tylerprogramming/ai

This repository will have different projects using AutoGen and Tutorials

What it solves

This repository provides a centralized, up-to-date collection of code examples for modern AI agent frameworks. It solves the problem of keeping pace with rapid changes in the AI ecosystem by offering tested, current implementations for frameworks like AutoGen, CrewAI, and PydanticAI, ensuring developers have working code that reflects the latest library versions.

How it works

The repository is organized into distinct categories: frameworks, standalone mini-projects, third-party integrations, and utility tools. Each project is self-contained with its own requirements file. The code is regularly smoke-tested and updated to align with specific framework versions (as of October 2026), providing a reliable reference for implementing features like agent monitoring, web scraping, and conversational flows.

Who it’s for

This project is for developers and AI enthusiasts who want to learn how to build with AI agents. It is particularly useful for those following the TylerReedAI YouTube channel who need the source code demonstrated in videos, or for anyone looking for practical, copy-pasteable examples to jumpstart their own agentic applications.

Highlights

  • Up-to-date Framework Examples: Includes current implementations for AutoGen v0.7+, CrewAI v1.15+, PydanticAI v2.x, and Smolagents v1.26.
  • Claude Skill Builder: Features a specialized skill for Claude Code that automatically scaffolds new AI agent projects with best practices.
  • Diverse Integrations: Contains practical examples for connecting agents with tools like Google Drive, Supabase, and n8n.
  • Utility Tools: Includes ready-to-use utilities such as web scrapers (crawl4ai) and repository image generators.
  • Verified Code: All projects are smoke-tested to ensure they work with the specified library versions.

Related

  • Project
    Sec-Link/Argus-Agentic-SOC-Platform

    Argus is an open‑source AI‑enhanced SOC platform. It combines a Next.js UI, Django/DRF backend, PostgreSQL (optional Elasticsearch), and an AI assistant that can answer incident queries and invoke tools via a JSON‑RPC “MCP” registry. Features include alert ingestion, Sigma‑style detection, ticketing, CMDB asset linking, workflow automation, and deployment via Docker‑Compose or Kubernetes.

  • Project
    Ricky-7-Yan/intelligent-audit-system

    An enterprise AI Agent workbench for audit delivery that automates evidence retrieval, control testing, and remediation within a traceable and evaluatable workflow.

  • Project
    composio-community/secure-openclaw

    A personal 24/7 AI assistant that integrates Claude or Opencode with messaging platforms like WhatsApp and Telegram to provide tool access and persistent memory.

  • Project
    hardness1020/learn-agent-architecture

    A structured, code-first educational resource that explains how to build the 'harness'—the software infrastructure required to turn LLMs into functional, autonomous AI agents.