Build and run agents you can see, understand and trust.

LLM-powered Agent Runtime with Dynamic DAG Planning & Concurrent Execution

Lightweight Python SDK for LLMs with unified API across 9 providers. Built-in ReAct & Plan-Execute agents, streaming, native tool calling, context injection, structured outputs, and observability.

The minimal AI agent engine

🤖 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.

Thoth - Personal AI Sovereignty

A simple ReAct agent that has access to LlamaIndex docs and to the internet to provide you with insights on LlamaIndex itself.

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.

Ship customer-facing AI with isolation, spend controls, and provenance.

基于大模型 (LLM) ，智能体(Agent)与 RAG 技术的智能口岸物流助手。通过 Agent 自动调度查询工具与检索法规知识库，为港口用户提供通关异常诊断与决策支持。

React AI Agent with Long-Term Memory and Tool calling

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.

multi agent orchestrator

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

This repository contains a Python application using LangChain to create a multi-agent system for answering queries with Yahoo Finance News and Wikipedia

A production-ready GenAI application built using LangGraph ReAct Agents, FastAPI, and Streamlit. This project demonstrates how to set up an end-to-end agentic chatbot system with backend + frontend integration.

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.

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.

Handcrafted ReAct Agent Engine | Supports FS / web page / weather query + code sandbox, including observability + visualization tools, focusing on circular thinking detection and task quality optimization

Built an AI Junior Data Scientist agent using LangChain AgentExecutor, Ollama, and FastAPI on a 10k‑row bank‑churn dataset; automated EDA and baseline modeling (logistic regression) and served results via a REST API with latency and usage metrics, achieving ~0.82 accuracy on held‑out customers.