#44th of 9 in Vector databases
faiss
C++ library for similarity search and clustering of dense vectors
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 41.2k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Sep 2026
- Language
- C++
39,237 on 25 Mar 202641,153 on 14 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Faiss is a C++ library with Python/numpy wrappers for nearest-neighbor search over dense vectors using L2 distance, dot product or cosine. It offers exact search, HNSW and NSG graph indexes, and compressed indexes that scale to billions of vectors in memory. Some indexes also run on GPU via CUDA or AMD ROCm, with optional NVIDIA cuVS backends.
Who it is for: Engineers embedding vector search in their own C++ or Python applications
Strengths
- Many index types trading off speed, accuracy, memory per vector and training time
- Compressed and binary indexes handle sets that do not fit in RAM uncompressed
- GPU indexes (CUDA, ROCm) replace CPU ones, single or multi-GPU
- Only hard dependency is a BLAS implementation; MIT licensed
Weaknesses
- Library only: no server, REST API, auth or built-in persistence service
- Vectors are identified by integers; metadata filtering must be built separately
- Choosing and tuning an index type requires understanding the trade-offs
- Builds with cmake; prebuilt packages are listed for Anaconda only
What it needs
- GPU optional
- Needs BLAS, CUDA or ROCm (optional), NVIDIA cuVS (optional)
Head to head
Also in Vector databases
See all 9| Rank | Project | Score |
|---|---|---|
| 1 | MilvusDistributed vector database with dense, sparse and hybrid search at scale | 80 out of 100 |
| 2 | MeilisearchRust search engine API with full-text, vector and hybrid search | 74 out of 100 |
| 3 | QdrantRust vector database with payload filtering, REST and gRPC | 66 out of 100 |
| #5 | HelixDBRust graph database with native vector and BM25 search | 61 out of 100 |
| #6 | WeaviateGo vector database with built-in vectorizers, hybrid search and RAG | 60 out of 100 |