Cohere-compatible reranker over MCP — pay-per-call in USDC, no account, no GPU, no model download.

Self-hosted Qwen3 retrieval server with Embedding, Reranker, MCP, and Web console.

Local-first RAG engine with hybrid search, BGE reranker, self-learning loop, and MCP server

Local hybrid-search (BM25 + vector + reranking) MCP server — ask questions of any local codebase or document folder, fully offline

MCP server for LangSearch Web Search & Semantic Rerank API. Use with Claude Code, Claude Desktop, or any MCP-compatible client.

Self-hosted MCP Japanese text indexing & search—chunking+embeddings with BM25×vector rerank

KINDX - On-device hybrid search engine for markdown documents with BM25, vector embeddings, and LLM reranking

Multi-engine web search + fetch MCP server (DDG, Brave, Tavily, Google AI Mode) with consensus-merge dedup, local cross-encoder reranking, and Groq synthesis

Searchable memory for your Claude Code sessions: local hybrid search with reranking, a CLI, and an MCP server for agents.

MCP server for LangSearch Web Search & Semantic Rerank API. Use with Claude Code, Claude Desktop, and any MCP-compatible client.

Searchable memory for your Claude Code sessions: local hybrid search with reranking, a CLI, and an MCP server for agents.

Semantic search over your Gmail, from inside Claude Code. Embeds your full inbox with zembed-1 and reranks with zerank-2 — finds emails by meaning, not keywords.

MCP server for LanceDB-backed long-term memory with hybrid retrieval (Vector + BM25), cross-encoder rerank, multi-scope isolation, and memory lifecycle management

A retrieval engine that refuses to guess. Register git repos and URLs, get grounded, cited answers over MCP and REST. Hybrid search, cross-encoder rerank, Postgres + pgvector.

Intent-first search that finds the right tool from a vague description. Hybrid retrieval over LLM-written cards, LLM rerank with recall safety, MCP server for AI agents, runs on a laptop CPU.

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.

Read-only MCP server for 1C BSL code search: hybrid BM25 + vector kNN retrieval over methods in Elasticsearch, RRF, dedup, rerank — context for code LLMs. | MCP-сервер поиска по коду 1С BSL: гибридный BM25 + векторный поиск по методам в Elasticsearch, RRF, дедупликация, ранжирование.

100% Free Developer Tier (zero API keys, zero wallet required): 15 deterministic AI agent & developer tools: AST context skeleton pruner, BPE token budget planner, BM25+RRF+MMR hybrid reranker, self-healing fuzzy diff patcher, polyglot AST symbol & comple

Local RAG search engine and MCP server for AI agents (Claude Code, Cursor, VS Code): hybrid BM25 + semantic search with reranking over Markdown and Obsidian notes, PDF, Office files and emails, fast at tens of millions of passages. Backlinks, metadata filters, browser UI. Runs on your own GPU or CPU: no cloud, no API keys.

Scoped hybrid-RAG CLI and MCP server with BM25, vector retrieval, reranking, and answer synthesis

Unified MCP search server with 8 providers, caching, reranking, and rate limits

JavaScript port of op-grep - intelligent code search with LLM reranking

AI-powered intelligent code search with LLM reranking - MCP server for Claude, Cursor, Cline

AI-powered intelligent code search - client package with grep, read, and AST analysis (GPU reranking via cloud API)

Persistent memory for Claude Code with hybrid search (BM25 + vectors + reranker) — MCP plugin

MCP Web Hound — unified web search, GitHub search, and GitLab search tools with caching, reranking, and rate limits

Code knowledge graph and MCP search server with tree-sitter parsing, vector + reranker retrieval, and bitemporal knowledge.

Fast local code intelligence for AI agents powered by AST Treesitter, SCIP, semantic search and a reranker

This is a local rag with retrieval-augmented experience log for coding with indexed framework, reranking documents, emdedding-normalization

🔍 Self-hosted web search MCP server for compliance-sensitive AI pipelines. Tiered scraping, PII detection (Presidio), pluggable reranking, content provenance, and full OpenTelemetry tracing. Built in Go for regulated industries.

CrawlEyes - Web Scraping & Search Toolkit for AI Agents. Full-text extraction + robust search + semantic reranking + MCP server. Zero API-key fallback, China-friendly.

Rust-native hybrid retrieval over LLM thinking traces - dense ANN + BM25 + rerank, all local ONNX. Daemon, HTTP + MCP, zero API keys.

CrawlEyes - Web Scraping & Search Toolkit for AI Agents. Full-text extraction + robust search + semantic reranking + MCP server. Zero API-key fallback, China-friendly.

