AgentScope: Agent-Oriented Programming for Building LLM Applications

fullstack chat agent with authentication, request credits and payments built in

🤖 Advanced AI agent system combining ReAct reasoning and Plan-Execute strategies with unified memory, reflection patterns, and browser automation tools. Built with LangGraph, LangChain, and Google Gemini.

A pure Python implementation of ReAct agent without using any frameworks like LangChain. It follows the standard ReAct loop of Thought, Action, PAUSE, and Observation. The agent utilizes multiple tools, including Calculator, Wikipedia, Web Search, and Weather. A web UI is also provided using Streamlit.

An AI-powered investment analysis tool 📈 that leverages simple ReAct AI agent flow framework and financial analysis techniques to provide comprehensive portfolio insights. This intelligent agent helps investors make data-driven decisions by offering deep portfolio risk assessment, stock profiling, and personalized recommendations.

A minimalistic approach to building AI agents

LLM OSINT is a proof-of-concept method of using LLMs to gather information from the internet and then perform a task with this information.

ReAct (Reasoning and Acting) agent built from scratch in Python. No libraries, no abstractions, simple and straight to the point.

一个简单的AI Agent，可以通用处理各种问题

This project implements a travel chatbot powered by the RAG (Retrieve and Generate) chain, providing real-time information retrieval using various tools and the ability to fetch weather reports.

Innovative AI agent implementations using LangGraph—featuring ReAct, RAG (Corrective, Self, Agentic), chatbots, microagents, and more, with multi-AI agent systems on the horizon! 🤖🚀

A lightweight, streaming-first ReAct (Reasoning + Acting) agent that works with any LangChain-compatible model. Focus on agent logic while LangChain handles the provider complexity.

All projects done for LangChain - Develop LLM powered applications with LangChain Udemy Course

From-scratch implementation of a ReAct agent using LangChain, showcasing manual control over tool invocation, prompt design, and reasoning loop without relying on built-in abstractions.

A sample project to demonstrate how a langgraph ReAct agent can be wrapped with the A2A protocol

FOXO Agentic RAG assistant for document QA, weather-food tips, Fitbit CSV, life & nutrition.

An extensible AI personal assistant that uses a ReAct agent to call MCP-provided tools for real-time questions.

Application that generates automatic responses to Amazon Lex messages using generative AI.

Conversational Agent for YouTube Video Exploration: A conversational assistant that uses YouTube video transcripts to answer questions, provide summaries, and highlight key moments with timestamps. Ideal for efficiently navigating and understanding video content.

Jednoduchý AI agent postavený na frameworku **LangChain**, který komunikuje přes OpenAI LLM (model `gpt-4o`). Agent používá nástroje (tooly) pro vyhledávání na české Wikipedii, jednoduchou kalkulačku a aktuální počasí přes Open-Meteo API a Wolfram Alpha pro pokročilé výpočty a vědecké dotazy.