🔗 Simplify vector database operations with CrossVector, a unified Python library for seamless integration and flexible backend switching.

🛠 Build enterprise-grade AI agents with MaxKB, an open-source platform designed for simplicity and performance.

🌐 Scrape and visualize job listings from company career pages and ATS boards with a streamlined dashboard for easy access to the newest opportunities.

Open-source RAG engine for ingesting, indexing, and querying unstructured documents

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

This is the public release of MIRA OS. Discrete memories decay through momentum loss, tools auto-configure when dropped into tools/ folder, and the system prompt composes from modular trinkets. I would like to think I've made an elegant brain-in-box. You load it and send cURL requests - it talks back, learns, and uses tools. Contributions welcome.

The Postgres-Native Search Replica - Decouple your vector workloads via native Logical Replication and serve high-performance Hybrid Search without touching your primary's CPU

An end-to-end ETL pipeline and RAG system for searching and analyzing Kinda Funny video content.

Semantic knowledge graph navigation for Obsidian or markdown vaults using AI-powered vector embeddings and PostgreSQL+pgvector

Hybrid hierarchical RAG with keyword search (Postgres FTS), semantic re-ranking (pgvector), and evals in CI. UI lets users chat with Dwarkesh Patel episodes via multi-query RAG.

Local-first document archive assistant for semantic search and RAG using local LLMs and embeddings.

Plataforma Multi-tenant para orquestación de Agentes de IA en WhatsApp. Incluye RAG (Búsqueda Vectorial), gestión de dominios (Salud, E-commerce, Créditos) y panel de administración en Streamlit.

⚡ Next-gen orchestration for building and scaling intelligent conversational AI.

Permission-aware RAG KB chatbot using FastAPI + Streamlit. Docs are embedded and stored in Postgres (pgvector). Retrieval is filtered by user access level and sent to a Ollama LLM to generate grounded answers with citations. Fully containerized with Docker Compose.

Persistent conversational memory for AI via MCP — built by humans and AI, for humans and AI.

Production-ready RAG system starter kit with local LLM inference, hybrid search, and intelligent document processing - deploy AI that learns from your knowledge base in minutes.

A LangChain-based agent using Ollama for local LLM inference and PostgreSQL for embeddings, hybrid search (vector + lexical), and reranking.

🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL

YouTube Playlist Summarizer Backend