Standalone vector database with SQL, SPARQL, and Cypher - powered by RuVector WASM

String similarity utilities based on Dice's Coefficient (bigram overlap).

Generic property graph engine with vector similarity search — extracted from scrollstr's PolyGraph

OneReach SDK client for Lookup

Find similarity between two strings, based on Dice Similarity Coefficient DSC

Text Similarity is a simple tool for checking the similarity between two texts. It returns the similarity score.

MemberJunction: Tag Engine - server-only tag engine with semantic embedding support for tag resolution

MemberJunction: AI Vectors In-Memory Utilities

EntityDB is an in-browser vector database wrapping indexedDB and Transformers.js

WebAssembly bindings for Meta's PDQ perceptual image hashing algorithm

CLI for Rauta (rauta.ai) — GPU infrastructure, compared in public. Canonical install: `npx rauta-ai`. Interim package name while unscoped `rauta` awaits npm similarity clearance. Sign up, connect provider keys (BYOK), buy prepaid credits, provision GPUs,

Implements the Jaccard algorithm for finding the similarity coefficient between sentences

Local-first text analysis CLI and MCP server for people, automation, and AI agents.

Libsql provider for Mastra - includes both vector and db storage capabilities

Layered, local, vector-backed context compressor for pi — supersede/collapse/cluster compaction with deduped inline recall.

An absurdly fast embedded graph database for Node.js. Sub-microsecond reads, pure Rust core.

Small text utilities shared across nodeve tooling: fuzzy identifier matching, boundary-aware trimming, slugifying, word-wrap, and string sanitizing.

Vector storage, embedding, and semantic search for Semiont

React popup component from Minutemailer

Primitives and SDK for LLM agent content workflows: compression, patching, progressive disclosure, signed URLs, collaborative document lifecycle, and retrieval planning