{"id":4455,"library":"bedrock-agentcore-starter-toolkit","title":"Bedrock AgentCore Starter Toolkit","description":"The Bedrock AgentCore Starter Toolkit is a Python CLI toolkit designed to simplify the deployment of AI agents to Amazon Bedrock AgentCore Runtime. It enables developers to take Python-based agent logic (e.g., built with Strands Agents or LangGraph) and deploy it to AWS with minimal infrastructure management. The library is currently at version 0.3.5 and undergoes rapid development with frequent patch releases. While still active for existing Python workflows, AWS now recommends using the `@aws/agentcore-cli` (an npm-based CLI) for new projects due to its broader framework support and features.","status":"active","version":"0.3.5","language":"en","source_language":"en","source_url":"https://github.com/aws/bedrock-agentcore-starter-toolkit","tags":["AWS","Amazon Bedrock","AI Agents","CLI","Deployment","Generative AI","Serverless"],"install":[{"cmd":"pip install bedrock-agentcore-starter-toolkit==0.3.5","lang":"bash","label":"Install latest version"}],"dependencies":[{"reason":"Required Python version.","package":"python","optional":false,"min_version":"3.10"},{"reason":"AWS SDK for Python, essential for interacting with AWS services including Bedrock AgentCore.","package":"boto3","optional":false},{"reason":"The core Python SDK for building Bedrock AgentCore applications, used to define agents.","package":"bedrock-agentcore","optional":false},{"reason":"Commonly used agent framework in quickstart examples, though other frameworks (LangGraph, etc.) are supported.","package":"strands-agents","optional":true}],"imports":[{"note":"This class is used to wrap your agent's Python logic, making it deployable to the Bedrock AgentCore Runtime. The starter toolkit CLI then interacts with this wrapped application.","symbol":"BedrockAgentCoreApp","correct":"from bedrock_agentcore.runtime import BedrockAgentCoreApp"}],"quickstart":{"code":"import os\nfrom bedrock_agentcore.runtime import BedrockAgentCoreApp\n\ndef my_agent_logic(request):\n    \"\"\"\n    Processes an incoming request for the AI agent.\n    \"\"\"\n    prompt = request.get(\"prompt\", \"Hello from AgentCore!\")\n    # Simulate agent processing or integrate with an LLM\n    response_content = f\"The agent received your prompt: '{prompt}'.\"\n    return {\"response\": response_content}\n\napp = BedrockAgentCoreApp()\n\n@app.entrypoint\ndef production_agent(request):\n    \"\"\"\n    The entrypoint function for the Bedrock AgentCore Runtime.\n    This function wraps your core agent logic.\n    \"\"\"\n    return my_agent_logic(request)\n\nif __name__ == \"__main__\":\n    # This block allows local testing of the agent logic.\n    # For deployment, the `agentcore` CLI interacts with this file.\n    print(\"Starting local AgentCore development server...\")\n    print(\"Access at http://localhost:8080/invocations\")\n    app.run()\n\n# To deploy and invoke via the CLI, run these commands in your terminal:\n# 1. Save the above Python code to a file, e.g., `my_agent.py`.\n# 2. Configure your agent: `agentcore configure --entrypoint my_agent.py --name my-bedrock-agent --region us-east-1`\n#    (Ensure AWS credentials are configured, e.g., via `aws configure`)\n# 3. Launch the agent: `agentcore launch`\n# 4. Invoke the deployed agent: `agentcore invoke '{\"prompt\": \"Tell me a fun fact about Python.\"}'`","lang":"python","description":"This quickstart demonstrates how to define a simple AI agent using `bedrock_agentcore.runtime.BedrockAgentCoreApp` and then deploy it using the `agentcore` command-line interface provided by the `bedrock-agentcore-starter-toolkit`. The Python code defines the agent's logic, which the CLI toolkit then containerizes and deploys to the AWS Bedrock AgentCore Runtime. Ensure your AWS credentials are configured (e.g., using `aws configure`) and you have the necessary IAM permissions to create roles, Lambda functions, and use Bedrock AgentCore services."},"warnings":[{"fix":"For new projects, consider installing and using the `@aws/agentcore-cli` via `npm i @aws/agentcore-cli`. Refer to the official AgentCore CLI documentation for migration guides if you need to move an existing project.","message":"For all new Bedrock AgentCore projects, AWS now officially recommends using the `@aws/agentcore-cli` (an npm-based CLI) instead of this Python toolkit. This Python starter toolkit is primarily intended for existing Python-based workflows. The `@aws/agentcore-cli` offers broader framework support and features for local development.","severity":"gotcha","affected_versions":">=0.3.4"},{"fix":"Review the `CHANGELOG.md` or release notes before updating to new versions, and thoroughly test your deployments after any updates.","message":"The Bedrock AgentCore Starter Toolkit is currently in 'public preview' status. This means that APIs and functionalities may change as the SDK is refined, potentially leading to breaking changes in future minor or patch releases.","severity":"gotcha","affected_versions":"All versions"},{"fix":"Ensure your AWS CLI is configured (`aws configure`) and the IAM role used for deployment has policies allowing `bedrock:*`, `iam:*`, `ecr:*`, and `lambda:*` actions, especially `bedrock-agentcore:*` for runtime operations. Specify the `--region` argument during `agentcore configure` if not using your default AWS region.","message":"Successful deployment and invocation of agents require correctly configured AWS credentials and appropriate IAM permissions for creating roles, ECR repositories, and Bedrock AgentCore runtimes. Common issues arise from insufficient permissions or incorrectly set AWS regions.","severity":"gotcha","affected_versions":"All versions"}],"env_vars":null,"last_verified":"2026-04-12T00:00:00.000Z","next_check":"2026-07-11T00:00:00.000Z"}