turbopuffer
No written verdict yet. Here is what commenters said.
Why people recommend it
“Surprised no one has mentioned Turbopuffer yet [1] which natively supports dense vector similarity and BM25 keyword indexes out of the box”
“Reminds me of the WAND vs MAXSCORE discussion by turbopuffer”
Show 2 more
“i use multiple DBs but the primary ones are turbopuffer and chroma for package search. they are really great”
“Turbopuffer, for example, doesn't use graphs at all, it uses SPFresh.”
Caveats and dissent
“Dashboard was last updated on September 7, it started on September 5”
Often compared with
Who recommends it in their own words
From the makers not counted in the ranking
“turbopuffer will also continuously monitor production recall at the per-shard level”
“Works well for the vast majority of our customers”
Threads where it came up
- ANN v3: 200ms p99 query latency over 100B vectors 3 mentions
- RIP, vector database 1 mention
- Building an open source (turbopuffer alternative)in Rust – Kosha 1 mention
- Celld: Self-hosted, distributed Durable Objects 1 mention
- Ask HN: What Are You Working On? (July 2026) 1 mention
- SQLite is all you need for durable workflows 1 mention
Also written as Turbopuffer. Data: turbopuffer.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 14
“Dashboard was last updated on September 7, it started on September 5”
“Performance on turbopuffer benchmarks”
“the approach is similar to https://turbopuffer.com/blog/object-storage-queue”
I’m still working on a price API for the Counter-Strike 2 market that provides real-time & historical data. Since my last post in February, I’ve gotten to ~25 paying users, which is cool considering it started as a fun project. Sorta a niche within a niche here. The market is distributed across a bunch of 3rd-party marketplaces, and there's no 'simple' API that provides genuinely high-quality data for the few marketp
“Surprised no one has mentioned Turbopuffer yet [1] which natively supports dense vector similarity and BM25 keyword indexes out of the box”
“how ~close is OpenData Vector to Turbopuffer in terms of performance today”
“Our tech stack is React, Typescript, AWS, Pulumi, Postgres, Clickhouse and Turbopuffer.”
“why should I use this instead of turbopuffer?”
“https://turbopuffer.com/customers/cursor”
“Reminds me of the WAND vs MAXSCORE discussion by turbopuffer”
“Vector & BM25 on Turbopuffer.”
Will do a shameless plug here of Skald: https://www.useskald.com/ You'll get the whole RAG/context layer going in an hour. Can self-host too if you prefer. This is really impressive btw!
“i use multiple DBs but the primary ones are turbopuffer and chroma for package search. they are really great”
“Turbopuffer, for example, doesn't use graphs at all, it uses SPFresh.”