Retrieval Python Packages

fastembed

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

bm25s

Fast BM25 search in Python, powered by Numpy and Numba

mteb

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

pageindex

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

semble

Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read

beir

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

topk-sdk

High-quality search for AI-native applications.

fastretrieval

Fast multi-model retrieval runtime: ONNX and GGUF embeddings, reranking, and a declarative model contract

moss

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

fastembed-gpu

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

infino

Embedded retrieval library built on Parquet. Fast, efficient, and scalable.

whoosh3

Fast, pure-Python full-text indexing and search. Actively maintained continuation of Whoosh / whoosh-reloaded. Install: pip install whoosh3

rtfm-ai

The open retrieval layer for AI coding agents. Indexes code, docs, legal, research, data — 22 parsers (incl. EPUB, DOCX, ODT), FTS5 + semantic search, knowledge graph. Serves surgical context via MCP. Open source, local, free.

mxbai-rerank

Crispy reranking models by Mixedbread

living-memory-model

A verifiable memory layer for language models — facts in a graph, every claim with its source.

bruriah

Evidence-backed project memory for coding agents: explain why your codebase is the way it is without letting past decisions hijack agent context.

brinicle

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

act-atmos

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

openkb

OpenKB: Open LLM Knowledge Base

reasongraph

Graph memory for AI agents: facts in, entities and cause->effect relations extracted with small open models, multi-hop recall with a cited chain. Library, HTTP/MCP service, LangChain, hosted at memory.primaxiom.ai

tokenpak

Local proxy that puts the right project context in front of the model before it starts working — with a receipt for what was added

sibyl-memory-client

Durable, file-based long-term memory for AI agents. Five-package plugin family: SDK, CLI, MCP server, Hermes adapter, and a LangGraph BaseStore. No vector database, no embeddings.

ir

An information-retrieval substrate for agentic systems

deutsches-ki-toolkit

Deutschsprachige KI-Infrastruktur für Dokumente, Datenschutz, Suche und RAG: deutsche PII-Erkennung mit Prüfsummen, Komposita-Zerlegung, strukturtreues Chunking, hybrides Retrieval und RAG mit geprüften Quellenangaben. Live-Demo im Browser.