Framework Crash Courses
Available
6.1 Agent Lifecycle Callbacks
Autonomous ReAct Agent Loop•Beginner
61agentlifecyclecallbacks/ ├── agent.py # Agent with lifecycle callbacks ├── app.py # Streamlit web interface └── README.md # This file.
Architecture Taxonomy Node
Framework Crash Courses
Structured tutorials exploring OpenAI Agents SDK, Google ADK, Smolagents, LangGraph, and CrewAI.
Showing 38 curated projects
← Back to all categories
Framework Crash Courses
Available
6.2 LLM Interaction Callbacks
Autonomous ReAct Agent Loop•Beginner
62llminteractioncallbacks/ ├── agent.py # Agent with LLM interaction callbacks ├── app.py # Streamlit web interface └── README.md # This file.
Framework Crash Courses
Available
Advanced Handoffs
Autonomous ReAct Agent Loop•Beginner
Demonstrates advanced handoff configuration including callbacks, structured inputs, and custom tool naming. cp ../env.example .env from agent import main.
Framework Crash Courses
Available
OpenAI SDK: Agents as Tools
Autonomous ReAct Agent Loop•Beginner
Demonstrates advanced orchestration patterns where agents are used as tools by other agents. cp ../env.example .env from agents import Runner.
Framework Crash Courses
Available
OpenAI SDK: Multi-Agent Delegation
Multi-Agent Hierarchical Collaboration•Beginner
Demonstrates advanced orchestration patterns where specialized agents are used as function tools by orchestrator agents. cp ../env.example .env.
Framework Crash Courses
Available
Basic Handoffs
Autonomous ReAct Agent Loop•Beginner
Demonstrates fundamental agent-to-agent task delegation using the OpenAI Agents SDK handoff system. cp ../env.example .env from agent import main.
Framework Crash Courses
Available
Built-in Tools
Autonomous ReAct Agent Loop•Beginner
Google ADK provides powerful pre-built tools that are optimized for performance and reliability. These tools integrate seamlessly with Gemini models and provide essential capabilities like web search and code execution.
Framework Crash Courses
Available
Built-in Tools Agent
Autonomous ReAct Agent Loop•Beginner
Demonstrates using OpenAI Agents SDK built-in tools like WebSearchTool and CodeInterpreterTool. cp ../env.example .env from agents import Runner.
Framework Crash Courses
Available
Conversation Management
Autonomous ReAct Agent Loop•Beginner
Demonstrates manual conversation threading with toinputlist() and automatic management with Sessions. cp ../env.example .env from agent import manualconversationexample, sessionconversationexample.
Framework Crash Courses
Available
Custom Tracing
Multi-Agent Hierarchical Collaboration•Beginner
Demonstrates advanced tracing patterns including custom traces, spans, and workflow organization for complex multi-agent systems. cp ../env.example .env.
Framework Crash Courses
Available
Customer Support Ticketing Agent with Structured Output
Autonomous ReAct Agent Loop•Beginner
cd 31customersupportticketagent 4. The response will be a structured JSON with all ticket details.
Framework Crash Courses
Available
Default Tracing
Autonomous ReAct Agent Loop•Beginner
Demonstrates the built-in automatic tracing system that captures all agent workflow events without any setup required. cp ../env.example .env.
Framework Crash Courses
Available
Email Generation Agent with Structured Output
Autonomous ReAct Agent Loop•Beginner
4. The response will be a structured JSON with subject and body fields.
Framework Crash Courses
Available
Execution Methods
Autonomous ReAct Agent Loop•Beginner
Demonstrates the three execution methods available in the OpenAI Agents SDK: sync, async, and streaming. cp ../env.example .env from agents import Runner.
Framework Crash Courses
Available
Function Tools
Autonomous ReAct Agent Loop•Beginner
def calculatecompoundinterest(principal: float, rate: float, years: int) -> dict: Calculate compound interest for an investment. Use this function when users ask about investment growth.
Framework Crash Courses
Available
Function Tools Agent
Autonomous ReAct Agent Loop•Beginner
Demonstrates custom function tools creation using the @functiontool decorator. cp ../env.example .env from agents import Runner from agent import rootagent.
Framework Crash Courses
Available
Multi Sessions
Autonomous ReAct Agent Loop•Beginner
Demonstrates managing multiple concurrent sessions for different users, contexts, and conversation types. cp ../env.example .env from agent import multiusersessions, contextbasedsessions.
Framework Crash Courses
Available
Parallel Execution
Autonomous ReAct Agent Loop•Beginner
Demonstrates running multiple agents simultaneously using asyncio.gather() for improved performance and quality through diversity. cp ../env.example .env.
Framework Crash Courses
Available
Personal Assistant Agent
Autonomous ReAct Agent Loop•Beginner
A basic personal assistant agent demonstrating the fundamental concepts of agent creation with the OpenAI Agents SDK. cp ../env.example .env from agents import Runner.
Framework Crash Courses
Available
Product Review Agent
Autonomous ReAct Agent Loop•Beginner
A complex structured output agent demonstrating advanced Pydantic schemas for product review analysis. cp ../env.example .env from agents import Runner.
