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

pylibseekdb

Multi-language client bindings for SeekDB (Python, Node.js), powered by libseekdb

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). AGPL.

velesdb

The local-first memory engine for AI agents. One offline Rust binary fuses vector + graph + columnar under SQL — remember / recall / why over the Model Context Protocol. why() reconnects a decision to its context across sessions, where pure vector recall (Mem0/Zep) goes blind. Runs on server, laptop, browser, edge. Zero cloud.

ailake

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

alayalite

AlayaLite – A Fast, Flexible Vector Database for Everyone.

brinicle

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

llama-index-vector-stores-velesdb

The local-first memory engine for AI agents. One offline Rust binary fuses vector + graph + columnar under SQL — remember / recall / why over the Model Context Protocol. why() reconnects a decision to its context across sessions, where pure vector recall (Mem0/Zep) goes blind. Runs on server, laptop, browser, edge. Zero cloud.

langchain-velesdb

The local-first memory engine for AI agents. One offline Rust binary fuses vector + graph + columnar under SQL — remember / recall / why over the Model Context Protocol. why() reconnects a decision to its context across sessions, where pure vector recall (Mem0/Zep) goes blind. Runs on server, laptop, browser, edge. Zero cloud.

haystack-velesdb

The local-first memory engine for AI agents. One offline Rust binary fuses vector + graph + columnar under SQL — remember / recall / why over the Model Context Protocol. why() reconnects a decision to its context across sessions, where pure vector recall (Mem0/Zep) goes blind. Runs on server, laptop, browser, edge. Zero cloud.

quiver-client

Security-first, memory-frugal vector database in Rust with a retro terminal cockpit.

agentvec

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

sqlitegraph

Embedded graph database on SQLite — HNSW vector search, Cypher-like queries, graph algorithms (BFS, A*, SCC, dominance), ACID + WAL + MVCC delta log, Python bindings, Native V3 CSR backend.

vector-inspector

The missing developer tool for working with vector databases. A comprehensive desktop app for visualizing, querying, and managing vector data.

annlite

Fast and Light Approximate Nearest Neighbor Search Library integrated with the Jina Ecosystem

vectlite

Embedded vector store for local-first AI applications.

tidevec

The world's first temporally-aware causal vector database. TVIndex + CausalEdge + GPU CAGRA + RS(10,4) 11-nines durability. C++20, Apache 2.0.

simmetry

NumPy-first similarity scores for strings, vectors, points, and sets.

hannoy

Production-ready KV-backed HNSW implementation in Rust using LMDB

llama-index-vector-stores-zeusdb

LlamaIndex integration for ZeusDB vector database. Enterprise-grade RAG with high-performance vector search.

tool-compass

Semantic MCP tool-discovery gateway — find tools by intent, not memory. Hybrid semantic+lexical search, stdio + remote HTTP backends, full-schema describe(), per-tool timeouts & allow/deny. Install via npx, pip, or Docker.