Anthropic Launches Claude Managed Agents to Standardize Production Infrastructure

Claude

Apr 9, 2026 · Updated Apr 28, 2026

Anthropic launched Claude Managed Agents in public beta, providing a suite of APIs for building and hosting AI agents at scale. By handling the underlying infrastructure for sandboxing and session management, the platform allows teams to move from prototypes to production deployments in days.

Anthropic launched Claude Managed Agents in public beta, a suite of composable APIs for building and deploying cloud-hosted agents. The platform includes an orchestration harness (a coordination layer that manages task execution) and production-grade infrastructure. It handles the complex backend work of secure sandboxing and tool execution automatically.

Building production agents typically requires months of engineering cycles for state management and security. This update shifts the burden of agentic engineering (the discipline of building reliable agent systems) from the developer to the platform. It enables long-running sessions that persist for hours, allowing agents to work autonomously through disconnections.

You can now deploy agents through the Claude Console, Claude Code, or a new CLI. Pricing follows standard token rates plus a $0.08 per session-hour runtime fee. Advanced features like multi-agent coordination are currently in research preview, requiring a separate access request through the platform.

View the full update on claude.com

Claude

@claudeaiApr 8

Introducing Claude Managed Agents: everything you need to build and deploy agents at scale. It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days. Now in public beta on the Claude Platform. https://t.co/vHYfiC1G56

4.1k42k

View on X

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

See all AI news & updates from Anthropic →

Keep reading

Anthropic Launches Self Hosted Sandboxes to Run Claude Agents Inside Your Perimeter

Anthropic introduced self-hosted sandboxes and MCP tunnels to allow Claude Managed Agents to execute tools and access data within a company's private infrastructure. This update addresses enterprise security concerns by decoupling the AI's reasoning loop from the sensitive environments where code is run and data is stored.

AnthropicJun 2

Anthropic launches ant CLI to automate Claude Managed Agents from the terminal

Anthropic released the ant CLI, a terminal-based tool that exposes every Claude API endpoint as a subcommand. The interface allows developers and AI agents to manage models, files, and agentic sessions through standard shell workflows and version-controlled YAML files.

Amazon Web ServicesApr 24

AWS Launches Managed Agent Harness to Automate Infrastructure for AI Agents

AWS introduced a managed agent harness for Amazon Bedrock AgentCore that allows developers to launch working AI agents in three API calls without writing orchestration code. By handling sandboxing, session persistence, and security, the platform reduces the time required to move from an initial agent prototype to a production-ready deployment.

LangChainJun 10

LangChain Simplifies Production AI Agent Deployment with Managed Deep Agents

LangChain introduced Managed Deep Agents in private beta, an API-first hosted runtime for its open-source Deep Agents. This offering aims to streamline the operational complexities of deploying autonomous AI agents, allowing developers to focus on agent behavior rather than managing infrastructure.