Hnsw Python Packages

datasketch

MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog, HyperLogLog++, LSH Ensemble and HNSW

vicinity

Lightweight Nearest Neighbors with Flexible Backends

voyager

🛰️ An approximate nearest-neighbor search library for Python and Java with a focus on ease of use, simplicity, and deployability.

zvec

A lightweight, lightning-fast, in-process vector database

yantrikdb

Cognitive memory engine for AI agents — temporal decay, contradiction detection, autonomous consolidation, knowledge graph, ANN recall via HNSW. Embeddable Rust library with Python bindings; powers yantrikdb-server (HTTP gateway, MCP server, openraft cluster). Apache-2.0.

brinicle

A resource-efficient C++ vector index engine built for low-RAM production workloads

feather-db

Embedded vector database + living context engine Part of Hawky.ai — AI-Native Digital Marketing OS

fenecdb

Minimal, vector-native embedded database in Rust. Compiles to WebAssembly, has its own query language (FenecQL) and speaks the PostgreSQL wire protocol.

ailake

AI-Lake Format: self-contained Parquet + HNSW index — unifying tabular data, embeddings, and vector search in a single Iceberg-compatible file

velesdb

The explainable, local-first memory engine for AI agents. One ~9 MB binary fuses vector + graph + columnar under VelesQL; why() returns the evidence path behind every recall. No cloud, no glue code — runs on server, browser, mobile and desktop.

alayalite

AlayaLite – A Fast, Flexible Vector Database for Everyone.

ann-search

Rust implementation of a bunch of approximate nearest neighbours searches; now with Python bindings

engram-memory-system

Memory system for AI agents with hybrid retrieval, MCP tooling, and LongMemEval-leading performance.

annlite

⚡ A fast embedded library for approximate nearest neighbor search

vantadb-py

Embedded persistent memory and vector retrieval engine for local-first AI apps, with HNSW, BM25, and RRF hybrid retrieval.

ultsql

UltSQL is a 100% Pure-Dart converged database engine combining SQL, NoSQL JSON, HNSW Vector RAG, and PL/SQL with zero C dependencies.

agentvec

Lightweight, serverless, embedded vector database written in pure Rust.

recern-vector

A single-file, embedded, inspectable vector database. Rust, Python and a CLI.

aster-vec

Embedded on-device vector database for AI agent memory and local RAG — disk-based HNSW in an LSM-tree, C++/Python, optimized for low memory footprint

apache-airflow-providers-ailake

AI-Lake Format: self-contained Parquet + HNSW index — unifying tabular data, embeddings, and vector search in a single Iceberg-compatible file

pomaidb

Embeded Vector Database for low performance devices

langchain-velesdb

The explainable, local-first memory engine for AI agents. One ~9 MB binary fuses vector + graph + columnar under VelesQL; why() returns the evidence path behind every recall. No cloud, no glue code — runs on server, browser, mobile and desktop.

llama-index-vector-stores-velesdb

The explainable, local-first memory engine for AI agents. One ~9 MB binary fuses vector + graph + columnar under VelesQL; why() returns the evidence path behind every recall. No cloud, no glue code — runs on server, browser, mobile and desktop.

haystack-velesdb

The explainable, local-first memory engine for AI agents. One ~9 MB binary fuses vector + graph + columnar under VelesQL; why() returns the evidence path behind every recall. No cloud, no glue code — runs on server, browser, mobile and desktop.