Claude Managed Agents
Anthropic's managed agent platform: a hosted agent harness that runs the agent loop in an Anthropic-managed cloud sandbox or a self-hosted sandbox.
Description
Claude Managed Agents (CMA) is Anthropic's managed agent platform, part of the Claude Developer Platform. It provides a pre-built, configurable agent harness and the infrastructure to run Claude as an autonomous agent — instead of building your own agent loop, tool execution and runtime, you get a fully managed environment where Claude can read files, run commands, browse the web and run code. The harness supports built-in prompt caching and context compaction.
The platform is built around four concepts: Agent (model, system prompt, tools, MCP servers, skills), Environment (an Anthropic-managed cloud sandbox or a self-hosted sandbox on your own infrastructure), Session (a running agent instance with SSE streaming and server-side persisted event history), and Events. Agents are created once (POST /v1/agents) and referenced by ID; sessions pin a config version. Built-in tools are Bash, file operations, web search/fetch and MCP.
Scheduled (cron) deployments and the ability to steer or interrupt a session are available. The feature is in beta (managed-agents-2026-04-01 header), usable from the SDK (Python, TypeScript, Go, Ruby, PHP, Java), the ant CLI and the REST API, and is also available on Claude Platform on AWS. Because it is stateful, CMA is not currently eligible for Zero Data Retention or a HIPAA BAA.
MLOps LifecycleMLOps LifecycleFull model lifecycle: registry, feature store, prompt management, monitoring and human-in-the-loop.
Human-in-the-Loop
SecurityEnterprise SecurityCertifications, access controls and data-protection features essential for corporate deployments and cloud privacy compliance.
Developer EcosystemDeveloper EcosystemDeveloper resources: available SDKs, supported programming languages, and infrastructure features and model-deployment methods.
Pricing & Business ModelPricing & Business ModelBilling models (usage-based, provisioned throughput), resource limits and SLA parameters (uptime, support tiers).
Pricing models