Model-agnostic plug-n-play LangChain/LangGraph agents powered entirely by MCP tools over HTTP/SSE.

Local LLM ReAct Agent with Guidance

DocChat is an AI-powered Multi-Agent RAG system using Docling for structured document parsing and BM25 + vector search retrievers to retrieve fact-checked answers from PDFs, DOCX, and text files, preventing hallucinations. 🚀

An AI-driven tool integrating Abaqus and OpenAI's LLM for automating finite element simulations, including input file generation, job execution, stress extraction, parametric studies, and sensitivity analysis, streamlining complex workflows for enhanced decision-making.

A LLM based agent that interacts with user calls as a receptionist for scheduling bookings integrated with Gmail, Calendar etc

Chat-React-CSV-Bot is a sophisticated conversational agent engineered with OpenAI's GPT-3.5 model and React agent. This project integrates natural language processing capabilities to develop a chatbot adept at comprehending and generating responses to user inquiries.

Implementing LangChain concepts and building meaningful stuffs

This project is a modular AI chatbot framework that allows dynamic interaction with multiple LLM providers using LangGraph, LangChain, Streamlit, and FastAPI. It also optionally integrates search tools such as Tavily for online augmentation.

Automated Market Researcher

An AI-powered full-stack web app that helps startup founders, investors, and professionals quickly research a company and prepare for meetings.

AI agents and Agentic AI projects - ReAct agents , Reflection Agents(Generator + Reflector) etc.

Inspection AI Pilot (工程检测智能领航员) 这是一个面向工程检测行业的垂直领域 AI Agent 演示项目。它摒弃了传统的静态问答模式，构建了一个具备 ReAct 逻辑 的智能体。该系统能够通过 Mock API 实时拉取 IoT 检测仪器数据，并结合基于 Markdown 结构化 RAG 的国家标准库（JGJ/T 23等），自动进行数据分析、强度推算与合规性判定。项目采用 Qwen 大模型驱动，LangChain 编排，uv 进行环境管理，旨在展示大模型在“自动化报告生成”与“标准查阅”场景下的落地潜力。

LinkMind is an intelligent conversational ReAct agent built with LangChain and Streamlit. It leverages a chain-of-thought reasoning approach integrated with web search, document scraping, and FAISS-based vector search powered by Google's Gemini to deliver detailed, context-aware responses while maintaining session memory.