agent SDK
A library that packages the agent loop with tools, budgets, saved state, tracing and hooks for human approval.
In more detail
The OpenAI Agents SDK, Anthropic's Claude Agent SDK, Google's ADK and LangGraph all contain the same loop you can write by hand. They save boilerplate, but you still own the tools, the permissions and the evals.
Related terms
- OpenAI Agents SDK — OpenAI's open-source Python and TypeScript framework for agents, with tools, handoffs between agents, guardrails, tracing and human-in-the-loop approvals.
- Claude Agent SDK — Anthropic's framework for building agents on the same loop, tools and context management that power Claude Code.
- Google ADK — Google's Agent Development Kit, an open-source framework for building, running and deploying agents with an event-driven runtime.
- LangGraph — LangChain's library for building agents and workflows as graphs of steps with saved state.
Taught in
- What An AI Engineer Does — AI Engineering: LLM Apps, RAG & Agents
- Planning, Memory And Many Agents — AI Engineering: LLM Apps, RAG & Agents
- Agent SDKs And Human Approval — AI Engineering: LLM Apps, RAG & Agents
References
- OpenAI Agents SDK: Running agents (the agent loop, max_turns)
- Claude Agent SDK: How the agent loop works