facebookresearch/faiss
Dense vector similarity search and clustering library
- Chart
- Not on a chart right now
- Stars
- 41.8k
What it is
Faiss is a library for efficient similarity search and clustering of dense vectors, including datasets larger than RAM. It is written in C++ with Python/numpy wrappers and optional GPU implementations.
Who it is for
AI and machine learning engineers and researchers building large-scale vector search or clustering systems.
Why it is trending
It gained 626 stars today, reaching 41,766 total stars, shortly after its v1.16.0 release on November 10, 2026.
Main features
- Similarity search using L2 distance, dot product, and cosine similarity
- Compressed vector representations and graph indexes such as HNSW and NSG
- Single and multi-GPU support via CUDA, AMD ROCm, and optional cuVS
- Supporting tools for evaluation and parameter tuning
Summarized on November 17, 2026 from the README and repository data. It can be wrong; check the source before relying on it. Report a wrong summary