articleX14 Sept 2026
Stop thinking about embeddings
@turbopuffer is a search database built directly on object storage that handles both semantic and full-text search.
Erik Kaunismäki@ErikKaum
x.com
turbopuffer
vector and full-text search built on object storage: fast, 10x cheaper, and extremely scalable
Categories
Articles
All articlesarticleX5 Aug 2026
How to build a 256 TB search index
turbopuffer is a search database built directly on object storage. The system has a single stateful dependency (S3/GCS) and leans heavily into compute/storage disaggregation.
Nathan VanBenschoten@natevanben
x.com
articleturbopuffer.com
Post-training open-weight models for large-scale code search
Applied Compute partnered with turbopuffer to show that a small, specialized search model post-trained to use precomputed search indexes can achieve impressive search quality at a fraction of the cost and latency of frontier models.
turbopuffer.com
More in Search & Retrieval
View all tools
BackSearch
Point-in-time web search and page fetch over a frozen archive. Query the web as it existed on any past date, reproducibly.
CocoIndex
Open-source incremental data framework for AI agents. Keep codebases, docs, and knowledge continuously indexed — fresh context, zero re-processing. Python API.
Exa
The Exa Web search API retrieves the best, realtime data from the web for your AI