Claude Platform on AWS

Claude Platform Console is Anthropic's web console for building agents and applications with Claude models and managed agent infrastructure. Its guided quick-start flow lets users create an environment, agent, and session without writing code. The managed-agent flow separates the session event log, the agent's harness and Claude-based “brain,” and sandboxed tools or “hands”; credentials are injected through an egress proxy rather than exposed to the sandbox.

Claude Managed Agents is Anthropic's managed agent infrastructure: a configurable agent harness for running Claude on long-running and asynchronous tasks. An agent combines a model, system prompt, tools, MCP servers, and skills; an environment specifies an Anthropic-managed cloud sandbox or a self-hosted sandbox; and a session runs the agent and produces persisted events. Applications send user messages as events, while Claude runs tools and streams responses through server-sent events; sessions can be steered or interrupted, and their event history can be retrieved. The service provides managed tool execution and sandbox infrastructure, including shell commands, file operations, web search and fetch, and MCP connections. It includes prompt caching, compaction, persistent filesystems, conversation history, and server-side storage, so users do not need to build their own agent loop, sandbox, or tool-execution layer. The documentation also describes a design that separates the agent's harness and model from its sandboxes and tools, with credentials handled outside the sandbox through an egress proxy. Claude Managed Agents is in beta and requires the managed-agents-2026-04-01 beta header. Stateful sessions are not currently eligible for Zero Data Retention or HIPAA Business Associate Agreement coverage.

Claude Console is Anthropic’s web console for building applications and managed agents with Claude models. It provides API-key creation, a natural-language quick start for creating an agent, deployment search and triggering, and live session transcripts with a debug event stream that includes model latency. The managed-agent workflows described for it include scheduled deployments, fan-out across sessions with custom tools, workspaces for tenancy and access, and a research-preview memory process called Dreaming that reviews past sessions to improve a memory store.

Claude Managed Agents documentation is Anthropic's resource for building and operating managed Claude agents, covering environments, agents, sessions, events, tools, authentication, orchestration, and related APIs. It describes Managed Agents as a pre-built, configurable agent harness running in managed infrastructure, with cloud or self-hosted sandboxes, persistent session state, server-sent event streaming, tool execution, prompt caching, and context compaction. The documentation is part of Anthropic's Claude Platform Docs and includes quickstarts, configuration guides, operational references, and beta-access requirements.

Amazon Bedrock AgentCore is an AWS service for deploying and operating AI agents in production. It provides a framework- and model-agnostic runtime for agents built with systems such as Strands Agents, CrewAI, LangGraph, LlamaIndex, Google ADK, or OpenAI Agents, with support for Python and TypeScript applications. Its capabilities include managed agent runtime hosting, sessions, memory, identity and access management, a gateway for turning APIs, Lambda functions, and services into MCP-compatible tools, built-in tools such as code execution and web search, and OpenTelemetry-based observability for tracing, debugging, and monitoring. The linked AWS Labs repository provides sample applications, tutorials, deployment templates, integrations, and blueprints covering these capabilities. The AgentCore CLI scaffolds projects, supports local development with hot reload and local invocation, and deploys agents to AWS with commands such as `agentcore deploy` and `agentcore invoke`. The samples repository is licensed under Apache 2.0.