A tiny Rust proxy that batches high-QPS embedding requests before forwarding them to Hugging Face Text Embeddings Inference (TEI).

Discover your next great read with AI-powered RAG semantic search and intelligent recommendations.

An overview and analysis of structures optimized for nearest neighbour searches.

VectorXLite — A fast, lightweight vector search with payload support and SQL-based filtering.

LLM documents spliting with AI agent that wrap chunks within document's context and store into a vector DB with simple chat

Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

🎨 Visualize audio in your terminal with Chroma, a Rust-based ASCII art shader that offers GPU-accelerated effects and real-time configuration adjustments.

A context-aware, emotionally adaptive AI framework with memory, entity routing, and narrative continuity built as a personal AI companion system.

Semantic search and relevance engine for e-commerce

High-performance Rust API with AI, multi-format docs, Gemini integration, security, CLI.

Lightweight implementation of ANN (Approximate Nearest‑Neighbor) search

⚡🧠 Vectro+ — High-Performance Embedding Engine in Rust 🦀💾 Compress, quantize, and accelerate vector search 🚀 Boost retrieval speed, cut memory, keep semantic precision 🎯🔥

🐙 Meta-AI Orchestrator unifies multiple LLMs with dynamic routing, RAG search, and DAG pipelines for enterprise AI workloads across providers, with observability and QA.

A simple vector database in rust

Open Source Vector Database implemented in the Rust Programming Language.

VectorLite is a Rust-native, in-process vector store that brings sub-millisecond search and local embeddings to your AI agents and edge systems.

A serverless-friendly vector database in your hands

VectraDB: Fast, Persistent, and Rust-Powered Vector Database with REST, gRPC, and Python Client Support

High-performance rust vector search library and service