MCP server providing semantic code search and indexing for git repositories
PostgreSQL Model Context Protocol (MCP) server - JavaScript implementation
A simple example showing how to do metadata extraction with RAG using Mastra, OpenAI, and PGVector.
Core indexing and search functionality for h-codex
Enhanced MCP server with multi-query search, hybrid search, and collections for MAGMA computational algebra system
Gravitas — temporal semantic memory for agentic systems. A gravit is the atomic unit of weighted, time-bound knowledge.
CMMV module for LLM integration, tokenization, RAG dataset creation, and fast FAISS-based vector search for code indexing.
RAG abstraction layer for AI Kit (documents, chunking, embeddings, vector stores).
RAG vector index helpers for HNSW and IVFFlat
Cloud providers for CogxAI — Supabase storage + Voyage AI embeddings
Unforget memory plugin for OpenClaw — zero-LLM, 4-channel retrieval, zero config
Long-term session memory for Claude Code. Captures every transcript, indexes events in TimescaleDB, and auto-injects relevant history into every new prompt. Multi-tier retrieval with a SQL-only fast path; rationale synthesis compresses turns into searchab
AI chat assistant widget for the Vendure admin dashboard — adds a floating chat panel to the React-based Vendure 3.x dashboard
Core indexing engine for Claude Context Local (PostgreSQL + Ollama)
Zero-dependency, in-memory vector database for AI Agents. Supports Cosine Similarity and Persistence.
MemWal — Privacy-first AI memory SDK with Ed25519 delegate key auth
Continuum delivery CLI for status, UI, Claude plugin install, and Codex launch.
Local MCP server for Claude Context using PostgreSQL and Ollama
One Postgres API. Two modes. Real PostgreSQL (pg) for production, PGlite (in-process WASM) for standalone / dev. Same SQL, same query shape, drop the server when you don't need it.
A simple example showing how to optimize information density with RAG using Mastra, OpenAI, and PGVector.
A simple example showing how to do metadata extraction with RAG using Mastra, OpenAI, and PGVector.
EpistemicDB server — HTTP + WebSocket API for the epistemic database
Core routing and query intelligence for SymbioseDB
<p align="center"> <a href="http://nestjs.com/" target="blank"><img src="https://nestjs.com/img/logo-small.svg" width="120" alt="Nest Logo" /></a> </p>