Claude Agent SDK
by Anthropic
Lets Python and TypeScript developers embed the Claude Code agent loop in their apps, with built-in tools, hooks, subagents, MCP, permissions, and resumable sessions.
Skills
Built-In Tools
Gives the agent Claude Code's tools to read, write, and edit files, run commands, and search the web.
Hooks
Runs your callbacks on agent events such as tool calls or session start to block or modify behavior.
Subagents
Spawns separate agent instances for focused subtasks with isolated context, optionally in parallel.
MCP Integration
Connects the agent to external tools and data sources through Model Context Protocol servers.
Sessions
Persists conversation history to disk so an agent can resume or fork a session with full context.
Related Agents
Strands Agents
Builds production agent harnesses in Python or TypeScript with a model-driven agent loop, pluggable model providers, MC…
Claude Code
Anthropic's agentic coding tool that runs in the terminal, reads and edits codebases, executes commands, and connects t…
CrewAI
Multi-agent orchestration framework for building teams of AI agents that collaborate, delegate, and solve complex tasks…
SandBase Harness
Runs local-first, self-hosted AI agents with persistent sessions, sandboxed tools, memory, credentials, audit trails, r…