turbopuffer

Serverless vector and full-text search database that stores data on object storage for low-cost, low-latency retrieval.

Visit turbopuffer.com ↗Pricing & calculator Alternatives

Works with AI agents:llms.txt

Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

turbopuffer is a hosted search database for vector search and BM25 full-text search. All data lives in object storage (such as S3 or GCS), with NVMe SSD and memory used only as a cache, which keeps very large or very numerous indexes cheap to run.

Data is grouped into namespaces, each with its own prefix on object storage; a common pattern is one namespace per customer. You upsert documents with an ID, attributes and vectors. Each write lands in a write-ahead log on object storage, committing at most once per second per namespace, and is indexed asynchronously; not-yet-indexed data is still searched. The first query to a namespace reads straight from object storage and is slower, after which it is served from cache. Official clients cover Python, TypeScript, Go, Java and Ruby. It can also embed text for you if you name a model on an attribute.

Useful for a small team: metadata filters combined with vector or full-text ranking; hybrid search; branching, which clones a namespace copy-on-write in constant time; and cross-region namespace copies for backup. Queries are strongly consistent by default. It runs in shared regions on AWS and GCP plus one Azure region, with single-tenant and bring-your-own-cloud options for enterprise customers.

Its stated limits: writes take up to about 200 ms to commit, cold queries take hundreds of milliseconds, there are no automated backups or general transactions, and reranking is left to your code. It is not offered as open source or a self-hosted package.

Where it fits

Vector Database · Managed vector storeVery large or many-tenant indexes where storing everything on object storage keeps cost down.Trade-off: No free tier (paid plans have a monthly minimum), and it's cloud-only.

How turbopuffer itself is built

3 tools, from its own code, website and Product Hunt page.

Postmark

Resend

Vercel

Who uses it

8 makers' products, each linked to the source that shows it, and 7 open-source projects that declare it in their code.

Customer story 8Subprocessor list 1Declared in code 7How evidence is collected →

Sort

LinearIssue tracking and project management tool for software teams, with a focus on speed and…Vector DatabaseCustomer story +1 · source ↗

falServerless GPU platform providing APIs for image, video, audio and 3D generative models…Vector DatabaseCustomer story · source ↗

Mem0Mem0 enables AI agents & apps to continuously learn from past user interactions, enhanci…Vector DatabaseCustomer story · source ↗

PlayerzeroPlayerZero builds an engineering world model so SRE, QA, and support teams resolve incid…Vector DatabaseCustomer story · source ↗

ReadwiseEasily revisit and learn from your highlights and annotations.Vector DatabaseCustomer story · source ↗

PylonPylon lets humans and AI agents collaborate on customer work, investigating, resolving,…Vector DatabaseCustomer story · source ↗

KeplerVector DatabaseCustomer story · source ↗

LegoraVector DatabaseCustomer story · source ↗

puppyone-cloud Context drive for your AI agentsVector DatabaseIn its code · source ↗

Mastra TypeScript framework for building AI agents, workflows, and RAG applications with memory…Vector DatabaseIn its code · source ↗

agentset The open-source RAG platform: built-in citations, deep research, 22+ file formats, parti…Vector DatabaseIn its code · source ↗

Dub Open-source link management and attribution platform for short links, conversion trackin…Vector DatabaseIn its code · source ↗

cocoindex Incremental engine for long horizon agents 🌟 Star if you like it!Vector DatabaseIn its code · source ↗

honcho Memory library for building stateful agentsVector DatabaseIn its code · source ↗

Vision-Agents Open Vision Agents by Stream. Build voice and vision agents quickly with any model or vi…Vector DatabaseIn its code · source ↗

Open source: a project that declares turbopuffer as a dependency in its public code — verifiable, but not necessarily a live product.

Loved and watch-outs

Themes that recur in makers' words and Hacker News comments, each linked to what it summarises.

