Claude Managed Agents vs Claude Agent SDK
People think Claude Managed Agents and the Claude Agent SDK are the same, since both give you a ready-made Claude agent. The Agent SDK is a library. Its agent runs inside your own app, on your own machine or server. Managed Agents is a service in the Claude API. Its agent runs as a hosted session in a sandbox, and your app sends it events.
Claude Managed Agents
A Claude service that runs your agent for you. Its tools run in a sandbox.
Claude Managed Agents is a part of the Claude API that runs a whole agent for you. You set up an agent once, with a model, a system prompt and its tools. Then you pick an environment, which is a cloud sandbox or one on your own servers. Each job runs as a session, and you talk to it by sending events and reading a stream back. Claude runs commands, edits files and searches the web inside that sandbox. It is in beta, so each call needs the managed-agents-2026-04-01 beta header.
Claude Agent SDK
A kit that puts the Claude Code agent inside your own app.
The Claude Agent SDK is a library for Python and TypeScript that runs Claude Code's agent inside your own app. It gives your code the same tools, agent loop, permissions, sessions and hooks that Claude Code has. The SDK ships with a Claude Code binary and runs it for you. It used to be called the Claude Code SDK.
In one line
- Claude Managed Agents
- A Claude service that runs your agent for you. Its tools run in a sandbox.
- Claude Agent SDK
- A kit that puts the Claude Code agent inside your own app.
These live in different corners of the glossary (Development and AI), which is exactly why they get confused.