Cut LLM costs by up to 80% and unlock sub-millisecond responses with intelligent semantic caching.A drop-in, provider-agnostic LLM proxy written in Go with sub-millisecond response

Web2LLM.txt – A fast, open-source website-to-LLM context file generator. Paste any https:// URL and instantly get a clean llm.txt file with token & cost estimation—ideal for RAG, prompt engineering, and AI training workflows.

EarningsAI Demo is a powerful tool that combines audio transcription, document processing, and AI-powered analysis to help users extract insights from earnings calls and financial documents. Built with Fireworks AI and MongoDB, it provides both a command-line interface and a web application for processing and querying financial data.

Projeto de TCC para graduação em bacharelado de Ciência da Computação de uma extensão para navegadores Chromium que permite aos usuários analisar a veracidade de uma notícia com um clique.

Prism (Personal Retrieval & Insight System for Multimedia). This project is currently in progress. Offline Al-powered RAG system that links text, image & audio knowledge - built with FastAPI and local LLMs.

AI driven Content Creation Automation.

RAG Based AI-Agent that gives answers to any query related to poornima colleges(PU, PCE, PIET)

🚀 Optimize LLM usage with PromptCache, a smart middleware that cuts costs and speeds up responses by caching repetitive queries.

SUPERCORE 企业级基础设施解决方案官网。采用瑞士国际主义风格，内置 3D 可视化展示与 AI 语义搜索客服系统

AI-powered stock movement predictor that analyzes real-time financial news and market data using LLMs, RAG pipelines, and vector databases to forecast short-term stock direction. Built with LangChain, LangGraph, and reinforcement learning to continuously improve predictions from news sentiment and market signals.

Backstage Internal Developer Portal for Nivara AI — software catalog, TechDocs, scaffolder, GitHub integrations, Tech Radar, RBAC, quality scorecards, and hybrid RAG AI assistant.