, "2026-06": {}, "2026-07": {"neutral": 1, "recommend": 1}, "2026-08": {"neutral": 1, "recommend": 1}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 790095232, "item_id": 49380952, "url": "https://news.ycombinator.com/item?id=49380952", "by": "60secs", "date": "2026-08-20", "stance": "recommend", "quote": "Check out https://github.com/lancedb/lancedb too", "excerpt": "Check out https://github.com/lancedb/lancedb too", "context": "", "use_case": "database", "switched_from": "", "story": "I Analyzed 163K Lines of Kuzu's Codebase. Here's Why Apple Wanted It"}, {"id": 787847377, "item_id": 49240461, "url": "https://news.ycombinator.com/item?id=49240461", "by": "idontneedcoffee", "date": "2026-08-10", "stance": "neutral", "quote": "lancedb for some basic cossim search", "excerpt": "I divide my unstructured universe into workspaces, each workspace is a self-contained shareable/moveable soon-to-be-containerized runtime running an in-process LMDB with roaring bitmaps and (for now, S2-like hilbert space projections will replace it soon) lancedb for some basic cossim search. You configure your data sources per Workspace - imap, files, s3, soon slack(bc I use it), on top you create a classically-look", "context": "", "use_case": "vector similarity search", "switched_from": "", "story": "Ask HN: What are you working on? (August 2026)"}, {"id": 781752144, "item_id": 48859509, "url": "https://news.ycombinator.com/item?id=48859509", "by": "laminarflow027", "date": "2026-07-10", "stance": "recommend", "quote": "Very cool, gotta try this out!", "excerpt": "Very cool, gotta try this out! Curious, how does it handle blob data (e.g., images) -> Is there a way to display the image blobs in the widget too? Kind of like how Hugging Face displays Lance blobs in their dataset viewer: https://huggingface.co/datasets/lance-format/handwriting-ocr Either way, thanks for sharing!", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: LanceDB VS Code Extension"}, {"id": 781456130, "item_id": 48841008, "url": "https://news.ycombinator.com/item?id=48841008", "by": "karmakaze", "date": "2026-07-08", "stance": "neutral", "quote": "AnythingLLM has LanceDB out of the box", "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": "Vector database", "switched_from": "", "story": "Turning a pile of documents into a searchable useable knowledge base"}, {"id": 767514098, "item_id": 47969631, "url": "https://news.ycombinator.com/item?id=47969631", "by": "dkdcdev", "date": "2026-04-30", "stance": "neutral", "quote": "presume it\u2019s like LanceDB and MotherDuck", "excerpt": "I believe as it states that\u2019s only for the core extensions listed here: https://duckdb.org/docs/current/core_extensions/overview all are by the DuckDB team except three third-party owners. I\u2019m unfamiliar with Vortex, but presume it\u2019s like LanceDB and MotherDuck with a serious company behind it. and presumably the DuckDB team trusts them not to ship malware in their extension I think it\u2019s a UX trade off that benefits ", "context": "", "use_case": "", "switched_from": "", "story": "Full-Text Search with DuckDB"}, {"id": 755526113, "item_id": 47220382, "url": "https://news.ycombinator.com/item?id=47220382", "by": "auvira_systems", "date": "2026-03-02", "stance": "recommend", "quote": "Have you looked into adding a local vector DB (like LanceDB or similar)", "excerpt": "I love seeing more 'Local-First' tools hitting the front page. We\u2019ve been moving our own project (a financial IDE) toward a purely local-first architecture, and the biggest challenge is always balancing zero-cloud with useful features. Using Claude Code as the base is a clever move because it already has the context of the filesystem. Have you looked into adding a local vector DB (like LanceDB or similar) to give 'pa", "context": "building a financial IDE", "use_case": "local long-term memory", "switched_from": "", "story": "Show HN: I turned Claude Code into a personal assistant"}, {"id": 755185010, "item_id": 47199063, "url": "https://news.ycombinator.com/item?id=47199063", "by": "ravila4", "date": "2026-02-28", "stance": "neutral", "quote": "index embeddings in LanceDB and do semantic search", "excerpt": "Nice! I rely on Obsidian a lot for syncing knowledge while working with Claude agents, such as storing research and daily logs to catch up on the prior day\u2019s work. It already