摆脱 AI 工具锁定：Tailscale Aperture 的身份、预算与网关设计

简要说明Brief Description

一个没有锁定效应的 AI 未来——Tailscale 的 Remy GuercioAn AI Future Without the Lock-In — Remy Guercio， Tailscale

目录Table of Contents

• 简介
  Intro
• AI 锁定的一年
  A year of AI lock-in
• 无限预算时代的终结
  The end of unlimited budgets
• 浪费的 token
  Wasted tokens
• 我们怎么出去？
  How do we get out?
• 财务部门想要答案
  Finance wants answers
• ROI 最大化
  ROI maxing
• 四个层次
  The four layers
• 认识 Aperture
  Meet Aperture
• 大多数 AI 网关的工作原理
  How most AI gateways work
• 来自 tailnet 的身份
  Identity from the tailnet
• 使用 tsnet 构建
  Built with tsnet
• 各模型的预算
  Budgets per model
• LLM 和 MCP 网关
  LLM and MCP gateway
• 统一管理身份验证
  Auth in one place
• 沙盒
  Sandboxes
• 为什么你需要网关
  Why you need a gateway

简介Intro

大家好。呃，感谢大家来参加今年 AI Engineer World's Fair 这个舞台上的最后一场演讲。嗯，是的，谢谢大家。我叫 Remy，在 Tailscale 的战略项目团队工作。呃，更具体地说，我负责我们的 AI 网关 Aperture。今天我想聊一聊，嗯，什么才算是一个没有厂商锁定的 AI 未来，或者说，要实现这样的未来需要些什么。我觉得，过去 12……年里我们看到的很多锁定……Well, hi folks. Uh, thanks for joining me here for the last talk on this stage uh of the uh AI engineer world's fair this year. So, um, yeah, thank you for joining me. My name is Remy. I am on the strategic projects team at Tailscale. Uh and more specifically I actually work on our AI gateway aperture and today I want to talk a little bit about you know what it means or you know what it's going to take uh to have an AI future without the lockin. I think a lot of the locking that we've seen uh over the last 12

AI 锁定的一年A year of AI lock-in

这几个月来，是啊，如果我们快速回顾一下过去 12 个月，我觉得这一年很大程度上可以用“token 最大化”这个说法来形容。我说的不是你在 AI 爱好者圈子之外可能听到的那种负面含义，而是说，这一年我们一直在摸索：有了百万 token 的上下文窗口，我们能做些什么；有了从任何地方获取上下文的能力——不只是 MCP 无处不在，还有那些擅长通过 CLI 查找上下文的编程工具，可以把上下文带进模型，再带到你需要的一切地方，然后从那里继续往下做。这真的挺酷的。我是说，有了这些，真正的智能体式编程才成为可能。months and yeah so if we take a look real quick at the you know the last 12 months you know I think it can really be you know described quite a bit by uh the phrase token maxing and I I don't mean that in the kind of you know negative sense that you might kind of hear outside of the you know kind of AI enthusiast circle. I mean that in the sort of you know it's been a year of trying to figure out you know what we can do with million token context windows uh with the ability to get context from anywhere right not just you know MCP being everywhere but you know also having coding tools right that are great at finding context using the CLI bringing that context into the model uh bringing it you know bringing it into you know everything that you need and and and going from there right it's it's been pretty cool right I mean we've gotten It's really made truly agentic coding possible having all of this right.

所以，是的，我是说，这确实挺酷的，而且你知道，随着我们继续推进，我们会看到的不只是智能体编程，还有其他智能体应用场景也会不断发展起来。所以，嗯，你知道，token 最大化挺酷的，但它确实有一些问题，对吧？显而易见的问题就是成本很高，对吧？这是一项极其昂贵的事情。嗯，我觉得过去 12 个月可能已经……So yeah, it's I mean it's it's quite cool and you know we're going to see uh not just agentic coding but you know other agentic use cases continue to take off uh as we as we do this. So um you know token maxing is cool but right it has it has problems right there's obvious problems right it's very expensive right it's it's it's an extremely expensive endeavor uh you know I think the last 12 months are you know have maybe been

