Bm25 Python Packages

rank-bm25

A Collection of BM25 Algorithms in Python

6.5M 1K 107

bm25s

Fast BM25 search in Python, powered by Numpy and Numba

1.5M 2K 99

adalflow

AdalFlow: The library to build & auto-optimize LLM applications.

30K 4K 376

mind-mem

Persistent AI memory for Claude Code, OpenClaw, and any MCP-compatible agent. v4.0.9 — Predicate.register() runtime API + CI fully green (26/26 jobs, 12 OS×Python matrix rows). BM25F+vector hybrid, governance-aware, 5428+ tests, 84 MCP tools, 15 clients.

27K 6 1

memtomem

Markdown-first, long-term memory infrastructure for AI agents. Hybrid BM25 + semantic search across markdown/code files via MCP.

10K 4 23

ctx-retriever

Trigger-Driven Dynamic Context Loading for Code-Aware LLM Agents

9K 5 2

moraine-cli

Unified realtime agent trace database & search MCP

5K 35 3

bm25

Fast BM25 search in Python, powered by Numpy and Numba

5K 2K 99

knowledge-rag

Drop docs, search instantly from Claude Code — 12 MCP tools, 20 format parsers, hybrid search + reranking. Zero servers, zero API keys, 100% local.

5K 79 14

lightrag

AdalFlow: The library to build & auto-optimize LLM applications.

5K 4K 376

seeklink

SeekLink — hybrid semantic search for markdown vaults. Four-channel RRF fusion, MLX reranker, native CJK support. Fully local.

3K 7 1

code-memory

MCP server with local vector search for your codebase. Smart indexing, semantic search, Git history — all offline.

3K 33 7

vera-ai

Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ranges, and symbol metadata. Built in Rust.

3K 85 10

retriv

A Python Search Engine for Humans 🥸

3K 249 33

easy-elasticsearch

Using business-level retrieval system (BM25) with Python in just a few lines.

2K 31 6

uqa

UQA — Unified Query Algebra: a multi-paradigm database engine unifying relational, text retrieval, vector search, graph query, and geospatial paradigms under a single algebraic structure

2K 7 1

flamehaven-filesearch

Self-hosted RAG search engine — 34 formats, BM25+hybrid search, multi-LLM (Gemini/OpenAI/Claude/Ollama), FastAPI + Docker, production-ready in 3 min

2K 101 13

trw-memory

Standalone AI agent memory engine — hybrid search (BM25 + vectors), Q-learning scoring, Ebbinghaus decay, tiered storage, knowledge graph. Part of TRW Framework.

1K 1 1