Open-source memory engine for AI applications — semantic retrieval, AUDN mutation, and contradiction-safe claim versioning.
Lightweight TypeScript RAG system with PostgreSQL, OpenAI & Cohere - Built by beavers, for builders 🦫
Virtual filesystem for AI agents backed by PostgreSQL — ChromaFs-equivalent using just-bash
Core RAG schema with pgvector support for document embeddings
Memory SDK for AI chatbots - facts, embeddings, semantic search, emotional capture, consolidation
Database helpers and utilities for Kysely query builder
Advanced n8n node for Puter.js AI with RAG agentic capabilities, document processing, audio transcription, Supabase integration, and cost-optimized model priorities
PGlite is a WASM Postgres build packaged into a TypeScript client library that enables you to run Postgres in the browser, Node.js and Bun, with no need to install any other dependencies. It is only 3.7mb gzipped.
Amazon Aurora DSQL storage provider for Mastra
n8n community node for using Elasticsearch as a LangChain vector store (RAG, similarity search, AI agent tool)
MCP server for PostgreSQL with pgvector semantic search capabilities
Core library: database, services, and providers for Apart Intelligence
PostgreSQL (pgvector) vector-store adapter for @absolutejs/rag
A production-ready Model Context Protocol (MCP) server for semantic memory management
Core interfaces and reference storage adapters for the ggui MCP server — UiGenerator, SessionStore, BlueprintProvider, AuthAdapter, plus in-memory and SQLite implementations. The pluggable seam layer @ggui-ai/mcp-server is built on.
Postgres and pgvector adapter for @jeffs-brain/memory: tsvector BM25, halfvec cosine, and RRF hybrid retrieval.
pgvector support for Node.js and typescript
Production-ready AI engineering pipeline — multi-phase agents with real test verification, crash recovery, cost tracking, and durable memory. Works with Claude Code, Gemini CLI, and any OpenAI-compatible API.
MCP server for PostgreSQL vector database with semantic and full-text search capabilities using pgvector
Knowledge Base skill for Lunar — opt-in citation-grounded RAG over pgvector (schema-per-moon)
Memory-as-a-service MCP server for AI agents. 11 tools, Postgres + pgvector, multi-strategy retrieval. Works with Claude Code, Cursor, Codex, and any MCP client.
Institutional technical memory for AI coding agents using PostgreSQL, pgvector, hybrid search, MCP, Reflect, CLI, and local UI.
Commerce SDK for AI agents — sessions, managed auth, Complete Loop orchestration for Latin American APIs
PgShift vector — semantic search and hybrid search via pgvector.