#retrieval

MTEB: State-of-the-art evaluation of embeddings across languages and modalities

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read

Rust library for generating vector embeddings, reranking locally!

The Official Exa Javascript SDK

Up to 100x faster strings for C, C++, CUDA, Python, Rust, Swift, JS, & Go, leveraging NEON, AVX2, AVX-512, SVE, GPGPU, & SWAR to accelerate search, hashing, sorting, edit distances, sketches, and memory ops 🦖

97% token reduction for AI coding sessions — zero deps, 33 languages, MCP server