Most loved

Storing vectors on object storage with a cache in front keeps large-scale search cheap. HN HN 2 HN 3 turbopuffer.com
Handles hundreds of millions to billions of documents, a common next step when pgvector runs out. turbopuffer.com turbopuffer.com 2 turbopuffer.com 3 HN
Operationally simple, with BM25, attribute filtering, recall tuning and consistency options built in. HN HN 2 HN 3 HN 4
Teams ship multi-tenant semantic search within days and cut write costs. turbopuffer.com turbopuffer.com 2

Watch-outs

There is no offline local emulator, so development and CI must hit the hosted service. HN HN 2 HN 3
Its paid-only pricing floor is steep for small projects, which often stay on pgvector instead. HN HN 2

Reliability and open issues

Incidents on its status page4 in the last 90 days, 4 major · 25+ in the last year

critical Dashboard outage Sep 2026
major Elevated rate of 5xx in gcp-us-central1 Sep 2026
critical Outage in gcp-us-southeast1 Aug 2026

From its own status page, 2026-10-02. Vendors decide what they post; one page can cover several products.

Alternatives to turbopuffer

All alternatives by situation →

LanceDBAn embedded vector database that stores vectors and data as files on local disk or object storage, with no server to run.Open sourceFree tier3 makers · vector database Compare with turbopuffer →

PineconeA fully hosted index with nothing to operate, sized by usage.Free tier55 makers · vector database Compare with turbopuffer →

QdrantHeavy metadata filtering alongside vector search, self-hosted from one binary or on its managed cloud.Open sourceFree tier18 makers · vector database Compare with turbopuffer →

ChromaPrototyping RAG on your laptop with a pip or npm install and no server to run.Open sourceFree tier13 makers · vector database Compare with turbopuffer →

pgvectorApps already on Postgres that want vector search in the same database, joined with normal tables.Open sourceFree tier

WeaviateHybrid search that mixes keyword and vector results, with built-in modules that can create embeddings for you.Open sourceFree tier16 makers · vector database

MongoDBApps already on MongoDB Atlas that want vector search on the same documents, with no second store to sync.Self-hostableFree tier

Questions makers ask about turbopuffer

Which languages have official clients?

Python, TypeScript, Go, Java and Ruby. Everything goes through a JSON HTTP API with a public OpenAPI specification, so other languages can call it directly. source ↗

Why is the first query to a namespace slow?

An uncached namespace is read straight from object storage (about 874 ms at p50 for 1M documents), then cached on SSD so later queries take around 14 ms. You can send a warm-cache hint ahead of latency-sensitive traffic. source ↗

Are writes visible to queries right away?

Usually. A write is durable on object storage when the API returns and queries are consistent by default, but once a namespace has more than 128 MiB of unindexed writes, newer writes stay invisible until indexing catches up. source ↗

Where is my data stored, and is it SOC 2 / GDPR / HIPAA ready?

Data stays in the region you choose. turbopuffer is audited for SOC 2 Type 2, provides a DPA for GDPR and CCPA, and signs a BAA for HIPAA on request. source ↗

Does it back up my data?

There are no automated backups. You schedule server-side copies of namespaces to another region or cloud with copy_from_namespace, or rebuild from your primary data source. source ↗

Can I export my data?

Yes. You page through every document in a namespace with the query API, ordering by ID and advancing a filter on the last ID seen. source ↗

Is there a tool to migrate from another vector database?

No migration tooling is offered; you write the data in through the API yourself. Enterprise customers can get help from its solutions engineers. source ↗

Can I run it in my own cloud account?

Yes, as a bring-your-own-cloud deployment inside your VPC on AWS, GCP or Azure, or as a dedicated single-tenant cluster, arranged by contacting turbopuffer. source ↗

Is turbopuffer free?

No permanent free tier; paid use starts at $16/mo minimum usage. source ↗

Is turbopuffer open source or self-hostable?

Not open source, and hosted only.

Can AI coding agents work with turbopuffer?

It serves an llms.txt docs index.

Who uses turbopuffer?

8 makers' products we track, each with a source, and 7 open-source projects declare it in their code. source ↗