JSPM

PostgreSQL filesystem provider for just-bash with ltree, FTS, vector search, and RLS

Long-term project memory for AI agents backed by PostgreSQL and pgvector.

Persistent zero-knowledge memory for AI agents. Store, recall and transfer encrypted context across models.

Persistent knowledge memory layer for AI agents. Rust core, Postgres + pgvector backend, MCP protocol.

Advanced PGVector + Postgres nodes for n8n with full CRUD control

MCP server providing long-term memory for AI agents with semantic, graph, and temporal retrieval. Works with Claude Desktop, Claude Code, and Cursor.

Remote MCP server for searching U.S. FOIA statutes via Supabase. Provides hybrid search (BM25 + vector + RRF) with VoyageAI embeddings and reranking.

pgvector adapter for OrkaJS — works with PostgreSQL and Supabase

Standalone MCP server package for @mahin14m/project-context-memory.

Search microservice — full-text, semantic (pgvector), and hybrid document search

Knowledge microservice — RAG collections, document ingestion, chunking, embeddings, semantic/text/hybrid retrieval

Memory Service SDK for Metrio AI - multi-tenant memory management with pgvector

Genkit plugin for Supabase pgvector vector-store indexing, semantic search, and retrieval in TypeScript RAG apps.

The memory layer for AI applications — hybrid RAG retrieval, PII shield, polyglot storage

Memory microservice — vector search, semantic recall, collections, embeddings

Local semantic memory with PGlite + pgvector - budget Qdrant for AI agents

PostGraphile v5 codec plugin for pgvector — makes vector columns, mutations, and functions work automatically

Async learning layer that runs on top of any pgvector memory store. The LLM is stateless. Rumen isn't.

AI agent Postgres vector store tool with vector search and custom SQL capabilities

AI工具管理器 - 为Next.js项目提供AI工具管理和动态加载功能，添加了工具的创建、更新、删除、搜索等客户端功能，解决客户端导入服务器端工具的错误，继续优化客户端功能，添加分页搜索,参数去掉shape。自定义库取代@ai-sdk/react，解决swr问题,添加tool的模拟运行。添加一键生成工具。

A lightweight context engine for AI agents. Ingest events, build semantic context, query with natural language. Zero config default with SQLite + local TF-IDF embeddings.

Local-first PostgreSQL toolkit with hybrid text (tsvector) + vector (pgvector) search, Docker-managed ephemeral/persistent databases, and a TypeScript API for documents and entities.

AI SDK extension plugin for YouTube transcript vector embeddings with semantic search and RAG queries.

A complete Retrieval-Augmented Generation system using pgvector, LangChain, and LangGraph for Node.js applications with dynamic embedding and model providers, structured data queries, and chat history - supports OpenAI, Anthropic, HuggingFace, Azure, Goog

Persistent memory infrastructure for AI agents — knowledge graph, semantic dedup, decay, x402 micropayments

MCP server for Open Brain: Postgres + pgvector shared memory for Cursor, Claude, and any MCP client

AI-powered shopping assistant plugin for Vendure — LLM chat, vector search, cart management, and order tracking

ParadeDb JavaScript Client Library

Engine + storage abstraction for embeddings and similarity search.

Production MCP server for multi-agent AI research with OpenRouter

A framework for connecting your data to large language models

ParadeDb JavaScript Client Library Component for Midway.js

A production-ready Model Context Protocol (MCP) server for semantic memory management

Do

MCP Server for Claude Code, Cursor, Cline, Copilot, Github Copilot, Windsurf - Visual AI Agent Plan Execution, Approval Workflow, Plan Visualization, Agent Orchestration. See what your AI is thinking before it writes code. Works with Claude, GPT, Gemini,

TypeScript SDK for Supabase AI/RAG operations with pgvector

A production-ready Model Context Protocol (MCP) server for semantic memory management

AI-Native, PostgreSQL-compatible database with vector search, HNSW indexing, and full ACID compliance. All 421 tests passing. NEW: Window Functions, CTEs, Subqueries, JOINs, GROUP BY/HAVING!

PostgreSQL + pgvector provider for Khavee AI SDK

Your Claude Code sessions don't have to start from scratch anymore — SpecMem gives your AI real memory. It won't forget your conversations, your code, or your architecture decisions between sessions. That's the whole point. Semantic code indexing that act

A powerful, multimodal RAG engine with contextual retrieval, auto-prompt discovery, and PostgreSQL-native vector search

PostGraphile v5 plugin for pgvector similarity search

PostgreSQL + pgvector store adapter for mem0-community.

React component library for AI-powered chat widgets with RAG knowledge base integration, realtime updates, and human agent support

The Mind Palace for AI Agents — persistent memory (SQLite/Supabase), behavioral learning & IDE rules sync, multimodal VLM image captioning, pluggable LLM providers (OpenAI/Anthropic/Gemini/Ollama), OpenTelemetry distributed tracing, GDPR export, multi-age

Stdio proxy for PG-Memory - connects stdio-based MCP clients (Claude Desktop, Raycast) to your PG-Memory HTTP server using Clerk API key authentication. Personal knowledge base with 14 tools (6 read + 8 admin) including articles, Q&A, semantic search, and

Strapi v5 plugin for vector embeddings with OpenAI and Neon PostgreSQL. Enables semantic search, RAG chat, and MCP (Model Context Protocol) integration.

