fullstack-solution-template-for-agentcore  by awslabs

Accelerated full-stack agent development on AWS

Created 1 month ago
326 stars

Top 83.9% on SourcePulse

GitHubView on GitHub
Project Summary

Summary

The Fullstack AgentCore Solution Template (FAST) by AWS Labs accelerates the deployment of production-ready, secured, web-accessible full-stack applications on Amazon Bedrock AgentCore. Designed for delivery scientists and engineers, it reduces development time from weeks to days by handling infrastructure setup and providing a baseline for "vibe-coding," allowing focus on prompt engineering and GenAI implementation.

How It Works

FAST is a starter repository providing a secured, React-based frontend connected to an AgentCore backend, agnostic to agent SDKs (Strands, LangGraph) and coding assistants. Its architecture uses AWS Cognito for robust authentication across frontend, AgentCore Runtime, Gateway, and API Gateway. Infrastructure is managed via AWS CDK with Amplify hosting. Best practices are codified in documentation to guide AI coding assistants for customization and ensure security/architectural standards.

Quick Start & Requirements

To deploy the baseline system:

  1. Fork the repository.
  2. Navigate to infra-cdk/ and run npm install.
  3. Execute cdk bootstrap (once).
  4. Run cdk deploy.
  5. Execute python scripts/deploy-frontend.py. Detailed instructions are in the deployment guide. Prerequisites: AWS account, Node.js, npm, AWS CDK, Python.

Highlighted Details

  • Baseline System: Functional, multi-turn chat agent with pre-built tools.
  • Included Tools: Gateway Tools (Lambda-based, authenticated), Text analysis, Code Interpreter (secure Python sandbox), and session management.
  • Tech Stack: Frontend uses React/Next.js, TypeScript, Tailwind CSS, shadcn. Supports Strands, LangGraph.
  • AI Guidance: vibe-context directory provides rules and best practices for AI coding assistants.

Maintenance & Community

No specific details on notable contributors, sponsorships, or community channels (Discord, Slack) are provided in the README. The repository originates from AWS Labs.

Licensing & Compatibility

This project is licensed under the Apache-2.0 License, which is permissive for commercial use and integration into closed-source projects.

Limitations & Caveats

This asset is a proof-of-value, not a production-ready solution. Users must implement controls per the AWS Shared Responsibility Model. AWS disclaims responsibility for the security of applications built using this template.

Health Check
Last Commit

1 day ago

Responsiveness

Inactive

Pull Requests (30d)
15
Issues (30d)
10
Star History
107 stars in the last 30 days

Explore Similar Projects

Starred by Eric Zhu Eric Zhu(Coauthor of AutoGen; Research Scientist at Microsoft Research), Mckay Wrigley Mckay Wrigley(Founder of Takeoff AI), and
24 more.

E2B by e2b-dev

0.8%
11k
Open-source cloud runtime for AI apps and agents
Created 3 years ago
Updated 1 day ago
Feedback? Help us improve.