Agent framework
An agent framework is a software library that provides the common parts of an AI agent, such as the tool loop, state, memory, handoffs between agents and tracing, so developers do not build them from scratch.
Also called: agent SDK
By Divya Sharma · Checked Nov 15, 2026 · How we review
Every agent needs the same plumbing: call the model, run tools, keep state, retry on failure, log what happened. A framework packages that plumbing. Examples include LangGraph, CrewAI and the OpenAI Agents SDK.
What they offer
Frameworks differ in how much they decide for you. LangGraph calls itself a low-level orchestration framework: you describe the flow as a graph of nodes and shared state, and it adds durable execution, pauses for human review and memory. The OpenAI Agents SDK takes a lighter approach with a few primitives: agents with instructions and tools, handoffs between agents, guardrails and built-in tracing. Others give you ready-made roles for teams of agents.
When to use one
A framework saves time when you need persistence, retries, agent orchestration across several agents or tracing out of the box. It costs you visibility. Anthropic warns that frameworks add layers of abstraction that can hide the prompts and responses underneath, which makes bugs harder to find. For a simple agent, a direct loop over the model API may be clearer.
Agent SDK
"Agent SDK" usually means a framework published by a model provider, tied closely to its own API. The agent frameworks guide compares the options.
Related terms
- AI agent
- An AI agent is a system in which a language model decides its own next steps: it calls tools, reads the results and repeats until the task is done, instead of following a fixed script.
- Agent orchestration
- Agent orchestration is the control of which agents or model calls run in an application, in what order, and how each next step is chosen, either by a model making the decision or by fixed code.
- Agent loop
- An agent loop is the repeating cycle at the heart of an AI agent: the model asks for a tool call, the application runs it and returns the result, and the model decides what to do next.
- Multi-agent system
- A multi-agent system is a setup in which several AI agents, each with its own instructions, tools and context, work on parts of a task and pass results to each other or to a coordinating agent.
- Agent memory
- Agent memory is the set of techniques that let an AI agent keep information beyond a single context window, such as facts about a user or past work, by storing it outside the model and loading it back when needed.