Utility for batch creating vectors via API

TraceAI instrumentation for pgvector (PostgreSQL vector extension)

Core RAG schema with pgvector support for document embeddings

Embedded PostgreSQL with pgvector extension for Node.js applications

MCP client configuration for REMBR - semantic memory for AI agents, RLMs, and multi-agent systems

VS Code RLM integration - Recursive Language Model patterns with GitHub Copilot agents, skills, and semantic memory

CLI tool to create modern Node.js projects with TypeScript, AI capabilities, and more

MCP server for PostgreSQL vector database with semantic and full-text search capabilities using pgvector

RAG vector index helpers for HNSW and IVFFlat

Advanced n8n node for Agentic RAG with Supabase pgvector - handles structured/unstructured documents with AI-powered query refinement

RAG vector index helpers for HNSW and IVFFlat

Patches and enhancements for LangChain.js

Enterprise-grade Node-RED nodes for PostgreSQL + pgvector with OpenTelemetry observability, structured logging, and production-ready resilience.

Production MCP server for multi-agent AI research with OpenRouter

Advanced RAG integration library with intelligent user preference tracking, runtime schema introspection, dynamic entity graph building, and comprehensive debugging tools for MongoDB, PostgreSQL, and vector stores

A memory management system based on PostgreSQL + pgvector for LangGraph workflows

MCP server for semantic code search with PostgreSQL and pgvector

The open-source memory layer for AI agents — MCP server backed by PostgreSQL + pgvector + Apache AGE

Global vector memory MCP server with intelligent learning and feedback for Claude Code

Simplified Deep Research MCP for Qwen Desktop (no database)

Stateful AI agent memory layer for PostgreSQL with pgvector - TypeScript-first with intelligent context management

MCP server for fetching and searching documentation with semantic search

OpenRouter MCP server for research agents

RAG functions for import, export, and vector search

Strapi v5 plugin for vector embeddings with OpenAI and Neon PostgreSQL. Enables semantic search, RAG chat, and MCP (Model Context Protocol) integration.

Production-ready orchestration framework for Claude Desktop with 30+ specialized agents, smart hooks, vector memory, and autonomous workflows

Lightweight RAG toolkit for pgvector — chunking, hybrid search SQL, MMR, RRF, and more. Zero runtime dependencies.

Lightweight TypeScript RAG system with PostgreSQL, OpenAI & Cohere - Built by beavers, for builders 🦫

MeshOS - A memory system for AI agents

RAG functions for import, export, and vector search

OpenRouter MCP server for research agents

Automatically and continuously vectorize your PostgreSQL tables with the flexibility of your own embedding pipelines

Multi-vector RAG pipeline engine for Ejiogbe Voices. Declarative YAML pipeline orchestration with multi-vector fusion search. TypeScript-native, Supabase-backed.

Semantic search MCP server for your codebase using PostgreSQL + pgvector + Ollama

MCP server for semantic agent selection using pgvector embeddings

Unified wrapper around popular vector databases — one API, any backend

Hybrid search toolkit for Postgres (pgvector + BM25 + rerank)

PostgreSQL database adapter for Recall with native pgvector support. Production-ready AI memory storage with vector similarity search.

MCP Rag search of the customer related informations

MCP Knowledge Graph Memory Server with Supabase + pgvector for semantic search

A production-ready Model Context Protocol (MCP) server for semantic memory management

Multi-tenant, production-safe memory layer for AI applications

Easy-to-use semantic search plugin for Supabase with automatic embedding generation and vector similarity search

Reusable retrieval primitives for Taura-style “type → recall” apps.

Library-first realtime RAG engine with pgvector and streaming generation.

MCP server for knowledge base with Mastra.ai and pgvector

Production-ready RAG (Retrieval-Augmented Generation) framework for Next.js applications with PostgreSQL + pgvector

Free and open-source AI memory system for preventing code duplication and ensuring pattern consistency

A lightweight, project-agnostic semantic memory system for storing and retrieving text with embeddings

Automatically generate and sync vector embeddings for PostgreSQL text data

Official TS/JS client library for NeuraLex API

Core RAG schema with pgvector support for document embeddings

MCP server for semantic memory storage using local Postgres with pgvector

Production-ready TypeScript SDK for Vector Context DB - Multi-tenant vector database with AI pattern recognition

Universal SQL adapter for LokiCMS with multi-database support, data federation, and vector search

Regular-RAG is a framework-agnostic RAG (Retrieval-Augmented Generation) engine with built-in support for Knowledge Graphs and PostgreSQL/pgvector.

A lightweight RAG helper library (embeddings, splitter, in-memory store, Postgres adapter)

Persistent memory SDK for AI agents — Stanford Generative Agents architecture on Supabase + pgvector

A persistent, local-first semantic memory MCP server for IDEs, featuring dual SQLite/PostgreSQL support.

Virtual filesystem for AI agents backed by PostgreSQL — ChromaFs-equivalent using just-bash

Persistent developer memory MCP server — the LLM is stateless, Mnestra isn't

PostgreSQL pgvector vector store plugin for ragpipe

Multi-source knowledge plugin for OpenClaw — pgvector + LightRAG injection via before_prompt_build hook

Buzo — Vector store quality gate for CI/CD pipelines