nmslib/nmslib

Health v2 · maintenance only

Adoption not part of the score

3588 stars · 461 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

NMSLIB is a cross-platform C++ similarity search library with Python bindings for efficient k-nearest-neighbor search in generic and non-metric spaces. It also serves as a toolkit for evaluating approximate k-NN methods and includes the original HNSW implementation.

Use cases

• find nearest neighbors in high-dimensional vector embeddings
• approximate k-NN search for non-metric distance functions
• benchmark similarity search algorithms
• build vector search for semantic search or recommendations
• search with custom distance metrics in C++ or Python

When to choose

• you need fast approximate nearest-neighbor search with many distance/space options
• you need non-metric similarity search support
• you want to benchmark k-NN methods
• you want a dependency-free C++ core with Python bindings

When to avoid

• you only need plain cosine/L2 HNSW and prefer a simpler header-only library (use hnswlib)
• you need a managed vector database with filtering and persistence
• you need actively developed features or frequent updates

Facets

library · maturity maintenance

search-engine benchmarking machine-learning machine-learning databases cpp python windows cross-platform knn-search similarity-search ann non-metric-spaces hnsw vector-search nearest-neighbor algorithms search linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="nmslib/nmslib")