Top all-time · #1865
turbopuffer
Company blog · turbopuffer.com/blog · on HN as Sirupsensystemsdata
turbopuffer is the company blog at turbopuffer.com, writing about systems and data. Since 2023, 40 different Hacker News readers have linked it 55 times, most often “A Serverless Vector Database”. It is still writing: the last post was on 2026-10-26, and you can follow it by feed.
Too few sampled comments (20) to say how often HN recommends it.?
Why HN links it
HN readers link turbopuffer's site, docs and blog for its S3-backed vector search, architecture posts and benchmarks. Commenters often cite it as an alternative to other vector databases.
Summarised by Claude from a sample of 20 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
vector and full-text search built on object storage: fast, 10x cheaper, and extremely scalable
Most-linked posts?
- A Serverless Vector Database10 people · 11 mentions · first linked 2023-10-04
- Turbopuffer: Fast search on object storage5 people · 6 mentions · first linked 2024-07-07
- ANN v3: 200ms p99 query latency over 100B vectors4 people · 5 mentions · first linked 2026-01-21
- A distributed queue in a single JSON file on object storage4 people · 4 mentions · first linked 2026-02-12
- Vectorized MAXSCORE over WAND, especially for long LLM-generated queries4 people · 4 mentions · first linked 2025-12-12
- How to ship a database every day3 people · 3 mentions · first linked 2026-08-14
- RIP, vector database3 people · 3 mentions · first linked 2026-09-30
- Rust zero-cost abstractions vs. SIMD2 people · 2 mentions · first linked 2026-03-03
What Hacker News says?
Your vector store should let you store the original text as well as metadata, where you can store the version. For e.g. turbopuffer lets you filter on attributes https://turbopuffer.com/docs/query#filtering
Comment linking /docs/query
on “Production RAG: what I learned from processing 5M+ documents”Submitted RIP, vector database as a story · 405 points
HN discussionTo avoid any dependencies other than object storage, we've been making use of this in our database (turbopuffer.com) for consensus and concurrency control since day one. Been waiting for this since the day we launched on Google Cloud Storage ~1 year ago. Our bet that S3 would get it in a reasonable time-frame worked out! https://turbopuffer.com/blog/turbopuffer
Comment linking /blog/turbopuffer
on “Amazon S3 Adds Put-If-Match (Compare-and-Swap)”Submitted Turbopuffer: Fast search on object storage as a story · 379 points
HN discussionDashboard was last updated on September 7, it started on September 5. Bug? Or no progress? It's linked in the blog post so would expect it to work: https://turbopuffer.com/v3
Comment linking /v3
on “RIP, vector database”Submitted RIP, Vector Database as a story · 10 points
HN discussionWebsite is open source at https://github.com/TN1ck/tn1ck.com . Tech stack is literally just a Next.js website and I write my articles in React. I tried other things before e.g. Jekyll, but I found that dynamic content is really hard to do there, annoyingly hard. I keep it super simple and don't do "the proper way" of things at times (e.g. the blog index is manually done by me). But that keeps it simple & independent…
Comment linking /
on “Generating sudokus for fun and no profit”Submitted Turbopuffer: Continuous Recall Measurement as a story · 6 points
HN discussion> My other mild criticism is in the discussion on TigerBeetle’s consensus: yes, it seems quite clever and has no other dependencies, but it’s also not trying to deal with large rows. When you can fit 8,190 transactions into a 1 MiB packet that takes a single trip to be delivered, you can probably manage what would be impossible for a traditional RDBMS. Isn't that the point? They're saying to separate out transaction…
Comment linking /
on “TigerBeetle is a most interesting database”Submitted RIP, Vector Database as a story · 5 points
HN discussionTurbopuffer is awesome, really recommend it. Also they have extra features like automatic recall tuning based on you data, option to choose read after write guarantees (trading latency for consistency or vice versa), BM25 search, filtering on the filed and many more. Really recommend to check them out if you need a vector DB. I tried qdrant and zilli cloud solutions and in terms of operational simplicity turbopuffer…
Comment linking /docs/query
on “Will Amazon S3 Vectors kill vector databases or save them?”Submitted Training SID-1 to beat GPT-5 at search with 1k+ QPS RL as a story · 5 points
HN discussionAnyone interested in this space should look at https://turbopuffer.com - I think they were first to market with S3 backed vector storage, and a good memory cache in front of it.
