Updated

Faiss

Meta's open-source library for fast similarity search over vectors held in memory, on CPU or GPU.

61 open-source projects declare Faiss in their code; no maker's live product we track uses it yet.

Open sourceSelf-hostableFree tier

Profile checked

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

How makers use Faiss

What Faiss is used for

Vector Database · Embedded / local-first →A fast in-memory vector index library for research, batch jobs and apps that load their index at startup.Trade-off: A library, not a database — no metadata filtering service, persistence or updates beyond what you build.
Pinecone53Qdrant18Weaviate16Chroma12turbopuffer8Faiss0Makers' products on each, for vector database

Faiss vs the alternatives makers chose

OptionMakers' productsFree forAt 10,000 usersOpen source
Pinecone53 50%~3,300 users$113/mo · StandardNo
Qdrant18 17%~1,000 users$103/mo · Standard (3 nodes, 0.5 vCPU / 4 GiB each)Yes
Weaviate16 15%~1,000 users$253/mo · FlexYes
Chroma12 11%~760 users$51/mo · StarterYes
turbopuffer8 7%None$21/mo · LaunchNo
LanceDB3 3%——Yes
Faiss0 0%——Yes

For vector database: how many of the 107 makers' products we know the vector database of chose each option, and what each costs at 10,000 users.

Costs are the cheapest plan that fits, from each vendor's pricing page, at the usage our stack planner assumes for a product with that many users. Free for: the users its cheapest plan a business can use stays free for.

When to use Faiss, and when not

Something else fits better if

  • You already use Postgres and have up to a few million vectors: pgvector.
  • You're prototyping retrieval on your laptop, or want vectors in files with no server: Chroma.
  • You want a hosted index with nothing to operate: Pinecone or turbopuffer.
  • You need an open-source store with heavy filtering or hybrid search, self-hosted or managed: Qdrant or Weaviate.
From each decision's guide, written from what makers' products chose and why.

Reliability and open issues

The most wanted open issue on GitHub has 21 👍.

Most wanted on GitHub

Open on 2026-10-04 in facebookresearch/faiss, with activity in the last year — issues and feature requests by 👍.

Who uses it

No maker's live product on record yet, and 61 open-source projects that declare it in their code.

We haven't found a maker's live product that uses Faiss yet — only the open-source projects below, which declare it in their code.

Aix-DB
Aix-DBAix-DB 基于 LangChain/LangGraph 框架,结合 MCP Skills 多智能体协作架构,实现自然语言到数据洞察的端到端转换。Vector DatabaseIn its code · source ↗

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

What its projects tell coding agents

11 of the 32 open-source products built with Faiss that were worked on in the last 180 days keep instruction files for coding agents — 34%, against 53% of all the projects we read. AGENTS.md is in 7, CLAUDE.md in 7.

1,253words in the median file
uvthe package manager most named, in 5 of 10 files
90%say how to test a change
Named more in these files than in other projects' — in how many of the 10:
What AGENTS.md files say about other tools →What open-source products tell their coding agents →

Further reading

Questions makers ask about Faiss

What are the alternatives to Faiss?

For vector database, the other options makers' products we track chose most are Pinecone (53), Qdrant (18), Weaviate (16), Chroma (12), turbopuffer (8), LanceDB (3). Open source or self-hostable among them: Qdrant, Weaviate, Chroma, LanceDB. Each alternative, with the situation it fits, is on the Faiss alternatives page.

Is Faiss free?

Yes — it is free, open-source software.

Is Faiss open source or self-hostable?

Open source, and you can self-host it. source ↗

Can AI coding agents work with Faiss?

No llms.txt, official MCP server or CLI found yet.

Who uses Faiss?

No maker's live product we track yet; 61 open-source projects declare it in their code. source ↗