Private, local-first AI chatbot with persistent working memory. One command install via npx.
OpenAI embeddings + sqlite-vec storage and search for mikser-io
Honcho persistent-memory plugin for pi-dashboard — settings panel, per-card actions, self-host docker lifecycle, aggregate model listing.
Lightweight RAG toolkit for pgvector — chunking, hybrid search SQL, MMR, RRF, and more. Zero runtime dependencies.
PostgreSQL + pgvector storage adapter for Open-Engram
Temporal and hierarchical memory service for LLM agents — knowledge graph, episode segmentation, semantic deduplication, and efficient retrieval.
AI SDK extension plugin for YouTube transcript vector embeddings with semantic search and RAG queries.
Invite-only multi-user knowledge spaces with Markdown sync, graph navigation, media transcription, and handwriting blocks.
Community-based error knowledge sharing for OpenCode
Augur HTTP API server. Drop-in Fastify wrapper around @augur-rag/core with OpenAPI docs and trace explorer compatibility.
Shared memory for AI coding agents. Store, recall, and learn across tools, sessions, and teams.
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.
Self-hosted, local-first MCP server for agent memory backed by PostgreSQL + pgvector
Universal Reranker Node for n8n - supports vLLM, LocalAI, Infinity, Cohere and custom endpoints
Production-ready AI Assistant Server with advanced RAG (chunk-based semantic search + adjacent retrieval), conversation management, real-time communication, and human agent handoff
Compile-time-checked raw SQL for TypeScript + PostgreSQL. Inspired by sqlx.
Node.js SDK for CoMemo
Automatically index OpenCode, Claude Code, Cursor, VS Code, Codex, and Gemini CLI sessions into a shared sqlite-vec vector database for semantic search across your AI coding history
Long-term memory layer for AI agents — facade package
SDK for Brainbase — the knowledge graph API for AI agents with Neo4j graph intelligence
A lightweight, high-performance brain/memory system for AI Agents, powered by Bun
Always-on Node.js service bridging Telegram messaging to Claude AI with knowledge graph, journal, project management, and semantic search.
Strapi v5 plugin for vector embeddings with OpenAI and Neon PostgreSQL. Enables semantic search, RAG chat, and MCP (Model Context Protocol) integration.
AI agent Postgres vector store tool with vector search and custom SQL capabilities