awslabs / awslabs/agentcore-samples
Amazon Bedrock AgentCore Samples - [Add Cost Optimization Agent use case]
- Dominant language
- Python
- Stars
- 3.4k
- Forks
- 1.3k
- Avg merge
- 1d 22h
- Merged PRs (30d)
- 30
Description
**Describe the tutorial request**
A clear and concise description of what is being requested.
```
Add a Cost Optimization Agent use case to the 02-use-cases/ directory.
This agent helps users monitor, analyze, and optimize their AWS costs through natural language conversations. It demonstrates a single-agent architecture using the Strands framework with Claude 3.5 Sonnet for intelligent tool selection.
Key Features:
- 5 cost analysis tools: anomaly detection, budget information, cost forecasting, service breakdown, and current month costs
- AWS API integrations: Cost Explorer, Budgets, and CloudWatch
- Production-ready deployment using bedrock-agentcore-starter-toolkit
- Comprehensive documentation with architecture diagrams
- Environment variable configuration for model selection
- Complete test suite for local and deployed testing
This use case provides a practical example of building a cost monitoring agent and demonstrates best practices for single-agent implementations with LLM-powered tool orchestration.
Implementation is complete and ready for PR submission.
```
**Is this feature already supported by the AgentCore service?**
- [X] Yes
- [ ] No
If `yes`, please provide any appropriate documentation link.
This use case uses standard AgentCore Runtime capabilities documented at:
https://docs.aws.amazon.com/bedrock-agentcore/
Specifically uses:
- AgentCore Runtime for agent deployment
- Strands framework integration (supported framework)
- AWS SDK integrations (Cost Explorer, Budgets, CloudWatch)
Contributor guide
Assessment
This issue has not been assessed yet.