All-in-one platform for search, recommendations, RAG, and analytics offered via API

Rust-powered code intelligence CLI for AI coding agents. Builds call graphs and hybrid semantic search indexes (Dense + Sparse + RRF + Reranker) across 7 languages. Ships as native MCP tools for Claude Code and Codex CLI.

A BM25 embedder, scorer, and search engine, written in Rust.

db2vec: High-performance Rust CLI to parse database dumps (.sql, .surql), generate vector embeddings via Ollama, TEI, Gemini, and load into vector databases (Pinecone, Redis, Chroma, Milvus, Qdrant, SurrealDB). Optimized for speed on large datasets.

Library for embedding native GPU textures (GL FBO, Vulkan image, Metal IOSurface) into wgpu textures.

The open source distributed web search engine that searches by meaning.

Fast text embedding service

High-performance vector database & RAG memory layer - hybrid search, embeddings, RAPTOR trees, BM25 fusion for AI systems.

Semantic Grep - Superpower Your LLM

LIcense Embedding System (Rust)

Rust foundation library for AI-native apps — 16-provider catalog, async LLM client, MCP server, knowledge graph, local ONNX embedding (44 models), and safety utilities

(F)unctional (E)mbedding of (T)erms (I)n a (S)patial (H)ierarchy -- as a Rust crate!

ShrimPK kernel — Echo Memory prototype for AI models

The Moka JS Runtime, Based On Spider Monkey

Personal RAG engine — simple, fast, Rust. One binary (15 MB), one DB, native collections. MCP-native.

RustViking - OpenViking Core in Rust. High-performance AI memory infrastructure with AGFS virtual filesystem and layered vector indexing.

Triplet mining for contrastive learning — random, hard, semi-hard strategies

Measure distance between floating-point vectors in Rust

Hyperbolic geometry embeddings using Poincaré ball and Lorentz models

MCP server for semantic hybrid search (sqlite-vec + FTS5 with optional cross-encoder reranking) over a Markdown / plain-text knowledge base