works quite well with a custom skill that I build, but this may make the workflow smoother. I also built a cli tool to index embeddings in LanceDB and do semantic search. It helps agents create better internal links between notes. https://github", "context": "", "use_case": "embedding index", "switched_from": "", "story": "Obsidian Sync now has a headless client"}, {"id": 751793281, "item_id": 46987080, "url": "https://news.ycombinator.com/item?id=46987080", "by": "willtemperley", "date": "2026-02-12", "stance": "neutral", "quote": "relatively simple to set up an Arrow Flight endpoint working with LanceDB", "excerpt": "It's interesting to look at the relationship between this and Apache Arrow. \"The data types generally have a 1-1 correspondence with the Apache Arrow data types.\" [1] So it would probably be relatively simple to set up an Arrow Flight endpoint working with LanceDB. [1] https://lance.org/format/table/#manifest", "context": "", "use_case": "", "switched_from": "", "story": "Lance table format explained with simple animations"}, {"id": 746151344, "item_id": 46634459, "url": "https://news.ycombinator.com/item?id=46634459", "by": "someguyiguess", "date": "2026-01-15", "stance": "recommend", "quote": "I am doing something very similar also using lancedb", "excerpt": "Woah. I am doing something very similar also using lancedb https://github.com/nicholaspsmith/lance-context Mine is much more basic than yours and I just started it a couple of weeks ago.", "context": "", "use_case": "Vector database for RAG", "switched_from": "", "story": "Ask HN: How are you doing RAG locally?"}, {"id": 746143523, "item_id": 46633970, "url": "https://news.ycombinator.com/item?id=46633970", "by": "amscotti", "date": "2026-01-15", "stance": "neutral", "quote": "with LanceDB for the vector database", "excerpt": "More of a proof of concept to test out ideas, but here's my approach for local RAG, https://github.com/amscotti/local-LLM-with-RAG Using Ollama for the embeddings with \u201cnomic-embed-text\u201d, with LanceDB for the vector database. Recently updated it to use \u201cagentic\u201d RAG, but probably not fully needed for a small project.", "context": "", "use_case": "Vector storage", "switched_from": "", "story": "Ask HN: How are you doing RAG locally?"}, {"id": 746065649, "item_id": 46629103, "url": "https://news.ycombinator.com/item?id=46629103", "by": "autogn0me", "date": "2026-01-14", "stance": "recommend", "quote": "the embedded lancedb is convenient and has benchmarks", "excerpt": "https://github.com/ggozad/haiku.rag/ - the embedded lancedb is convenient and has benchmarks; uses docling. qwen3-embedding:4b, 2560 w/ gpt-oss:20b.", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: How are you doing RAG locally?"}, {"id": 745506610, "item_id": 46594163, "url": "https://news.ycombinator.com/item?id=46594163", "by": "devrob", "date": "2026-01-12", "stance": "neutral", "quote": "uses some local models and lanceDB", "excerpt": "I'm trying to build a simple, local, and semantic code + context search for coding agents like Claude Code. I noticed that when trying to work with Claude Code I burned my token allocation really quickly and with parallel agents, no better. But when I looked at the other repos things felt really complex, for me at least. I call it \"contextd\" and imagine it kind of like a context daemon you can always query in your re", "context": "", "use_case": "Vector storage", "switched_from": "", "story": "Ask HN: What Are You Working On? (January 2026)"}, {"id": 743072673, "item_id": 46442042, "url": "https://news.ycombinator.com/item?id=46442042", "by": "jtbaker", "date": "2025-12-30", "stance": "compare", "quote": "LanceDB has a similar mechanism for operating on remote vector embeddings/text search.", "excerpt": "Look into using duckdb with remote http/s3 parquet files. The parquet files are organized as columnar vectors, grouped into chunks of rows. Each row group stores metadata about the set it contains that can be used to prune out data that doesn\u2019t need to be scanned by the query engine. https://duckdb.org/docs/stable/guides/performance/indexing LanceDB has a similar mechanism for operating on remote vector embeddings/te", "context": "", "use_case": "Vector and text search", "switched_from": "", "story": "Show HN: Hacker Book \u2013 All the HN Belong to You 2006 \u2013 2025"}]}