Bm25 Python Packages

rank-bm25

A Collection of BM25 Algorithms in Python

bm25s

Fast BM25 search in Python, powered by Numpy and Numba

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

trw-memory

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

trelix-mcp

🌲 Fast, reliable code intelligence — Tree-sitter AST parsing, contextual hybrid search, adaptive query planning, call-graph expansion & LLM synthesis. 20+ languages. Zero infra.

trelix-langchain

🌲 Fast, reliable code intelligence — Tree-sitter AST parsing, contextual hybrid search, adaptive query planning, call-graph expansion & LLM synthesis. 20+ languages. Zero infra.

trelix-llama-index

🌲 Fast, reliable code intelligence — Tree-sitter AST parsing, contextual hybrid search, adaptive query planning, call-graph expansion & LLM synthesis. 20+ languages. Zero infra.

nxsearch

nxsearch: a full-text search engine

markdown-memory

MCP server that hands coding agents the one Markdown section that answers the question, not the whole file. Local hybrid search: BM25 keywords + ONNX embeddings in SQLite. No API keys, no network.

trelix

🌲 Fast, reliable code intelligence — Tree-sitter AST parsing, contextual hybrid search, adaptive query planning, call-graph expansion & LLM synthesis. 20+ languages. Zero infra.

memtomem

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

adalflow

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

mind-mem

Persistent AI memory for Claude Code, OpenClaw, and any MCP-compatible agent. BM25F + vector hybrid, governance-aware, local-first, zero-infrastructure.

pagelore

Durable project memory for AI coding agents (Claude Code, Codex, Cursor, Gemini CLI): decisions and bug post-mortems as markdown pages in your repo, BM25F search via CLI or MCP server, validated writes. No server, no database, stdlib-only Python.

contex-python

An MCP-native context bus that pushes updates to agents that subscribe to data using natural language.

lastlight

Low-power, offline retrieval (RAG) for disaster and infrastructure-failure guidance.

bm25

Fast BM25 search in Python, powered by Numpy and Numba

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.

pyqql

Declarative SQL query engine for Qdrant and edge vector databases. Multi-vector dense & BM25 sparse search, hybrid retrieval, CTEs, and MMR in Rust, Python, Node.js, and WebAssembly

loci-rag

A queryable second brain over your scattered notes and docs - hybrid retrieval (vector + BM25), section-level citations, and an MCP server so AI agents can use it. ~300 lines, no LangChain.

silica-core

Retrieval tools for coding agents, no model in the loop: SOTA-competitive files, search, read, code_pack and write_note over the folder your session is opened in, served over MCP.

fidelis-memory

Zero-LLM agent memory for Claude Code and AI agents: local-first BM25, dense-vector, and reciprocal-rank-fusion retrieval. Returns original passages verbatim by default. Available on PyPI as fidelis-memory. Apache-2.0.

pinakes

Pinakes — a portable, agent-first knowledge base. One directory = one KB.