Retrieval Python Packages

fastembed

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

mteb

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

bm25s

Fast BM25 search in Python, powered by Numpy and Numba

semble

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

pageindex

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

topk-sdk

High-quality search for AI-native applications.

beir

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

nokori

Nokori (残り) — behavioral memory layer for Claude Code and Cursor. Turns your corrections into rules that come back when it counts. 经验留下的痕迹，比记忆更深。

fastembed-gpu

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

mxbai-rerank

Crispy reranking models by Mixedbread

ir

An information-retrieval substrate for agentic systems

act-atmos

Atmospheric data Community Toolkit - A python based toolkit for exploring and analyzing time series atmospheric datasets

openkb

OpenKB: Open LLM Knowledge Base

inferedge-moss

Python SDK for semantic search with on-device AI capabilities

brinicle

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

redhop

RedHop — a reasoning-aware retrieval & context runtime for RAG (in-process, no vector DB). Light weight alternative to langchain and llamaindex for retrieval alone.

aelfrice

Bayesian memory that learns from feedback for LLM agents

gritlm

Generative Representational Instruction Tuning

cellin

build long-lived multimodal memory, dream over it, and retrieve context with transparent weighting

moss

The retrieval layer for production AI systems. Lightning-fast (<10ms) search without vector databases. Built for browser, edge, on-device, and cloud.

intel-extension-for-transformers

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

memor-cli

Measured memory for coding agents — Claude Code, Codex, Copilot. Fire and forget, no API keys needed.

memorizing-transformers-pytorch

Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate nearest neighbors, in Pytorch

cbrkit

Customizable Case-Based Reasoning (CBR) toolkit for Python with a built-in API and CLI