Agent Dev Toolkit banner
awslabs awslabs

Agent Dev Toolkit

AI community

Description

**A development tool for building Generative AI agents with the Strands platform**

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

Agent Development Toolkit (ADT) For Strands

**A development tool for building Generative AI agents with the Strands platform**

ADT provides a single command-line interface that lets developers build, test, and iterate on [Strands agents](https://github.com/strands-agents/sdk-python) with ease during local development. The CLI unifies agent execution, observability, UI, and local containerization into one cohesive developer experience, enabling developers to iterate and experiment faster with immediate feedback loops and streamlined workflows.


Table of Contents

  1. What is ADT?
  2. Quick Start
  3. Installation
  4. Core Commands
  5. Creating Your First Agent
  6. Development Workflow
  7. Project Structure
  8. Configuration
  9. Adding Custom Tools
  10. Built-in Tools
  11. Model Context Protocol (MCP) Integration
  12. UI and Observability
  13. Docker and Container Mode
  14. Troubleshooting
  15. Command Reference

What is ADT?

ADT (Agent Development Toolkit) is a development tool that works with the [Strands platform](https://strandsagents.com/latest/). It provides:

  • Project scaffolding - Generates agent project structure with configuration files
  • Development server - Runs agents locally with a FastAPI backend
  • Chat interface - Web UI for interacting with agents during development
  • Tool integration - Supports custom tools and MCP protocol
  • Container support - Can run the development server in Docker

What it does:

  • Generates complete agent project directories
  • Provides templates for agent configuration and tool development
  • Runs a local web server with chat interface to test agent locally
  • Auto-di