-
MCP server for agentful pattern learning with vector database
Version check not run yet
Search and retrieval (RAG) npm Local MIT
-
Symbol-level codebase retrieval MCP server: get_symbol(name) returns a definition span + usages, never a whole file.
Version check not run yet
Developer tools npm Local 5 a week ISC
-
On-device LLM inference for the browser and Node.js — text, vision, speech (TTS/STT), and embeddings on a native WebGPU engine. Offline, private, no API keys. React hooks, MCP, and Vercel AI SDK inclu
Version check not run yet
Design and media npm Local 20 a week MIT
-
MCP Server for code intelligence capabilities (Embedding, Graph-RAG, Call-chain tracing, Bug locator)
Version check not run yet
Developer tools npm Local MIT
ME
Memwright io.github.bolnet/memwright 1.6 · 33/100 Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.
Version check not run yet
Databases Official MCP Registry Local
-
KINDX - On-device hybrid search engine for markdown documents with BM25, vector embeddings, and LLM reranking
Version check not run yet
Search and retrieval (RAG) npm Local 19 a week MIT
-
Code RAG MCP server: semantic indexing and retrieval of a local codebase (declaration-aware chunking + bge-m3 embeddings + Qdrant hybrid search). Exposes search_code / index_codebase / index_status /
Version check not run yet
Search and retrieval (RAG) npm Local 19 a week MIT
-
A Model Context Protocol (MCP) server that provides semantic search over Pinecone vector databases using hybrid search (dense + sparse) with reranking.
Version check not run yet
Search and retrieval (RAG) npm Local 19 a week BSL-1.0
-
Elasticsearch MCP Server with full version support (ES 5.x-9.x) and comprehensive API access
Version check not run yet
Search and retrieval (RAG) npm Local APACHE-2.0
-
Ratel Local package: a project-scoped persistent MCP gateway with BM25, semantic, and hybrid capability search plus the ratel-local CLI.
Version check not run yet
Search and retrieval (RAG) npm Local 17 a week MIT
-
Composable LLM agents, typed task graphs, and streaming RAG pipelines in Rust
Version check not run yet
DevOps and infrastructure crates.io Local
-
Sub-150ms Web-to-Markdown Engine & Model Context Protocol (MCP) Server for LLM Context Efficiency & RAG Pipelines.
Version check not run yet
DevOps and infrastructure npm Local 16 a week MIT
-
MCP server for persistent document storage with full-text search
Version check not run yet
Docs and knowledge bases npm Local 16 a week MIT
AI
ailore io.github.gregdalzotto/ailore 1.6 · 33/100 Local-first semantic search and RAG for your codebase and docs. Ask questions in natural language and get answers grounded in your own files, with citations. Works fully offline with Ollama, or with O
Version check not run yet
Model and agent tools npm Local 16 a week MIT
-
Thalamus cognitive hub for OpenClaw: packet handoff, vector memory, routing telemetry, encoder daemon, and multimodal ingest.
Version check not run yet
Memory and context npm Local 16 a week MIT
TO
Tokennuke io.github.BigJai/tokennuke 1.6 · 32/100 Code indexing MCP: 15 tools, 10 languages, hybrid search, call graphs, O(1) retrieval.
Version check not run yet
Search and retrieval (RAG) Official MCP Registry Local
-
Code indexing MCP: 15 tools, 10 languages, hybrid search, call graphs, O(1) retrieval.
Version check not run yet
Search and retrieval (RAG) Official MCP Registry Local
DM
docsearch-mcp io.github.patrickkoss/docsearch-mcp 1.6 · 32/100 MCP server and CLI tool for local document search with hybrid semantic+keyword search across PDFs, files, and Confluence
Version check not run yet
Office documents and spreadsheets npm Local 26 a week APACHE-2.0
-
Local MCP server for Obsidian/markdown vaults. NVIDIA nemotron-3-embed-1b semantic search, pure-JS int8 vector store, OKF frontmatter, wikilinks, memory, live file watcher.
Version check not run yet
Search and retrieval (RAG) npm Local 15 a week MIT
-
MCP (Model Context Protocol) server for ConnorDB — gives LLM agents (Claude Desktop, Cursor, Claude Code, any MCP client) one-click access to a ConnorDB engine: hybrid search, document retrieval, audi
Version check not run yet
Search and retrieval (RAG) npm Local 15 a week SEE-LICENSE-IN