Star 总榜

A rag application to chat with your documents with the help of gemini, pinecone and Next.js

Production-ready Retrieval Augmented Generation (RAG) system with hybrid retrieval, advanced evaluation metrics, and monitoring. Build enterprise LLM applications with reduced hallucinations, better context management, and comprehensive observability.

For your repository, issuedigger will notify authors of new issues about similar, previously submitted ones, saving manual digging. Implemented as a single, AI-enabled Cloudflare Worker.

Learn TypeScript chatting effortlessly with AI

Miscellaneous codes and writings for MLOps

Add different kinds of data: Youtube videos, PDFs, Internet links and ask questions based on the content provided using an intuitive UI.

Decentralized memory-sharing protocol for AI agent

The Facial Recognition Based Attendance System is an automated solution designed to streamline attendance management in educational institutions. By utilizing advanced facial recognition technology, the system eliminates manual attendance processes, reduces proxy attendance, and provides real-time attendance tracking with comprehensive reporting .

Explore cutting-edge Redis capabilities for Vector Similarity Search, Hybrid Search (Vector Similarity + Meta Search), Semantic Caching, and an advanced RAG model integrated with a Language Model (LLM) Chatbot. Unlock the full potential of Redis as a vector database with this comprehensive showcase of powerful features.

A Multi-Agent RAG platform using Vector DBs and AI models to accurately answer AML/CFT compliance queries.

Embeddable vector database for Rust and Python. HNSW indexing, metadata filtering, hybrid search, and snapshots. The SQLite of vector search.

This project implements RAG using OpenAI's embedding models and LangChain's Python library

The in-browser vector store that remembers — a Rust→WASM HNSW engine that persists to OPFS and stays consistent across tabs. Private, offline semantic search in 3 lines.

Rules you can enforce, state you can derive, context you can query: plain files in your repo, under whichever coding agent you use.

🔒 Privacy-first MCP server for Claude using PostgreSQL + Ollama. Local alternative to cloud-based code context with full data sovereignty. No API keys, no external calls, 100% local.

A clean, modular implementation of an Agentic RAG (Retrieval-Augmented Generation) system built with a production-ready architecture.

A low-token visual evidence compiler for text-only coding agents. Convert images into compact Visual Evidence Packets (VEP) for DeepSeek, Codex, Claude Code, and other text-only models.

It is a voice bot based on LLM.

AI-powered multimodal chat app with real-time responses, file support, token tracking, and dark mode. Built with Next.js. Open source under MIT.

Finalist at Brainhack TIL 2024: Team 12000SGDPLUSHIE