Search Packages

rank-bm25

A Collection of BM25 Algorithms in Python

bm25s

Fast BM25 search in Python, powered by Numpy and Numba

mind-mem

v3.7.0 — Persistent, auditable, contradiction-safe memory for coding agents. HTTP/REST auth fail-closed by default. Cross-platform atomic rollback (Linux/macOS/Windows). 71 MCP tools, 17 AI clients, hybrid BM25+vector+RRF, mind-mem:4b (Ollama). LoCoMo 86.33 conv-0 (Mistral, +8.4 vs published).

trw-memory

Persistent memory engine with hybrid retrieval, tiered storage, and semantic dedup for AI agents

adalflow

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

memtomem

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

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.

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.

moraine-cli

Unified realtime agent trace database & search MCP

lightrag

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

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

bm25

Fast BM25 search in Python, powered by Numpy and Numba

ctx-retriever

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

flamehaven-filesearch

FLAMEHAVEN FileSearch - Open source semantic document search with multi-provider LLM support (Gemini, OpenAI, Claude, Ollama)

engram-search

High-recall conversational memory retrieval. 98% R@5 on LongMemEval, 94% on LoCoMo — no LLM required. Local-first, cloud-ready.

seeklink

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

retriv

A Python Search Engine for Humans 🥸

groundmemory

Persistent identity and memory across AI tools - mcp-native, local-first, framework-agnostic, production-ready.

easy-elasticsearch

An easy-to-use Elasticsearch BM25 interface

bayesian-bm25

Bayesian probability transforms for BM25 retrieval scores

velocirag

Lightning-fast RAG for AI agents. ONNX-powered, 4-layer fusion, MCP server. No PyTorch.

code-memory

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

mnemosyne-engine

LLM Context Compression and Retrieval Engine -- zero dependencies, sub-100ms queries, document + code ingestion

graphstore

Agentic brain DB - the cognitive layer for AI agents