Persistent memory and code intelligence for AI coding agents
MCP server for semantic agent selection using pgvector embeddings
Core RAG schema with pgvector support for document embeddings
Vector embeddings type for Saltcorn
Persistent knowledge memory layer for AI agents. Rust core, Postgres + pgvector backend, MCP protocol.
CogxAI — Persistent memory SDK for AI agents. Store, recall, dream, and reflect. Stanford Generative Agents architecture on Supabase + pgvector.
Common utilities and Prisma clients shared across TROFOS services. This includes * Main Prisma client for the backend database * Additional Prisma client for the vector DB (pgvector) * Shared TypeScript types, constants, and helper functions
Long-term project memory for AI agents backed by PostgreSQL and pgvector.
Universal memory SDK for Daily applications - embedded pgvector + memgraph
Semantic search MCP server for your codebase using PostgreSQL + pgvector + Ollama
Supabase storage adapter for Open-Engram with vector search via pgvector RPC
Persistent memory and code intelligence for AI coding agents
Production-ready RAG (Retrieval-Augmented Generation) framework for Next.js applications with PostgreSQL + pgvector
Library-first realtime RAG engine with pgvector and streaming generation.
A chat interface for AI coding agents — control Claude Code, Codex, Gemini CLI, OpenCode from browser and mobile
Hybrid search toolkit for Postgres (pgvector + BM25 + rerank)
Type-safe entity-resolution DSL. Declare entities, fields, scopes, and scoring channels in a TypeScript config; the matcher (samesake-server) runs the queries against PostgreSQL + pgvector. Cross-references between scoring channels and declared fields/emb
MCP server with mem0 integration for long-term memory using PostgreSQL and pgvector
Advanced n8n node for Agentic RAG with Supabase pgvector - handles structured/unstructured documents with AI-powered query refinement
MCP Knowledge Graph Memory Server with Supabase + pgvector for semantic search
A simple example showing how to optimize information density with RAG using Mastra, OpenAI, and PGVector.
PG-native long-term memory for AI agents. Turn-level embedding, hybrid RRF ranking, optional knowledge graph. MCP server, CLI, and library API.
A simple example showing how to do result re ranking with RAG using Mastra, OpenAI, and PGVector.
Postgres-backed long-term memory for the Render agent harness.