PostgreSQL storage backend for Bentley (with pgvector support)
PostgreSQL + pgvector backend for db0. Native hybrid vector search, cross-device memory sync for AI agents.
Adaptive retrieval orchestration for RAG and semantic search in TypeScript: per-query routing across vector / BM25 / hybrid + cross-encoder reranking, with full traces. Works with pgvector, Pinecone, Turbopuffer, or any custom adapter.
PostgreSQL adapter for @kgensearch — tsvector + pgvector, up to 100M records
MCP server for PostgreSQL vector database with semantic and full-text search capabilities using pgvector
Ollama embedding helpers with task-type prefixes and pgvector SQL literal support.
Lightweight RAG toolkit for pgvector — chunking, hybrid search SQL, MMR, RRF, and more. Zero runtime dependencies.
MCP server for knowledge base with Mastra.ai and pgvector
MCP server for Beacon — a personal, agent-readable knowledge system on Supabase + pgvector
Self-hosted, local-first MCP server for agent memory backed by PostgreSQL + pgvector
FastCar 的 PostgreSQL 组件，提供连接池、ORM 映射、事务管理、多数据源、原生 SQL 执行，以及基于 `pgvector` 的向量检索能力。
Stateful AI agent memory layer for PostgreSQL with pgvector - TypeScript-first with intelligent context management
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.
OpenClaw Plugin — Supabase pgvector long-term memory + knowledge base with auto-recall
Persistent memory for AI agents. Multi-strategy retrieval (semantic + BM25 + RRF), 3-zone cosine triage, type-aware lifecycle, entity canonicalization. Postgres + pgvector.
The samesake matcher — Hono-based HTTP service for entity resolution against PostgreSQL + pgvector. Runs match queries, persists active-learning feedback, calibrates per-scope thresholds, surfaces duplicate clusters. BYO embedding/parse functions — zero L
Search microservice — full-text, semantic (pgvector), and hybrid document search
A simple example showing how to insert your embedding in pgvector using Mastra and OpenAI.
A simple example showing how to insert your embedding in pgvector using Mastra and OpenAI.
Personal agent-readable second brain — Postgres + pgvector + MCP
PostgreSQL + pgvector storage adapter for Open-Engram
No description provided.
MCP server — agent problem/solution KB backed by Postgres + pgvector, embeddings via Ollama
NestJS library for knowledge base management with vector search — PostgreSQL (pgvector) and MongoDB backends, OpenAI embeddings, RAG retrieval