Claude Agent SDK

Agentic AIFrameworks and SDKsPublished By Simon Budziak

Claude Agent SDK is Anthropic's library that packages the agent loop behind Claude Code, its terminal coding assistant, as a programmable runtime for Python and TypeScript. An application gets the same tools, context management, and permission model without anyone implementing the tool loop by hand.

Anthropic’s docs subtitle it “Build production AI agents with Claude Code as a library”, packaging what powers Claude Code (Claude Agent SDK docs). It records over 33 million PyPI downloads per month as of August 2026, mostly below the radar of framework comparisons.

What do you actually get in the harness?

The SDK inherits everything that makes Claude Code usable day to day: built-in tools for reading files, editing code, running commands, and searching the web; hooks that run custom code at points in the agent lifecycle; subagents for specialized tasks; MCP connections to external systems (what MCP is); granular permissions controlling which tools run automatically versus which need approval; and sessions that maintain context across exchanges. It is a complete AI agent harness rather than a set of parts.

Where is the boundary?

The tradeoff is the flip side of the lineage. The SDK is Claude native on purpose, so teams that need model portability weigh it against provider-neutral frameworks. Its high download count against modest community buzz fits the pattern of a vendor embedding a package across its own tooling surface. Used for what it is, a runtime with production guardrails battle-tested inside another product, it is one of the strongest starting points in the ecosystem.

Frequently asked questions

What is the relationship between Claude Code and the Claude Agent SDK?

Claude Code is the terminal product; the Agent SDK is the same agent loop, tools, and context management packaged as a library. The SDK was rebranded from the Claude Code SDK once it grew beyond coding tasks into general agent building.

Can the Claude Agent SDK run non-Anthropic models?

No. The SDK is Claude native by design: its tools, permission system, and context management are built around Claude models. Teams running multi-model fleets treat it as one strong option among several rather than a default runtime.

Summarize this page with

See this working in a system we built