然而，下一波真正的浪潮已经涌现：智能体（Agent）时代。这里的"智能体"，不是简单的聊天机器 人。它指的是 以大型语言模型为认知引擎，具备自主决策、目标导向和环境交互能力的 AI 系统。 从 ChatGPT 到 Claude，从文心一言到 DeepSeek，我们已习惯与各种 Copilot 协作。它们能力惊 人，但本质仍是 被动响应 的工具——我们发出指令，它们返回结果。 "我看到很多开发者卡在'只会调 API'的层面，这非常可惜。AI 智能体的底层，是一套精密的 系统工程。掌握它，意味着你能从'工具的使用者'转变为'智能系统的创造者'。这不仅是技能 的提升，更是思维模式的跃迁。" 想象一下： 这就是 Agentic AI ——未来最炙手可热的技术方向，也是拉开下一代 AI 应用差距的关键。 热潮之下，开发者真正的 挑战是什么？ 智能体开发就像一座冰山。水面之上，是大家熟悉的"调 API、写 Prompt"；水面之下，才是真正的 复杂性所在： 这些，才是考验开发者能否将炫酷概念转化为真实价值的核心能力。面对这片充满机遇但略显复杂的 海域，一位资深的技术"引路人"—— 王延飞老师 ，分享了他的观察。 作为一位 ...

Hey, this is Lance. I want to talk a bit about the deep agents package that we recently released. Now, the length of tasks that an agent can take every seven months.And we see numerous examples of popular longrunning agents like Claude Code, Deep Research, Manis. The average Manis task, for example, can be up to 50 different tool calls. And so, it's increasingly clear that agents are needed to do what we might consider deeper work or more challenging tasks that take longer periods of time.Hence, this term d ...

Agent Protocol Landscape - The industry is moving towards interoperability through three open protocols for agentic frameworks [1] - These protocols create a universal language for agents, enabling different frameworks to work together [3] Key Protocols - AG-UI (Agent-User Interaction) facilitates bidirectional communication between agent backends and frontends, enabling interactive agent experiences within applications [1][2] - A2A (Agent-to-Agent) is a protocol for multi-agent coordination, task delegation, and intent sharing across systems [3][5] - MCP (Model Context Protocol) is the standard for agents connecting to tools, data, and workflows [5] Interoperability and Integration - Protocols eliminate the need for point-to-point integrations, allowing developers to build to protocols instead [3] - Frameworks like LangGraph, CrewAI, and Agno can be integrated into the same frontend without rewriting UI logic [3] - CopilotKit unifies the entire stack into one framework, simplifying the implementation of these protocols [4] Example Workflow - A LangGraph agent retrieves data via MCP, delegates analysis to a CrewAI agent via A2A, and streams results to a React app via AG-UI [6]

Agent Protocol Landscape - The industry is converging on three open protocols for agent interoperability: AG-UI (Agent-User Interaction), MCP (Model Context Protocol), and A2A (Agent-to-Agent) [1][2] - These protocols are complementary layers of a stack, not competing standards, facilitating a universal language for agents [2] - Protocols enable integration of frameworks like LangGraph, CrewAI, and Agno into the same frontend without rewriting UI logic [3] Protocol Functionality - AG-UI enables bidirectional connection between agentic backends and frontends, creating interactive agents within applications [1][2] - MCP standardizes how agents connect to tools, data, and workflows [2] - A2A facilitates multi-agent coordination, enabling task delegation and intent sharing across systems [2][5] Framework Integration - CopilotKit unifies the entire protocol stack into one framework, providing generative UI support and production-ready infrastructure [3][4] - An example workflow involves a LangGraph agent pulling data via MCP, delegating analysis to a CrewAI agent via A2A, and streaming results to a React app via AG-UI [6] Development Focus - Protocols allow developers to focus on building agent capabilities instead of integration mechanics, as interoperability is handled automatically [3]

Hi there, this is Christian from Langchain. Just a couple of weeks ago, we released version one of Langchain and Lang Graph. And one of the cool features of it is that it makes it really easy to stream events and results from the agent down to any type of front end that you're using, whether it's React, Vue, or Swelt.So, in this video, I want to build a little CHPT clone that shows you how you can build and create agent right in your Nex. js application. Every longchain agent maintains a state throughout it ...

