A Collection of Pydantic Models to Abstract IRL
-
Updated
Dec 10, 2025 - Python
A Collection of Pydantic Models to Abstract IRL
Design patterns and reference implementations for autonomous AI agent systems. ReAct, tool-use, memory management, fallback, and multi-agent orchestration.
🤖 An AI-powered DevOps agent implementing ReAct architecture to automate mobile release pipelines (Crash Check -> Perf -> Build -> Audit). Built with LangGraph & Ollama.
AI agents for genomics
🤖 Intelligent, secure, and multilingual chatbot backend for Lorenzo Maiuri's website. Built with FastAPI, Gemini LLM, LlamaIndex, and MongoDB. Features session memory, tool-calling, and robust security
🔎 AI Search Agent powered by LangChain and Llama-3.3 (Groq). Uses ReAct reasoning to perform real-time web, Wikipedia, and ArXiv searches with a transparent Chain-of-Thought UI.
Autonomous security investigation agents with ReAct reasoning and tool calling
A self-reflective LLM agent with tools, memory, and reasoning built using LangChain + ReAct + Reflexion. Modular FastAPI backend + Streamlit UI.
Intelligent weather agent powered by LLM and MCP protocol. Provides real-time weather data, forecasts and historical information through natural language queries using Groq, LangChain and multi-API orchestration.
Autonomous multimodal AI agent for Linux. Features a dynamic visual grid overlay for high-precision GUI automation using Llama 3 Vision, Groq, and Python.
An autonomous Data Engineering AI agent built from scratch in Python using the ReAct pattern for dynamic SQL generation and data exploration.
Production ReAct (Reasoning + Acting) agent framework with 20+ built-in tools — calculator, web search, code executor, file manager, API caller and database query
ReAct pattern implementation — build step-by-step reasoning AI agents with tool use
Add a description, image, and links to the react-pattern topic page so that developers can more easily learn about it.
To associate your repository with the react-pattern topic, visit your repo's landing page and select "manage topics."