DeepStudy AI automates research, refines queries dynamically, and generates high-quality reports—all while leveraging the power of cutting-edge AI models
# 🔍 DeepStudy AI DeepStudy AI is an advanced research assistant that helps generate comprehensive reports based on a given topic. By leveraging AI models like DeepSeek, Llama3, Gemma2, and DeepSeek (via OpenRouter and Groq), this system refines research queries, performs web searches, and compiles structured reports with relevant insights. ## 📸 Preview <p> <img src="./public/demo1.png" alt="img-demo1"></img> <img src="./public/demo2.png" alt="img-demo2"></img> </p> ## 🧠 AI-Driven Research Workflow <p> <img src="./public/AI Agent WorkFLow.png" alt="workflow"></img> </p> DeepStudy AI follows an iterative research process: 1. **Topic Input & Clarification** – Users enter a topic, and the system generates follow-up questions to improve research quality. 2. **Research Plan Generation** – Based on user input, it formulates a research strategy. 3. **Web Search (Exa AI API)** – Queries are optimized and executed to fetch relevant content. 4. **Content Extraction & Filtering** – Retrieved data is analyzed for relevance. 5. **Iterative Research Loop** – If necessary, the system refines queries and repeats searches to enhance report quality. 6. **Report Generation** – A structured and well-researched report is compiled. ## 🚀 Key Features - 🔧 **Fully Customizable Research Flow** - 🔍 **Adaptive Search Queries** for better results - ⚙️ **Seamless AI Model Integration** (DeepSeek, Llama3, Gemma2, DeepSeek) - 💼 **Modular & Scalable Architecture** - 🌐 **Built with Next.js & Vercel AI SDK** - ♻️ **Iterative Research Process** for accuracy ## 🛠️ Tech Stack - **Framework**: Next.js - **Styling**: Tailwind CSS, Shadcn UI - **AI Integration**: Vercel AI SDK - **LLMs**: DeepSeek, DeepSeek, Llama3, Gemma2 (via OpenRouter & Groq) - **Web Search**: Exa Search API - **Language**: TypeScript ## 📌 Prerequisites Before getting started, ensure you have: - An **OpenRouter API Key** (or alternative LLM providers like Groq) - An **Exa Search API Key** ## 🔧 Setup Instruction
HAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型