Core Insights - LangChain has completed a $125 million funding round, achieving a post-money valuation of $1.25 billion, marking its status as a unicorn [3] - The company has released a significant update with LangChain 1.0, which is a complete rewrite of the framework after three years of iterations [3][4] - LangChain is one of the most popular projects in the open-source developer community, with 80 million downloads per month and millions of developers actively using it [3] Development Background - LangChain was initiated in October 2022 by machine learning engineer Harrison Chase as a side project, initially consisting of about 800 lines of code [5] - The project was inspired by the fragmented tools and lack of abstraction in the AI development landscape, leading to the creation of a framework that connects models with tools [6] Evolution of LangChain - The framework has evolved from a simple integration tool to a comprehensive application framework, focusing on context-aware reasoning [9] - LangChain's architecture includes a component and module layer, as well as an end-to-end application layer, allowing developers to quickly build applications with minimal code [9][10] Challenges and Solutions - The team faced numerous issues, including a backlog of around 2,500 unresolved problems and user feedback regarding the need for greater control and customization [11] - To address these challenges, LangChain introduced LangGraph, which allows developers to manage agent logic more flexibly and supports long-running tasks [12][13] Key Features of LangChain 1.0 - The new version emphasizes controllability and built-in runtime capabilities, allowing for persistent execution environments and checkpoint recovery [16][27] - A middleware concept has been introduced, enabling developers to insert additional logic into the core agent loop, enhancing extensibility and customization [25][30] - The framework now supports dynamic model selection based on context, allowing for better optimization between capabilities and costs [26][27] Future Directions - LangChain's product lines focus on scaling the open-source ecosystem, enhancing the integration development environment for LangGraph, and improving the scalability of LangSmith [13] - The company aims to maintain its position at the forefront of AI development by providing flexibility and options for developers in a rapidly evolving landscape [26]

Core Insights - LangChain announced a successful funding round of $125 million, achieving a valuation of $1.25 billion [2][5] - The company, which focuses on developing an open-source framework for AI agents, was founded in 2022 and has quickly gained popularity among developers [3][5] Funding Details - The latest funding round was led by IVP, with new investors CapitalG and Sapphire Ventures joining existing backers such as Sequoia Capital, Benchmark, and Amplify [3][5] - LangChain's valuation increased from $200 million after a $25 million Series A round led by Sequoia Capital [5] Product Development - LangChain has evolved into a platform for building AI agents, launching significant upgrades to its core products, including the LangChain agent-building tool, LangGraph for orchestration and context/memory, and LangSmith for testing and observability [5] - The company maintains high popularity among open-source developers, boasting 118,000 stars and 19,400 forks on GitHub [6]

Group 1 - LangChain, an open-source AI agent framework developer, has achieved a valuation of $1.25 billion after completing a $125 million funding round [2] - The funding round was led by IVP, with new investors CapitalG and Sapphire Ventures joining existing investors such as Sequoia Capital, Benchmark, and Amplify [2] - LangChain was founded in 2022 by Harrison Chase and has quickly gained popularity for addressing challenges in building applications using early large language models (LLMs) [2][3] Group 2 - The company has evolved into a platform for building intelligent agents, launching a comprehensive upgrade of its core products, including LangChain, LangGraph, and LangSmith [3] - LangChain maintains high popularity among open-source developers, boasting 118,000 stars and 19,400 forks on GitHub [3]

Core Viewpoint - OpenAI's AgentKit is a comprehensive toolset for developers and enterprises, but it is critiqued for being a visual workflow builder rather than a true agent builder, lacking the necessary autonomy and predictability for complex tasks [2][3][10]. Group 1: Purpose and Functionality - The primary goal of low-code workflow builders is to enable non-technical users to create agents independently, reducing reliance on engineering teams [7]. - Visual workflow builders, including OpenAI's AgentKit, are fundamentally workflow builders and not true agents, which limits their effectiveness in handling complex tasks [10]. Group 2: Differences Between Workflows and Agents - Workflows are characterized by fixed processes with complex branching logic, while agents operate with simplified logic abstracted into natural language, allowing for more autonomous decision-making [8][9]. - The trade-off between predictability and autonomy is crucial; workflows sacrifice autonomy for predictability, whereas agents do the opposite [8]. Group 3: Challenges of Visual Workflow Builders - Visual workflow builders face challenges due to limited engineering resources in many companies, making it difficult to meet all technical demands [12]. - Non-technical users often have a clearer understanding of the agents they need, which complicates the development of effective visual workflow tools [12]. Group 4: Solutions for Different Complexity Levels - For high-complexity scenarios, a code-based workflow is necessary to ensure reliability, as these situations often require intricate workflows with multiple branches and parallel processing [14]. - In low-complexity scenarios, simple agents (Prompt + tools) can reliably address issues, and building these agents without code is simpler than creating workflows [16]. Group 5: Future Directions - The industry does not need more workflow builders; instead, the focus should be on enabling users to easily create stable and reliable agents without code [22]. - Optimizing code generation models to better assist in writing LLM-driven workflows and agents is a key area for future development [23].

Anthropic's Claude Code, OpenAI's Deep Researcher, and Manus's general purpose agent have demonstrated that agents can be amazingly effective on complex, long-running tasks. We call these Deep Agents because they have a few key differentiators from earlier forms of agents. In our new LangChain Academy course, Deep Agents with LangGraph, you'll learn their key characteristics and how to implement them in your own Deep Agent.So what makes these agents different. Under the hood, they use a simple ReAct tool-ca ...