Local hybrid search for Korean Markdown notes & Obsidian vaults (BM25 + Hangul bigram + Qwen3 + rerank, MCP/CLI/SDK) · 한국어 마크다운 로컬 검색

Governed multi-agent memory for AI agents — hybrid markdown+SQLite, FTS, vector search, LLM reranking. One Go binary, MCP stdio + HTTP + SSE.

Local-first knowledge retrieval for AI agents, combining FTS5, vector search, reranking, and traceable MCP results.

Local MCP code search that cuts AI agent tokens: AST chunks, CPU reranking and a dependency impact graph. -63.9% tokens measured.

TypeSafe cookbook skill suggestion (Jev) as a stdio MCP server for Hermes: one Choice call ranks the roster + gates, a second reranks the top-3; suggests at most one skill.

Local code search MCP server for AI agents: Miru hybrid search + Kalpana Discrete RIF rerank + adaptive context cutoff. Fewer tokens, no API keys, code never leaves your machine.

Semantic web search MCP server with Kagi, Scrapfly, PDF extraction, and local ONNX reranking for Claude Desktop, Gemini CLI, and Codex.

The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM reranking. And it's free & burns less tokens.

Local-first agentic RAG with citations - hybrid search, reranking and multimodal retrieval over your own documents, no database server required - Minimal dependencies

MCP server for LanceDB-backed long-term memory with hybrid retrieval (Vector + BM25), cross-encoder rerank, multi-scope isolation, and memory lifecycle management

RAG proof of concept: hybrid retrieval (pgvector HNSW + lexical RRF), cross-encoder reranking, dual embeddings (OpenAI + local GPU/CPU), and an MCP server — Python, PostgreSQL, Docker (NVIDIA/ROCm)

MCP server that turns a local SearXNG instance into citation-aware web search for AI agents — Readability extraction, MiniLM semantic rerank, inline-clickable markdown citations.

万忆 · 永不遗忘的全量记忆系统 — MCP 标准 stdio + 事件溯源 + 过程记忆 + 语义向量检索 + sqlite-vec ANN + reranker 精排 + 记忆图谱 + 元认知知识空白 + 只读 Markdown 镜像 + 护城河全自动，23 个 MCP 工具。

Web search MCP server that does search result reranking locally on your machine, formerly known as mcp-local-rag. ✨ no API keys ✨

OpenScout is a Perplexity-inspired answer engine that turns a single question into a grounded, cited response. It combines web search, retrieval, reranking, and LLM synthesis in a lightweight Streamlit Application

Lightweight QMD alternative: fully local hybrid search engine (BM25 + vector + rerank) and MCP server in a single ~15MB Go binary. No Node.js. Runs on Raspberry Pi.

Local knowledge search for coding agents: GPU hybrid search and reranking with source citations, plus saved decisions and session captures, served by one shared MCP daemon.

MCP server for Pipecat voice AI framework documentation. Search 6,936 chunks from 317 pages via Claude Desktop or Cursor. Hybrid BM25 + FAISS retrieval with cross-encoder reranking. 78.8% MRR, 93% Recall@5, 36ms avg latency.

Semantic code search MCP server: Tree-sitter AST chunking + voyage-code-3 embeddings + hybrid retrieval (sqlite-vec + FTS5 + RRF) + Voyage rerank-2.5 + call graph expansion

MCP server exposing hybrid RAG (BM25 + dense + RRF + reranking) over SEC filings — with FastAPI backend, Next.js frontend, and 22-query evaluation.

Production-grade GraphRAG system: hybrid retrieval (vector + BM25 + knowledge graph), reranking, grounded cited answers with refusal, SSE streaming, and an MCP server, built with FastAPI, LangChain, LangGraph, Qdrant, and React.

Universal AI Agent Long-Term Memory Engine — Hybrid Vector+BM25, cross-encoder reranking, Weibull decay, LLM smart extraction, semantic dedup, tiered content. Zero-ops LanceDB backend.

Code search and session observability for coding agents. Hybrid BM25+semantic, optional cross-encoder rerank, self-bench on your own data. npm install -g @sivru/cli

MCP server for local-first document knowledge bases: LanceDB hybrid search (bge-m3 + CrossEncoder rerank), native BM25 with jieba, and PDF-to-LaTeX ingestion via a local MinerU pipeline

Semantic code search MCP server: Tree-sitter AST chunking + voyage-code-3 embeddings + hybrid retrieval (sqlite-vec + FTS5 + RRF) + Voyage rerank-2.5 + call graph expansion. Thin npx wrapper that launches the Python package via uvx.

Local code search and architectural memory MCP server for AI coding agents. Hybrid retrieval (vector + FTS + reranker) with Tree-sitter AST chunking. Runs entirely on your machine.

Code-search platform for AI coding agents: vector search fused with BM25 keyword scoring and reranking, tree-sitter AST chunking, a web app, a REST API and a 12-tool MCP server.