# nmslib/nmslib

Non-Metric Space Library (NMSLIB): An efficient similarity search library and a toolkit for evaluation of k-NN methods for generic non-metric spaces.

Repository: https://github.com/nmslib/nmslib
Canonical: https://ross.abutalabs.com/products/nmslib
Language: C++
License: Apache-2.0
License Family: permissive
Topics: knn-search, non-metric, neighborhood-graphs, k-nn-graphs, vp-tree
Last push: 2026-04-13T22:42:50+00:00

## Health v2 (maintenance only)
Score: 57/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 77, release rhythm 8, longevity 100
- inputs: {"age_days": 4802, "days_push": 142, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3588, forks 461 (observed 2026-08-28T04:08:11.148182+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: search-engine, benchmarking, machine-learning
- domain: machine-learning, databases
- platform: cpp, python, windows, cross-platform
- tags: knn-search, similarity-search, ann, non-metric-spaces, hnsw, vector-search, nearest-neighbor, algorithms, search, linux, macos

## Member repositories
- nmslib/nmslib (main) score 57

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:11.148182+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:33:53.503584+00:00, confidence not recorded.
  - readme: https://github.com/nmslib/nmslib (fetched 2026-08-28T04:08:11.148182+00:00, sha 49119d5651b9)
- Data as of 2026-08-30T08:39:29.467469+00:00.