Conversation
- Add complete Next.js application with Vercel deployment configuration - Implement dual model provider support (Amazon Bedrock and OpenAI) - Create pluggable session backend (memory, file, and S3 storage options) - Add Docker setup with standalone Next.js build for containerized deployment - Include AgentCore server for stateful agent operations - Add chat API route with streaming support - Configure environment templates and deployment documentation - Provide architecture diagrams and deployment guides - Update deploy module README with new adapter reference
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds a
create-next-app-shaped chat template where the Vercel AI SDK owns the client and providers, and Strands Agents runs the loop, tools, sessions, and hooks inside the Next.js route handler through theVercelModeladapter. Ships with one-click deploy to Vercel and a container path to Amazon Bedrock AgentCore.Location:
typescript/02-deploy/02-nextjs-vercel-adapter/What's included
useChatfrom@ai-sdk/reactmanages the conversation and streaming UI.calculator,current_time), session persistence, and lifecycle hooks run inapp/api/chat/route.ts.VercelModeladapter — Strands wraps any Vercel AI SDK provider (@ai-sdk/amazon-bedrock,@ai-sdk/openai). Switch providers with one env var, no code changes./ping+/invocations) on an ARM64 container.Dockerfileusing standalone Next.js output.Model providers
Testing
npm run dev— chat UI streams tokens and tool activity viauseChat."what is 128 divided by 4?"(calculator) and"what time is it in America/Mexico_City?"(current_time).npm run agentcore— local AgentCore runtime responds on/pingand streams from/invocations.Asana
Ref: https://app.asana.com/1/8442528107068/project/1217155663608611/task/1218279858515566?focus=true