AgentCore Runtime
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 2
- AWS guide runs Claude Code as a remote Bedrock agent
AWS Machine Learning Blog published a guide and sample for running Claude Code as a remote coding agent on Amazon Bedrock AgentCore. Each task runs in an isolated AgentCore Runtime session inside the user’s AWS account and returns a GitHub pull request for human review and merging. The sample also demonstrates private networking, short-lived credentials, least-privilege permissions and Amazon Bedrock data controls.
AWS Machine Learning Blog · 🔥 0 - Amazon previews AgentCore Runtime session endpoints for live agent apps
AWS Machine Learning Blog says Amazon Bedrock AgentCore Runtime session endpoints let users open applications running inside an agent session directly from a browser. Each session receives an authenticated URL that routes HTTP and WebSocket traffic only to allowed ports, while the runtime isolates sessions in microVMs. In the vendor demonstration, a coding agent runs a Vite website whose interface changes to a dark theme without a page refresh.
AWS Machine Learning Blog · 🔥 0
Experience and discussion from the community
Share my AgentCore Runtime experienceAsk about AgentCore Runtime
Nobody has shared their experience with AgentCore Runtime yet.