LangGraph

LangGraph 提供了一种结构化方法来构建 Python 中的智能代理工作流，通过状态、节点和边的组合实现可追踪的执行流程。

本文详解使用Python和LangGraph构建多智能体AI系统，对比框架与无框架实现的差异，强调本地运行的低成本优势。

本地优先AI代理通过LangGraph和子代理实现复杂任务编排，提升响应效率。

通过 Pipecat 框架，可在几分钟内将 LangGraph 代理转换为语音代理，适用于现有代理的多模态扩展。

本文介绍了如何使用 Playwright 和 LangGraph 构建能够与真实网站交互的 AI 代理，适用于没有 API 的场景。

《Deep Agents 实战》教程系统讲解 LangChain 生态下的 Agent 开发三层架构，提供虚拟文件系统、子 Agent 和 Skills 等实战内容。

《Deep Agents 实战》教程基于 LangChain / LangGraph 生态，讲解如何使用 Deep Agents 构建真实应用，重点介绍虚拟文件系统、任务规划、子 Agent 和 Skills 复用。

可观测性对于智能代理是必不可少的，需结合 LangGraph 和 LangSmith 工具实现。

AWS Machine Learning Blog article discusses how AWS Generative AI Innovation Center collaborated with Works Human Intelligence to build two AI agents using Amazon Bedrock AgentCore, showcasing cost reductions and increased efficiency.

LangChain introduces the Agent Development Lifecycle (ADLC), dividing agent development into four phases—build, test, deploy, and monitor—emphasizing that its fundamental difference from traditional software lies in infinite input/output spaces and non-determinism, with successful teams adopting a "ship early, iterate fast" pattern.

OncoAgent是一个开源的隐私保护肿瘤临床决策支持系统，结合了双层LLM架构和LangGraph拓扑，显著提升了决策支持系统的性能和安全性。

Data science has entered the 'Agentic Era,' shifting the focus from manual procedural execution to the evaluation and supervision of autonomous AI agents. These agents use a 'Perceive-Reason-Act-Evaluate' loop to handle data cleaning, EDA, and tuning, evolving the data scientist's role from an executor of 'how' to a decision-maker of 'whether'.

Building AI Agents should follow four maturity levels: validate with frameworks, customize with state machines, optimize UX with Kanban, and deploy to the cloud. Avoid hype and evolve from simple to complex based on needs.

LangChain's Deep Agents come with durable execution, where every agent step is checkpointed, ensuring observability, fault tolerance, and human-in-the-loop. DeltaChannel addresses the storage scaling issue for long-running agents.

LangChain推出基于代理的RFP处理系统，通过四个自动化代理提升响应效率，集成LangGraph和LangSmith技术。

Leve 是一个基于 LangGraph 的文件系统优先的持久化代理框架，通过目录结构定义代理并编译运行。

GPT Researcher 是基于 deepagents 的高性能开源工具，简化了深度研究代理的构建。

通过pipecat_ai工具可将LangGraph代理快速转换为语音代理，LangSmith支持全流程追踪。

文章推荐了一门关于代理AI的课程，涵盖LangChain、LangGraph等工具，但内容信息密度较低。

Odessia is an AI-powered travel agent supported by LangChain technology, allowing users to plan and book entire trips in one conversation.