JSPM

LanceDB: A serverless, low-latency vector database for AI applications

OpenClaw enhanced LanceDB memory plugin with hybrid retrieval (Vector + BM25), cross-encoder rerank, multi-scope isolation, long-context chunking, and management CLI

LanceDB implementation of RAG interfaces for vibe-agent-toolkit

Local RAG MCP Server - Easy-to-setup document search with minimal configuration

Give your OpenClaw agent lasting memory: structured facts, semantic search, auto-capture & recall, decay, optional credential vault. Part of Hybrid Memory v3.

OpenClaw memory plugin: local LanceDB + DashScope-compatible embeddings

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

Codebase graph analysis for AI agents — AST + call graph + type graph + hybrid semantic search via MCP

面向 A 股投资与盯盘场景的 OpenClaw 智能股票插件，基于 TickFlow API 提供实时监控、收盘后复盘、多维综合分析、关键价位跟踪与告警能力。OpenClaw smart stock plugin for A-share investing and watchlist workflows, powered by TickFlow API for realtime monitoring, post-close review, multi-dimensional analysis, key l

LanceDB-backed long-term memory provider for OpenCode

Local-first AI memory engine for multi-agent workflows — 17-tool MCP server. Zero config (LanceDB) or Azure (Cosmos + AI Search).

HireBase - AI-powered CV search engine with LanceDB and MCP

Ultra-simple code search tool with Jina embeddings, LanceDB, and MCP protocol support

Interactive CLI for persona-based local AI workflows

Native TypeScript AI memory system and MCP server (Zero-LLM, LanceDB)

Cognitive science-based AI memory framework — Weibull decay, triple-path retrieval, multi-backend storage

Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol, vector search, git-based knowledge graphs, cloud backup. Never lose context again.

OpenClaw plugin for multimodal RAG - semantic indexing and time-aware search for images and audio using local AI models

Local-first semantic memory plugin for OpenClaw — LanceDB + Ollama, no cloud required.

Local RAG MCP Server - Enhanced with hybrid search, memory management, and code file support (fork of shinpr/mcp-local-rag)

LanceDB: A serverless, low-latency vector database for AI applications

Local semantic code search with LanceDB indexing and DeepInfra-powered retrieval

A lightweight web-based viewer for LanceDB databases with advanced table browsing, column filtering, and SQL WHERE clause support

MCP-сервер для поиска UI-компонентов с использованием RAG на базе LanceDB и GigaChat

Embex Vector Database ORM Node.js Bindings

AI agent memory MCP server with hybrid BM25 + vector search — no Docker required

MCP plugin for semantic code search using LanceDB - gives AI coding agents deep context from your entire codebase

Claude Code skill — Direct-to-Runtime Zero-Hop Stack architecture guide

Semantic embeddings and vector search - find concepts that resonate

Local RAG MCP Server - Easy-to-setup document search with minimal configuration

OpenClaw MCP router plugin for Model Context Protocol (MCP): semantic tool search and dynamic tool calling to reduce prompt bloat

Local RAG MCP Server with extended file support (including PPTX)

Reusable local-first hybrid retrieval core powered by SQLite, LanceDB, and optional OpenAI embeddings.

LanceDB: A serverless, low-latency vector database for AI applications

A local-first Model Context Protocol (MCP) server that provides semantic search capabilities for codebases

LanceDB: A serverless, low-latency vector database for AI applications

Genkit AI framework plugin for LanceDB.

LanceDB Vector検索エンジン

Agent memory plugin for OpenCode - persistent memory with semantic search using LanceDB

📚 Model Context Protocol server for AI-powered storytelling with Narrative Knowledge Graph - extract characters, locations, relationships and search your stories semantically.

search-docs サーバ実装

🔍 LanceDB vector storage for FlowRAG - embedded semantic search, no server required

Vidya — Hybrid memory plugin for OpenClaw agents. LanceDB vector store + Voyage AI embedding/rerank + BM25 keyword search.

