samples
Agent samples built using the Strands Agents SDK.
claude mcp add --transport stdio strands-agents-samples node \ --env PLACEHOLDER="No MCP server command defined for this repository. Configure as needed."
How to use
The Strands Agents Samples repository provides demonstrative Python and TypeScript examples that showcase how to build and run AI agents using the Strands Agents SDKs. The Python side uses the strands-agents package to instantiate an Agent and issue prompts, while the TypeScript side demonstrates creating an Agent with the strands-agents-sdk and invoking it to obtain responses. These samples are intended for learning, experimentation, and as a reference for integrating the SDKs into your own applications. To get started, explore the Python and TypeScript tutorials and adapt the patterns to your use cases, such as multi-agent coordination, retrieval-augmented generation, or simple conversational assistants.
How to install
Prerequisites:
- Python 3.10 or higher with pip
- Node.js 18 or higher with npm or yarn
Python setup (per Python samples):
- Create and activate a virtual environment:
python -m venv venv
# On macOS/Linux:
source venv/bin/activate
# On Windows:
venv\Scripts\activate
- Install the Python packages used in the samples:
pip install strands-agents strands-agents-tools
- Run or try the Python snippet from the tutorials (e.g., creating an Agent and sending a message).
TypeScript setup (per TypeScript samples):
- Ensure Node.js is installed (v18+).
- Install the SDK package:
npm install @strands-agents/sdk
- Run the TypeScript example or tutorial files using ts-node or build with your preferred workflow.
General tips:
- Review the tutorials under 01-tutorials for Python and the TypeScript tutorials for starter examples.
- Configure any required model providers or API keys as indicated by the tutorials or the referenced documentation links in the repository.
Additional notes
Tips and common issues:
- Ensure Python and Node environments are isolated (virtualenv for Python, project-local node_modules).
- For Python, verify pip is available and network access is unrestricted when installing dependencies.
- Some samples may require additional configuration for model providers or API access; follow the Model Provider Setup guidance linked in the repository.
- When running tutorials, environment variables for API keys or endpoints may be necessary; use a .env file or export variables as appropriate.
- This repository focuses on educational demos and is not intended for production use without applying security and robustness enhancements.
Related MCP Servers
bytebot
Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, operating within a containerized Linux desktop environment.
sdk-python
A model-driven approach to building AI agents in just a few lines of code.
ag2
AG2 (formerly AutoGen): The Open-Source AgentOS. Join us at: https://discord.gg/sNGSwQME3x
koog
Koog is the official Kotlin framework for building predictable, fault-tolerant and enterprise-ready AI agents across all platforms – from backend services to Android and iOS, JVM, and even in-browser environments. Koog is based on our AI products expertise and provides proven solutions for complex LLM and AI problems
tools
A set of tools that gives agents powerful capabilities.
sdk-typescript
A model-driven approach to building AI agents in just a few lines of code.