samples and sdk-python
The SDK provides the framework for building agents while the samples demonstrate practical implementations of that framework, making them complements designed to be used together—the samples serve as reference implementations and learning resources for developers using the SDK.
About samples
strands-agents/samples
Agent samples built using the Strands Agents SDK.
Demonstrates model-driven agent development across Python and TypeScript SDKs with production deployment patterns (Lambda, Fargate, AgentCore) and industry-specific use cases. Examples cover multi-agent systems, streaming, agentic RAG, AWS service integrations, and edge deployments including robotics. The repository organizes samples from fundamentals through evaluation frameworks and full-stack UX applications.
About sdk-python
strands-agents/sdk-python
A model-driven approach to building AI agents in just a few lines of code.
Supports multiple LLM providers (Bedrock, OpenAI, Gemini, Ollama, etc.) with native Model Context Protocol (MCP) integration for accessing thousands of pre-built tools. Features a customizable agent loop with Python decorator-based tool definitions, hot-reloading from directories, and bidirectional streaming for real-time interactions.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work