An open API service indexing awesome lists of open source software.

https://github.com/jritsema/agent-starter

AgentCore Demos
https://github.com/jritsema/agent-starter

agentcore agentic-ai agents bedrock

Last synced: 18 days ago
JSON representation

AgentCore Demos

Awesome Lists containing this project

README

          

# agent-starter

Simple AI agent using the [Strands Agents](https://strandsagents.com) Python library.

The agent runs locally with no dependencies on AWS except for the model calls which default to Amazon Bedrock (note that the model can be changed).

## Run locally

The following commands will create a Python virtual environment, install all required Python packages, and then start the HTTP API server. Note that these commands require [direnv](https://direnv.net/) which automatically activates the virtual directory whenever you change into it.

```sh
make init && make install && make start
```

To execute these steps manually, you can use the following:

```sh
python -m venv .venv
. .venv/bin/activate
pip install -r piplock.txt
python -u main.py
```

To test the local API, run:

```sh
python client.py
```

## Deploy to Amazon Bedrock AgentCore Runtime

To deploy the agent to [AgentCore Runtime](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/agents-tools-runtime.html) using Terraform, run:

```sh
kiro-cli chat --agent deploy -a "deploy this agent to aws"
```

If you prefer using a tool other than [Amazon Q CLI](https://docs.aws.amazon.com/amazonq/latest/qdeveloper-ug/command-line.html), you can use the prompt [here](./.amazonq/cli-agents/deploy.json).

## Dependencies

To run local:
- Python 3.13

To deploy to AWS:
- AWS credentials
- Docker
- Terraform

## Development
```
Choose a make command to run

init initialize a new python project
install add a new package (make install ), or install all project dependencies from piplock.txt (make install)
start run local project
test test the local api
```

Generated by https://github.com/jritsema/cookiecutter-python