Hybrid Search Python Packages

flashrank

Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.

topk-sdk

High-quality search for AI-native applications.

exomem

Self-hosted MCP server that makes your Obsidian/markdown vault searchable — text, PDFs, Office docs, images, audio — from any MCP client. Hybrid retrieval over a typed, governed corpus, sub-second at 50k notes; your files stay plain markdown.

mnemo-mcp

Persistent AI memory with hybrid search and embedded sync. Open, free, unlimited.

sqlalchemy-paradedb

The official SQLAlchemy integration for ParadeDB

moss

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

neug

The one data index for your agentic applications

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

uqa

Embeddable Rust query engine unifying relational, full-text, vector, graph, and probabilistic retrieval under one typed algebra.

knowledge-rag

Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools, 20 format parsers. Zero external servers, zero API keys.

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.

axon-rag

Local-first RAG engine with cited answers from your own docs. GraphRAG, sealed sharing, MCP-native, VS Code Copilot integration. Nothing leaves your machine.

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.

vaultspec-rag

Search code and feature records by meaning through the command line or Model Context Protocol (MCP). Inference runs on your GPU.

trelix

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

pyreindexer

Embeddable, in-memory, document-oriented database with a high-level Query builder interface.

ephemeral-buffer-mcp

Ephemeral in-memory command output capture and hybrid search MCP server for coding agents.

mind-mem

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

macrame-db

An embedded bitemporal graph ledger — concepts, typed relationships, and their full history of change, with hybrid vector/keyword search, graph traversal, and in-memory analytics, in a single .db file.

kairix-agentic-knowledge-mgt

Shared knowledge layer for human-agent teams. Agents search, classify, and manage knowledge alongside your team.