Hacktoberfest 2026: le issue che i maintainer hanno segnato per ottobre, aperte e adatte ai principianti. Sfoglia le issue Hacktoberfest

New pattern submission - lambda-web-agentcore-nodejs-terraform

Aperta
#3,358 0 commenti 0 reazioni 0 assegnatari Vedi su GitHub

I maintainer di solito rispondono entro 1 giorno

Nessuno ha ancora preso questa issue.

Valutazione

Difficoltà
3/5
Tempo stimato
Mezza giornata
Idoneità per principianti
22/100
Tipo di issue
Funzionalità
Chiarezza
Abbastanza chiara
Stato di attività
Attiva
Stack tecnologico
ai-infra-agents, aws, express, nodejs, python, terraform
Ambito
ai, cloud

Direzione di ricerca

This issue is a pattern submission announcement; the code lives in pull request #3359, which the body links but the linkedPullRequests field does not list. Start by reading that PR's pattern folder and its README to see the Terraform, Node.js Express app and Python agent, and check it against the repository's pattern template. Done means the maintainers review the pattern and either merge it or request changes on the PR.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Descrizione

Pattern name: lambda-web-agentcore-nodejs-terraform

Pull request: https://github.com/aws-samples/serverless-patterns/pull/3359

Description:

A fully serverless streaming chat app for an AI agent. An Express server running as an AWS Lambda Web Function serves the chat UI and calls a Strands agent hosted on Amazon Bedrock AgentCore Runtime, which calls Claude Haiku 5.5 on Amazon Bedrock. The answer streams back as server-sent events, token by token, from the model through AgentCore Runtime and the Web Function to the browser. Amazon CloudFront is the single public URL and adds a secret origin header that the Web Function checks, so the endpoint cannot be used to bypass CloudFront. The agent is deployed with AgentCore direct code deployment (no container image, Docker or Amazon ECR), and each sign-in gets its own AgentCore session for a private, multi-turn conversation. A login secret stored in AWS Secrets Manager, signed session tokens and caps on prompt length and answer tokens keep the public demo from being open access to the model.

Based on the Lambda Web Functions and AgentCore Runtime integration sample by Anton Aleksandrov (@aal80): https://github.com/aws-samples/sample-genai-strats/tree/main/agentcore/lambda-web-function-integration

Services used: AWS Lambda Web Functions, Amazon Bedrock AgentCore Runtime, Amazon Bedrock, Amazon CloudFront, AWS Secrets Manager, Amazon S3.

Language: Node.js (web app), Python 3.13 (agent)
Framework: Terraform
Level: 300

Tested end to end in a live account in us-east-1 and eu-central-1, then destroyed with nothing left behind.

Lingua principale
Python
Stelle
1.8k
Fork
1.1k
Merge medio
1g 14h
PR unite (30g)
9

Preparare l'ambiente

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di aws-samples/serverless-patterns

Tutte le issue di aws-samples/serverless-patterns

Issue simili

Altre issue su Python

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.