MCP servers and skills: search, filter by where they run, and compare.
1–24 of 54 tools for “cross-encoder”
Clear allCross-encoder reranker document store engine for high precision RAG (Haystack style)
SkillLink only★ 8
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.
PythonMIT★ 296No key
Rust-powered code intelligence CLI for AI coding agents. Builds call graphs and hybrid semantic search indexes (Dense + Sparse + RRF + Reranker) across 7 languages. Ships as native MCP tools for Claud
in the readmeTantivy BM25)│ │ (PetCodeGraph)│ └──────┬───────┘ └──────┬────────┘ └────────┬──────┘ │ │ │ └──────────────────────┼────────────────────────┘ ▼ ┌─────────────────┐ │ RRF Fusion │ ← Reciprocal Rank Fusion │ (Top-20 candidates)│ └────────┬────────┘ │ ▼ ┌─────────────────┐ │ Reranker │ ← Cross-⟦Encod
Node.jsMIT★ 768No key
Buddhist Digital Text Platform — 10,500+ texts, 613 sources, trilingual cross-canon, AI Q&A (RAG), knowledge graph, full-text search
in the readmefrom the canon itself — Retrieval-Augmented Generation over 670K+ embedded passages, optional cross-encoder reranking and root-sutra recall, **clickable 【《sutra》juan N】 citations** that open
Hosted by authorApache-2.0★ 350No key
Hybrid RAG (DuckDB vector + BM25 + RRF + recency/keyword priors + optional cross-encoder rerank) as an installable library + CLI.
PythonAGPL-3.0★ 9No key
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 ran
SkillMIT★ 120No key
On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search.
in the skill textderived multi-signal retrieval (BM25 + vector search + reciprocal rank fusion + query expansion + cross-encoder reranking), SAME -inspired composite scoring (recency decay, confidence, content-type half-lives
SkillMIT★ 210No key
Persistent local memory for AI coding agents — Claude Code, Codex CLI, Cursor, any MCP client. Temporal knowledge graph, procedural memory, AST codebase ingest, cross-project analogy. LongMemEval R@5
in the readmegraph, and fuses the ranked lists with reciprocal rank fusion; an optional cross-encoder can rerank the result. The default profile makes no LLM call
PythonMIT★ 73No key
Graph RAG on SQLite for AI agents: vector retrieval + hand-curated wikilink graph + cross-encoder rerank, with a zero-token per-turn memory ledger. Working pilot.
PythonMIT★ 9No key
Shared memory for AI agents
in the readmelocal embedder; one-time model download | | **+ BGE-reranker-v2-m3** | **97.6%** | local cross-encoder, max quality — opt-in, ≈5s p50 on CPU | Numbers come from plur
SkillApache-2.0★ 304No key
Local knowledge graph for AI agents. Hybrid search + MCP server for Obsidian vaults.
in the readmeconnections. - **5-lane hybrid search** — semantic embeddings + BM25 full-text + graph expansion + cross-encoder reranking + temporal scoring, fused via Reciprocal Rank Fusion . An LLM orchestrator classifies
SkillMIT★ 170No key
A Repository-Aware, Knowledge-Learning local MCP that understands your codebase in Real Time powered by Hybrid Semantic + Full-Text Engine, both supports claude code and codex
in the readmeexact matches. Results are fused via RRF and re-ranked by Cross-Encoder for precision. When embedding API is unavailable, gracefully falls back to graph search
Node.jsMIT★ 53No key
Local-first, deterministic memory store for AI agents: SQLite-backed BM25 with optional local ONNX semantic search and cross-encoder rerank, graph projection, and an MCP adapter. No required network o
DockerApache-2.0★ 3Few starsNo key
Read-only MCP server giving AI agents the web as compact, ranked, verified evidence. Local cross-encoder reranker, NLI claim verification, semantic cross-source agreement and contradiction detection.
Node.jsMIT★ 1Few starsNo key
Local-first encrypted memory for AI agents
in the readmememory through MCP, install uv and pull the local embedder and optional cross-encoder reranker: ```console uvx citadeldb-mcp pull e5-large uvx citadeldb-mcp pull
PythonApache-2.0★ 3Few starsNeeds a key
Lightning-fast RAG for AI agents. ONNX-powered, 4-layer fusion, MCP server. No PyTorch.
in the readmeknowledge graph traversal, and metadata filtering — fused through reciprocal rank fusion with cross-encoder reranking. All running on ONNX Runtime, no GPU, no API keys. Comes
PythonMIT★ 11No key
Bioinspired Agent Memory Engine — 7-layer brain-modeled memory lifecycle for AI agents. Just pass your LLM: CortiLoop(llm=agent.llm). Built-in embedding (bge-m3) + reranking (cross-encoder). Works wit
PythonMIT★ 4Few starsNo key
为 Agent 提供的本地联网搜索工具
in the readmeAgent Search 为 Agent 提供高效的本地联网搜索能力。支持并发检索多个关键词，通过 cross-encoder **rerank 重排**返回最相关结果，大幅减少搜索轮次和上下文消耗。 ## 这能帮你做什么？ **场景一：快速调研陌生领域** > "帮我调研一下 2024 年 RAG 技术的最新进展" 传统方式需要多轮搜索、逐个打开链接。agent-search 一次并发搜索多个关键词
Node.jsMIT★ 2Few starsNo key
AI-powered code generator for Arbitrum Stylus, SDK bridging, dApps & Orbit chains — 19 MCP tools with RAG
in the readmeuses a **Retrieval-Augmented Generation (RAG)** pipeline with hybrid search (vector + BM25 + cross-encoder reranking) to provide context-aware code generation. Available as a hosted service
PythonMIT★ 24No key
Academic-paper knowledge-base MCP server: PDF ingestion (MinerU), Qdrant vector search with reranking, two-phase KB management
in the readmechunking (configurable 300/1500/100 chars) -> embedding. - **Fast retrieval at scale**: embedding first-pass + cross-encoder re-rank, optional metadata filtering (`doc_id`, `section`, `year`, `journal`, ...) evaluated inside
PythonMIT★ 5No key
A Retrieval-Augmented Generation (RAG) Model-Controller-Provider (MCP) server designed to assist AI agents and developers in understanding and navigating codebases.. It supports incremental indexing a
in the readmemeaning, not just keywords. * **🎯 Two-Stage RAG**: 22-31% accuracy improvement with cross-encoder reranking (Qwen3-Reranker). * **🧠 Intelligent Chunking**: Parses code into functions and classes using
SkillMIT★ 15No key
A unified MCP server that indexes and retrieves Plesk documentation using vector embeddings and semantic search with reranking.
in the readmetool. It uses hybrid search (Vector + FTS), Reciprocal Rank Fusion (RRF), and Cross-Encoder reranking to deliver high-precision results in milliseconds. --- ## Architecture & Performance ```mermaid flowchart
PythonMIT★ 2Few starsNo key
Personal markdown memory for coding agents — brain-modelled curator, three retrieval tiers, lives on your disk.
in the readmedate as things change. On retrieval, a stack of BM25, vector embeddings, cross-encoder reranking, and agentic search surfaces the right memory at the right moment
PythonMIT★ 4Few starsNo key
Who stands behind it
