LangGraph

Since the previous Radar, we’ve observed that the LangGraph architecture — which treats every multi-agent system as stateful graphs with a global shared state — is not always the best approach for building agentic systems. We’ve also seen an alternative approach, used in frameworks such as Pydantic AI, that also works well.

Instead of starting with a rigid graph and a massive shared state, this approach favors simple agents communicating through code execution, with graph structures added later when needed. It often results in leaner and more effective systems for many use cases. Because each agent only has access to the state it needs, reasoning, testing and debugging become easier. As a result, we’ve moved LangGraph out of Adopt. While it remains a powerful tool, we no longer see it as the default choice for building every agentic system.

LangGraph 是一个用于使用 LLM 构建有状态的多智能体应用的编排框架。它提供节点和边等底层原语，以及内置功能，使开发人员能够精细控制智能体的工作流、内存管理和状态持久化。这意味着开发人员可以从一个简单的预构建图入手，并扩展到复杂且不断演进的智能体架构。通过支持流式处理、高级上下文管理以及模型回退和工具错误处理等弹性模式，LangGraph 使你能够构建健壮的生产级智能体应用。其基于图的方法确保了可预测的、可定制的工作流，并简化了调试和扩展。我们的团队使用 LangGraph 构建多智能体系统取得了很好的效果，这得益于其轻量级和模块化的设计。

LangGraph 是一款面向基于 LLM 的多 agent 应用构建的编排（Orchestration）框架。与抽象程度较高的 LangChain 相比，它提供了更底层的节点（Nodes）和边（Edges）等基本原语，允许开发者精细地控制 agent 工作流、记忆管理与状态持久化。这种基于图的设计使工作流更加可控且易于定制，使得在生产级应用中的调试、扩展和维护变得更加容易。尽管其学习曲线较陡，但 LangGraph 凭借其轻量化与模块化设计，在开发 agent 应用时展现出了强大的灵活性和扩展性。