LanceDB-backed long-term memory plugin for OpenClaw with auto-recall and auto-capture

MCP server that indexes Claude Code and Codex conversations for semantic search

CortexMem — Brain-Inspired Memory System for OpenClaw (类脑记忆系统)

Full-featured long-term memory system for Claude Code via MCP — hybrid retrieval, smart extraction, auto-capture, intelligent forgetting

Smart MCP server for Outline Wiki with AI-powered RAG Q&A, summarization, and semantic search

Native LanceDB vector database plugin for Capacitor — on-device vector search with ANN queries. Includes optional memory management layer.

MCP server for persistent agent memory — hybrid BM25 + vector search backed by LanceDB with local ONNX embeddings. No API keys, fully local.

Local-first semantic search for documents using MCP protocol. Requires Python 3.10+ and Docling (pip install docling).

OpenClaw memory plugin with markdown source-of-truth and LanceDB primary retrieval

SIE embedding function and reranker for LanceDB

MCP server for interacting with LanceDB database

A local-first knowledge base engine with vector search using LanceDB and Hugging Face embeddings

MCP server for interacting with LanceDB database

ContextEngine plugin for OpenClaw with retrieval-augmented context management and memory-aware compaction

MCP plugin for semantic code search using LanceDB - gives AI coding agents deep context from your entire codebase

MCP for adding semantic memory to AI coding agents

TraceAI instrumentation for LanceDB vector database

AST-aware semantic + lexical code indexer for AI agents

Persistent memory system for Claude Code via MCP — dual-write to Markdown + LanceDB with hybrid semantic search

MCP server for semantic memory and codebase search with LanceDB and Voyage AI embeddings

A high-performance local MCP server for semantic code search, summarization, and RAG.

LanceDB: A serverless, low-latency vector database for AI applications

AI-powered git code review toolkit with optional local RAG knowledge base

Simple, lightweight RAG / memory layer using LanceDB + local embeddings (Xenova/all-MiniLM-L6-v2)

Memory and task orchestration plugin for OpenCode with project/session isolation

Dig through any documentation with AI - MCP server for Claude, Cursor, and other AI assistants

AI-powered HR management MCP server — CV upload, semantic candidate search, interview scheduling and more. Works with Claude Code and any MCP-compatible client.

Dig through any documentation with AI - MCP server for Claude, Cursor, and other AI assistants

Universal LLM Memory Architecture (ULMA) plugin for OpenCode with project/session isolation

Admin UI components for Deno AI Toolkit workspace management

Semantic Cache is a library for caching natural text based on semantic similarity using LanceDB with multiple embedding provider support (OpenAI, Google Gemini, VoyageAI)

Privacy-first local memory plugin for Moltbot: SQLite for structured/temporal queries + local embeddings for semantic search. Zero cloud calls.

Local RAG MCP Server - Easy-to-setup document search with minimal configuration

LanceDB: A serverless, low-latency vector database for AI applications

Universal LLM Memory Architecture (ULMA) plugin for OpenCode with project/session isolation

Add AI-powered chat with RAG to any app in minutes

NMP Plus MCP Server - 36 commands via HTTP API for Cursor

MCP server for interacting with LanceDB database

Persistent memory for AI coding agents — vector search over past sessions

AI memory plugin for OpenClaw — embedded LanceDB vector search with confidence scoring, contradiction detection, multi-signal ranking, and user verification loop

Core functionality for GoGlyph - Universal Shared Brain for AI Agents

A wrapper for LanceDB, providing a simple and efficient way to interact with LanceDB databases in JavaScript and TypeScript.

MCP server that indexes Claude Code and Codex conversations for semantic search

NMP Plus MCP Server - 36 commands via HTTP API for Cursor

Vector database indexer for documentation

Local CLI tool for indexing and searching code repositories with full-text and semantic search.

Lightweight repo-local hybrid (semantic + keyword) code search over MCP. Pure npm — no Docker, no Ollama, no servers. 11 languages via tree-sitter, jina-code embeddings, LanceDB, live file watcher. One command to install.

Local-first chat memory with vector search for LLM applications. No cloud. No API keys. Your data stays on your device.

ctxloom — The Universal Code Context Engine. A local-first MCP server providing intelligent code context via hybrid Vector + AST + Graph search with Skeletonization (70-90% token reduction).

Native TypeScript AI memory system and MCP server (Zero-LLM, LanceDB)

MCP server for structured project memory — semantic search, knowledge graph, auto-ingest, analytics dashboard