Claude Agent SDK
Build production agents with the same tools and agent loop that power Claude Code
Claude Agent SDK lets developers build AI agents in Python and TypeScript using the agent loop, built-in tools, and context management from Claude Code. Agents can read files, run commands, search the web, and edit code without implementing tool execution.
It supports subagents, lifecycle hooks, MCP servers, permission controls, and resumable sessions. Authentication runs through the Anthropic API or providers like Bedrock and Vertex AI. For hosted execution, Anthropic also offers Managed Agents as a REST API.
Pricing: Per token usage
Choosing an agent framework right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Choosing an agent framework right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Claude Agent SDK Alternatives
Explore 86 products in the Agents category. View all Claude Agent SDK alternatives.
LangGraph
Low-level framework for building stateful, long-running AI agents with graph-based orchestration
AgentsKit
Open-source TypeScript ecosystem for building, distributing and operating AI agents without provider lock-in
Composio
Tool integration platform connecting AI agents to 1,000+ apps with managed auth and execution
Burr
Build stateful AI agents and applications as state machines, with a built-in tracing UI
FalsifyLab
MCP server giving AI agents live financial and on-chain data tools
ChatBotKit
Platform for building AI agents and deploying them across web, Slack, Discord, WhatsApp, and Telegram
Work on Claude Agent SDK? Feature it at the top of Agents.
Is your product missing?