Comment linking /
on “Will Amazon S3 Vectors kill vector databases or save them?”Submitted How to ship a database every day as a story · 4 points
HN discussionAt very high scale, there's less usage of graphs. Or there's a set of clustering on top of graphs. Graphs can be complex to build and rebalance. Graph-like data structures with a thing, then a pointer out to another thing, aren't that cache friendly. Add to that, people almost always want to *filter* vector search results. And this is a huge blindspot for consumers and providers. It's where the ugly performance surp…
Comment linking /docs/vector
on “Scaling HNSWs”Submitted Vectorized MAXSCORE over WAND, especially for long LLM-generated queries as a story · 4 points
HN discussionWhat a surprise that you are also a reader of books rather than other content: https://www.goodreads.com/user/show/7288759-vasco Reading a book is arguably easier than reading technical content or other articles, because they don't tend to be as information dense. I prefer reading things like this: https://commoncog.com/becoming-data-driven-in-business/ But someone might like reading documentation for e.g. databases…
Comment linking /docs
on “Letting go of the idea of keeping up”Submitted A distributed queue in a single JSON file on object storage as a story · 3 points
HN discussionIt seems that some of the goals and functionalities of Nixiesearch overlap with those of Turbopuffer [^1], though the latter is only focusing on vector search. I also resonate that search engine should be stateless and affordable to deploy for everyone. [1]: https://turbopuffer.com/blog/turbopuffer
Comment linking /blog/turbopuffer
on “Nixiesearch: Running Lucene over S3, and why we're building a new search engine”Submitted ANN v3: 200ms p99 query latency over 100B vectors as a story · 2 points
HN discussionIt works great. We’ve had SPANN in production since October of 2023 at https://turbopuffer.com/
Comment linking /
on “Spann: Highly-Efficient Billion-Scale Approximate Nearest Neighbor Search (2021)”Submitted ANN v3: 200ms p99 query latency over 100B vectors as a story · 2 points
HN discussionWe use pinecone and it is not ideal, looking at https://turbopuffer.com/ now. They look quite promising :)
Comment linking /
on “Show HN: I put PubMed in a vector DB”Submitted ANN v3: 200ms p99 query latency over 100B vectors as a story · 2 points
HN discussionThis feels similar to TurboBuffer, which is also built on top of S3 storage. TurboBuffer has been a leader in this space, powering vector search for major companies like Cursor, Linear, and Notion. It seems AWS is leveraging its strong S3 brand to compete directly in the vector database market. For more context, check out the TurboBuffer architecture docs and Notion’s presentation from the Data Council: https://turb…
Comment linking /docs/architecture
on “Amazon S3 Vectors”Submitted Designing inverted indexes in a KV-store on object storage as a story · 2 points
HN discussionSurprised no one has mentioned Turbopuffer yet [1] which natively supports dense vector similarity and BM25 keyword indexes out of the box [1]. https://turbopuffer.com/
Comment linking /
on “SQLite is all you need for durable workflows”Submitted Vectorized MAXSCORE over WAND, especially for long LLM-generated queries as a story · 2 points
HN discussionCopy aside I think the approach is similar to https://turbopuffer.com/blog/object-storage-queue The quiet improvements to S3 over the last 3 years like conditional puts unlocked a lot of use cases not previously feasible
Comment linking /blog/object-storage-queue
on “Celld: Self-hosted, distributed Durable Objects”Submitted Native filtering for high-recall vector search as a story · 2 points
HN discussion