无限预算的终结The end of unlimited budgets

其特点是，嘿，我们有，你知道，无限的 AI 预算，呃，而这在过去几个月里发生了变化，呃，就你知道，这意味着什么、使用 AI 意味着什么而言。嗯，我的意思是，你知道，一般来说，如果你做得对，它确实很贵，但它也确实会默认鼓励我所谓的“浪费 token”。我的意思是，我在做一个 AI 网关。我们自己也用这个 AI 网关。我能看到通过 AI 网关产生的所有用量。你简直想不到，有多少会话长达数百甚至数千条消息，却没有人清空上下文。他们就这么一直聊下去。我的意思是，有时候这确实有帮助，但你知道，这真的挺让人惊讶的。你会有……你……marked by hey we have you know unlimited AI budget uh and that's changed here in the last few months uh in terms of you know what it what it means to you know what it means to use AI um it also I mean you know it's expensive like just generally if you're doing it, you know, right, but it also it does incentivize what I would call like wasted tokens by default. I mean, I I work on an AI gateway. We use our AI gateway. I get to see all of the usage from the AI gateway. You would not believe the number of sessions that are hundreds or thousands of messages long where nobody clears the context. They just kind of keep going. I mean, it's helpful sometimes, but you know, it's it's it's pretty surprising. you will have you

浪费的令牌Wasted tokens

知道一个会话里有数千万个 token，呃，缓存基本上一直处于满载状态，一直满载，所以成本会变得非常高。还有另一件事，对吧？你知道，这段时间令人兴奋，人们在做新东西、构建新东西，但这也导致很多情况下出现了高度垂直整合的工具链。Claude Code 显然是一个重要例子，Codex 也是，对吧？大家都在构建自己的东西，从模型一路往上，直到最顶层，构建自己的智能体、构建自己的工具链。所以，嗯，好吧，这里有很多问题。那么，我的问题是，……know tens of millions of tokens of a session uh where it's the cash is basically maxed out maxed out the entire time uh it gets really expensive um and the other thing is right so you know this has been an exciting time right people are doing new things building new things uh but this has led to you know in many cases very vertically integrated tool chains uh cloud code is obviously you know a big one codeex right everybody's kind of building up their you know for all the way from the model you know all the way all the way up to the top uh you know building their uh you know building their agents, building their tool chains. So um all right there's a lot of problems there and so you know my question right in terms of

我们怎么出去？How do we get out?

这是，呃，你知道，我们该怎么解决这些问题？具体来说，怎么应对锁定效应？又该如何真正改进我们使用 AI 的方式，让我们能把它用在那些不只是前沿任务的事情上，而不是说我们基本上只是在浪费钱、浪费 token，诸如此类的事情。嗯，不过首先我想谈谈该如何避免解决这个问题时走错方向。呃，这种情况特别特别常见。过去六个月里，我们一直在跟很多人聊他们的 AI 开支和使用情况，对吧？我真的跟成百上百的人聊过。这就是做 AI 网关的好处之一：大家会来找你，说：“我不知道是怎么回事。我知道我们用了很多 AI。我每天都会收到一张 Anthropic 账单。”this is uh you know how do we address these problems in particular how do we address the lock in and you know how do we actually improve uh how we use AI such that you know we can use it for things that aren't just you know kind of essentially frontier task or where we're just kind of wasting wasting money wasting tokens uh you know that sort of thing. Um, but first I want to talk about how not to address the problem. Uh, and this is a super super common thing. So, uh, over the last 6 months, we've been talking to I've literally been talking to hundreds and hundreds of folks about their AI spend, their AI usage, right? That's the kind of benefit of working on an AI gateway. Folks come to you, they're like, I don't know what's going on. I know we're using a lot of AI. I get, you know, uh, I get an anthropic bill every day.

呃，我每天都会收到一张 Codex 账单。嗯，呃，你知道，我不只是说我总能看到它。所以你知道，我该怎么办？他们通常会带着一种解决方案来找我，那就是，哦，我们就……现在好像大家都在用 Cloud Code。所以我们就……统一到一家供应商，也许两家，对吧，也许两家。所以，呃，他们会说：“我得弄清楚这事。我要怎么弄清楚？我要怎么……哦，好吧，是啊，我会说，大家都用这个，对吧？我们就用这个东西。”嗯，这不是个好主意。呃，你知道，我现在坐在这里说这话，可能听起来很明显，这也许不是个好主意；但当你陷入那种恐慌状态，觉得我们已经花了很多……Uh, I get a codeex bill every day. Um uh so you know I it's not just that you know I see it all the time. So you know what do I do? They usually come with one kind of solution in mind uh and that is oh we're just going to like uh everybody seems to be using cloud code right now. So we're just going to like consolidate on a single vendor maybe two vendors right maybe two vendors. So that's uh they're like I need to get a handle on this. How do I get a handle on this? How I get you know oh okay yeah I will say everybody's going to use this right we're just going to use this thing. um that is not not a great idea. uh you know I might seem obvious sitting here it's maybe not a great idea but you know when you're in that panic zone of we've spent a lot of

