Advanced

Advanced examples covering caching, compression, concurrency, events, retries, debugging, culture, and serialization.

Example	Description
01 Create Cultural Knowledge	Create cultural knowledge to use with your Agents.
02 Use Cultural Knowledge In Agent	Use cultural knowledge with your Agents.
03 Automatic Cultural Management	Automatically update cultural knowledge based on Agent interactions.
04 Manually Add Culture	Manually add cultural knowledge to your Agents.
Advanced Compression	This example shows how to set a context token based limit for tool call compression.
Agent Serialization	Serialize and deserialize agents using to_dict/from_dict and save/load with a database.
Background Execution	Background execution allows you to start an agent run that returns immediately.
Background Execution Structured	Combines background execution (non-blocking, async) with Pydantic output_schema.
Basic Agent Events	Stream agent events including run lifecycle, tool calls, and content output.
Cache Model Response	Example showing how to cache model responses to avoid redundant API calls.
Cancel Run	Example demonstrating how to cancel a running agent execution.
Compression Events	Test script to verify compression events are working correctly.
Concurrent Execution	Concurrent Execution.
Custom Cancellation Manager	Shows how to extend BaseRunCancellationManager to implement your own.
Custom Logging	Example showing how to use a custom logger with Agno.
Debug	You can set the debug mode on the agent for all runs to have more verbose output.
Multi-Model Metrics	Track per-model token usage with memory model breakdown in metrics.details.
Culture Metrics	Track culture model token usage under the culture_model detail key.
Session Metrics	Accumulate metrics across multiple runs within a session using SessionMetrics.
Session Summary Metrics	Track session summary model token usage under the session_summary_model detail key.
Streaming Metrics	Capture metrics from streaming responses using yield_run_output=True.
Tool Call Metrics	Track tool execution timing with ToolCallMetrics on each ToolExecution.
Background Execution Metrics	Track metrics for background (async) agent runs with full token and model details.
Reasoning Agent Events	Stream agent events including run lifecycle, tool calls, and content output.
Retries	Example demonstrating how to set up retries with an Agent.
Tool Call Compression	Compress tool call history to reduce context size.
Learning Machine	Create agents that learn and improve from interactions over time.
Memory Manager	Use a MemoryManager to give agents persistent memory across sessions.
Basic Reasoning	Add chain-of-thought reasoning capabilities to agents.
Reasoning With Model	Use a separate reasoning model with configurable step limits.
Basic Skills	Basic Skills Example.
Check Style	Check Python code for style issues.
Commit Message	Validate or generate conventional commit messages.