turbopuffer
Hacker ApprovedRanked 4 of 10 vector databases by recommenders
Hosted database for vector and keyword search at large scale, recommended for its low cost and fast queries on very large datasets.
Hosted database for vector and keyword search at large scale, recommended for its low cost and fast queries on very large datasets.
15 people gave an opinion
- recommend it
- 13
- criticize it
- 2
- approval share
- 87%
Recommended in 8 of 13 months
- November 2025: recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: not recommended
- July 2026: recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 13 people recommend itNeeds 10 or more, met.
- 6.5 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 8 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Built-in vector and BM25 keyword search
“natively supports dense vector similarity and BM25 keyword indexes out of the box”
Comment from 29 May 2026 in “SQLite is all you need for durable workflows” “do pretty much what Turbopuffer did for text and vector data”
Comment from 2 Oct 2026 in “Cloudflare K2: serverless event streams” Low cost and latency at scale
“something like turbopuffer can do wonders for your costs”
Comment from 12 May 2026 in “Why senior developers fail to communicate their expertise” “And they recently got 200ms latency on 100B vectors.”
Comment from 11 Nov 2025 in “Scaling HNSWs” Admired site design and team
“Web design is inspired/somewhat taken from turbopuffer's site, since I really liked it.”
Comment from 13 Jul 2026 in “Ask HN: What Are You Working On? (July 2026)” “Turbopuffer team really cooking!”
Comment from 22 Jan 2026 in “ANN v3: 200ms p99 query latency over 100B vectors”
Other vector databases people recommend
The four most recommended other vector databases, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Qdrant | 22 | 3 | 88% | 10 | — | Approved |
| Chroma | 17 | 5 | 77% | 7 | — | Approved |
| sqlite-vec | 17 | 3 | 85% | 7 | — | Approved |
| turbopufferThis page | 13 | 2 | 87% | 8 | — | Approved |
| LanceDB | 12 | 2 | 86% | 7 | — | Approved |
What people said
10 of the 16 comments that mention it, newest first. Each links to the original comment.
“do pretty much what Turbopuffer did for text and vector data”
“noticeably sluggish on my m3 max”
“Web design is inspired/somewhat taken from turbopuffer's site, since I really liked it.”
“natively supports dense vector similarity and BM25 keyword indexes out of the box”
“something like turbopuffer can do wonders for your costs”
“Without that it's unfortunately a non starter”
“Often not a dealbreaker, actually! We can spin up new tpuf regions and procure dedicated interconnects to minimize latency to the on-prem network on request”
“Works well for the vast majority of our customers”
“Turbopuffer team really cooking!”
“And they recently got 200ms latency on 100B vectors.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.