Claude Agent SDK
Agent SDK from Anthropic
The Claude Agent SDK exposes the agent loop, tools and context management of Claude Code as a library for Python and TypeScript. Agents can read and edit files, run commands, search the web and spawn subagents for subtasks; hooks, permissions, sessions and MCP servers are built in. It was formerly called the Claude Code SDK. Use is governed by Anthropic's Commercial Terms, while the Python package itself is MIT licensed.
Good fit if
Focus: Developers embedding coding, research or automation agents with Claude in their own applications
- your project is about Coding agents, Research and analysis agents or Automation with file and shell access
- someone on your team writes code
Probably not if
- nobody on your team writes code (1/5 for use without developers)
Key figures
- Usable without developers
- 1/5
- Scalability
- 4/5
- Integrations
- 4/5
- Versioning
- 2/5
- Observability
- 3/5
Editorial rating on a scale from 1 to 5. Methodology
Fact sheet
- Category
- Developer
- Type
- Agent SDK from Anthropic
- Licence
- Anthropic Commercial Terms (Python-Paket MIT)
- Pricing
- Usage-basedSDK without license fee. Usage of the Claude API is billed per token, alternatively via Amazon Bedrock, Google Cloud or Microsoft Foundry.
- Deployment
- Self-Hosted, Cloud, Any
- Models
- Anthropic (Claude), Amazon Bedrock, Google Cloud, Microsoft Foundry
- RAG
- Yes
- Multi-Agent
- Yes
- SSO, roles (RBAC)
- SSO no, RBAC no
- Latest version
- 0.2.165 (Python)
- GitHub stars
- 8,200
Key features
- Built-in tools (files, shell, web search)
- Subagents
- Hooks and permissions
- Sessions and MCP
- Skills and plugins
Typical use cases
- Coding agents
- Research and analysis agents
- Automation with file and shell access
- Internal assistants
Sources
- Dokumentation(opens in a new tab)
- GitHub (Python)(opens in a new tab)
- GitHub (TypeScript)(opens in a new tab)
Checked on 9 Oct 2026
Implementation
Get Claude Agent SDK implemented
Free for you. Partners only pay for requests they accept.
Alternatives
Similar systems
Similar in category, features or use cases.
- DeveloperMicrosoft Agent FrameworkMicrosoft Agent Framework is Microsoft's open-source framework for agents and multi-agent workflows in Python and .NET. Version 1.0 shipped in April 2026 and is the unified successor of Semantic Kernel and AutoGen. A graph-based workflow engine supports branching, parallelism, checkpoints and human approvals; ready-made patterns exist for sequential, concurrent, handoff, group chat and Magentic-One orchestration. MCP and A2A are supported.View profile
- DeveloperInngest AIInngest is an event-driven durable execution platform: functions consist of steps that are retried automatically on failure and resumed after interruptions. For AI applications Inngest offers AgentKit and steps for LLM calls, so multi-step agents run reliably without operating your own queues. The server and CLI are licensed under the SSPL with delayed publication under Apache 2.0, the SDKs under Apache 2.0.View profile
- DeveloperOpenAI Agents SDKThe OpenAI Agents SDK is a lightweight framework for agents and multi-agent workflows in Python and TypeScript. It relies on a few primitives: agents with tools, handoffs to delegate to other agents, guardrails to validate inputs and outputs, and sessions as memory. Tracing is built in, MCP servers can be connected directly, and besides the OpenAI Responses API other model providers are supported. OpenAI describes the SDK as the production-ready evolution of Swarm.View profile
- DeveloperAutoGPTAutoGPT was one of the first well-known projects for autonomous GPT agents in 2023. Today it is a platform where you create, schedule and monitor agents via chat or a visual builder, plus a marketplace for ready-made agents. The platform is available hosted or self-hosted; the platform code is under the Polyform Shield License, while the original agent in the classic folder is MIT licensed.View profile