Framework Crash Courses
Available
Support Ticket Agent
Autonomous ReAct Agent Loop•Beginner
A structured output agent demonstrating Pydantic schema-based responses for customer support ticket creation. cp ../env.example .env from agents import Runner.
Framework Crash Courses
Available
Tutorial 1: Your First ADK Agent
Autonomous ReAct Agent Loop•Beginner
An ADK agent is a programmable AI assistant that can: Think of it as creating a smart function that uses AI to handle complex tasks. The main building block for creating AI agents in ADK.
Framework Crash Courses
Available
Tutorial 1: Your First OpenAI Agent
Autonomous ReAct Agent Loop•Beginner
An OpenAI agent is a programmable AI assistant that can: Think of it as creating a smart function that uses AI to handle complex tasks.
Framework Crash Courses
Available
Tutorial 2: Model-Agnostic Agent
Autonomous ReAct Agent Loop•Beginner
Learn how to create agents that work with different AI models using OpenRouter. This example shows how ADK can use OpenAI and Anthropic models through separate agent implementations.
Framework Crash Courses
Available
Tutorial 2: Structured Output Agent
Autonomous ReAct Agent Loop•Beginner
Traditional AI responses are unstructured text, making them difficult to process programmatically. Structured outputs solve this by: ┌─────────────────────────────────────────────────────────────┐.
Framework Crash Courses
Available
Tutorial 3: Tool Using Agent
Autonomous ReAct Agent Loop•Beginner
Tools are functions that your agent can call to perform specific tasks. Think of them as the agent's "hands" - they allow the agent to: ┌─────────────────────────────────────────────────────────────┐.
Framework Crash Courses
Available
Tutorial 4: Running Agents
Autonomous ReAct Agent Loop•Beginner
When you call any Runner method, the SDK executes a sophisticated loop that handles the complete agent workflow: ┌─────────────────────────────────────────────────────────────┐.
Framework Crash Courses
Available
Tutorial 5: Context Management
Autonomous ReAct Agent Loop•Beginner
Context management allows you to pass custom data structures to your agents that persist throughout the entire agent execution. Think of context as a shared state container that.
Framework Crash Courses
Available
Tutorial 6.3: Tool Execution Callbacks
Autonomous ReAct Agent Loop•Beginner
Tool execution callbacks allow you to monitor when agents use tools, track their execution lifecycle, and analyze the results. This provides visibility into how agents interact with external systems and APIs.
Framework Crash Courses
Available
Tutorial 6: Guardrails & Validation
Autonomous ReAct Agent Loop•Beginner
Guardrails are automated safety mechanisms that validate inputs and outputs to ensure AI agents operate within acceptable boundaries. Think of guardrails as safety checkpoints that.
Framework Crash Courses
Available
Tutorial 7: Plugins
Autonomous ReAct Agent Loop•Beginner
Plugins in Google ADK are custom code modules that can be executed at various stages of an agent workflow lifecycle using callback hooks. Unlike regular callbacks that are configured on individual agents or tools, plugins are registered...
Framework Crash Courses
Available
Tutorial 8: Handoffs & Delegation
Autonomous ReAct Agent Loop•Beginner
Handoffs enable agent specialization and delegation where agents can transfer tasks to other agents with specific expertise. Think of handoffs as a smart routing system that.
Framework Crash Courses
Available
Tutorial 8: Simple MultiAgent Researcher (Runs with ADK)
Autonomous ReAct Agent Loop•Beginner
A coordinator LlmAgent orchestrates three specialized agents in a sequential workflow: Research → Summarize → Critique. Each agent contributes to building a comprehensive research report.
Framework Crash Courses
Available
Tutorial 8: Tracing & Observability
Autonomous ReAct Agent Loop•Beginner
Tracing provides comprehensive workflow monitoring that automatically captures every event during agent execution: ┌─────────────────────────────────────────────────────────────┐.
Framework Crash Courses
Available
Tutorial 9.1: Sequential Agents - Business Implementation Plan Generator
Autonomous ReAct Agent Loop•Beginner
Business Topic → SequentialAgent → 4 Sub-agents (Sequential Execution) [Market Research + Web Search] → [SWOT Analysis] → [Strategy] → [Implementation].
Framework Crash Courses
Available
Tutorial 9.2: Loop Agents - Iterative Plan Refiner
Autonomous ReAct Agent Loop•Beginner
Topic → LoopAgent → [Refine Plan] → [Increment Iteration] → [Check Completion] ↑ │ └──────────────────────────── Repeat until stop ─────────┘.
Framework Crash Courses
Available
Tutorial 9.3: Parallel Agents - Market Snapshot Team
Multi-Agent Hierarchical Collaboration•Beginner
According to the ADK docs, Parallel Agents execute their sub-agents concurrently. Each child runs on its own invocation branch but shares the same session.state.
Framework Crash Courses
Available
Tutorial 9: Multi-Agent Orchestration
Multi-Agent Hierarchical Collaboration•Beginner
Multi-agent orchestration enables coordinated AI workflows where multiple specialized agents work together to solve complex problems. Think of orchestration as a conductor leading an orchestra where.