财务部门需要答案Finance wants answers

钱，而我们并不清楚具体该怎么做。呃，你知道，财务部门在跟你说话，像是在问：“你在做什么？”呃，嗯，你知道，就像我们说的，可以使用 AI，但也许别用那么多 AI。呃，你知道，这种反应相当自然：好吧，我要把所有东西整合起来，对吧？好吧，我要掌控它，我要——你知道——我要掌控这一切，呃，掌控这个。嗯，你知道，我认为这多少让我们窥见了未来 12 个月会看到什么，以及人们实际上正试图做什么，呃，至少在某种程度上。money and we don't know how exactly uh and we you know finance is talking to you it is being like what are you doing uh um you know like we said to you know use AI but maybe not use that much AI uh and you know it it's a pretty natural response to be okay I'm going to consolidate everything down right okay I'm gonna have a control on it I'm gonna have you know I'm gonna have control on this uh control of this Um and you know I think this is kind of peeking at what we're going to see the next 12 months and what people are actually trying to do uh at least at the you know kind of

最大化投资回报率ROI maxing

前沿模型，我想把它称为 ROI 最大化，对吧？我们要做的不是 token 最大化，而是 ROI 最大化。你知道，这确实是必要的，对吧？这不是……我说 ROI 最大化，并不只是指削减成本，而是指真正证明你所做的事情具有某种价值。不仅如此，还要让更多事情成为可能，对吧？如果你手头只有两个前沿模型，以及围绕它们构建的整套生态系统，那就意味着成本会达到一定水平，导致某些事情根本无法开展，对吧？如果使用 AI 的唯一方式就是这样，你就不可能真正把 AI 的应用推广到公司内部。所以，当我们考虑如何最大化 ROI 时，首先需要想一想，内部部署 AI 都包含哪些组成部分。frontier is uh what I would like to call ROI maxing right we're not going to be token maxing we're going to be ROI maxing uh and you know it's it's really just a necessity right it's not uh um and I don't mean that when I say ROI maxing I don't just mean cutting costs right I mean actually proving some sort of value uh to the thing that you're doing uh and not only that but also kind of opening things up, right? So if the only thing you have is like two frontier models and their entire stacked ecosystem, that's a certain cost level where you you it just makes things certain things untenable, right? You can't actually expand AI usage into the company if that's the only way you can use AI. Um and so you know when we think about ROI maxing, we first need to kind of think about like what are the components of an internal AI deployment.

我说的不是那种“嘿，我们在应用里开发了这个新 AI 功能”。我是指，你知道，在你们组织内部的内部环境中。I'm not talking about like a hey, we've built this new AI feature in our app. I mean, you know, internal internal to your organization.

四层The four layers

所以，你知道，大概有四样东西，对吧？有 LLM 或多个 LLM，对吧？这是其中一层。呃，还有一层是数据连接器。我的意思是，对很多人来说，这就是 MCP，但实际上，它可以是 CLI、API，或者任何获取数据的方式，比如读取文件，对吧？把文件读进你的智能体系统里。呃，还有界面。我觉得人们有时会把这一点忘掉，但你知道，一开始是聊天界面。后来我们有了两种，你知道，我们有了……有了带聊天功能的 IDE。然后我们又猛地从两种方式转回到……你知道，我要用手机来做。呃，然后，哦，现在的热门趋势是 Claude Code，比如说，我要……我们就通过 Slack 和智能体交互，对吧？And so, you know, there's four things, right? There's the LLM or LLMs, right? There's that layer. Uh there's sort of the data connector layer. I mean, this is MCP for a lot of people, but in reality, it's, you know, CLI or APIs or really just any way that you get data could be reading a file, right, into your uh into your agentic system. Uh there's the interface. I think people kind of forget about this sometimes, but you know, it's started with the chat interface. We got two, you know, we kind of got a uh we got, you know, idees with chat. We got, you know, kind of a whiplash back from two into, you know, I'm going to do it on my go to my phone. Uh, you know, to, oh, now the, you know, the hot thing is, you know, claude tag and like I'm going to use, you know, I'm going to use we're just going to interface with agents via Slack, right?

所以，呃，嗯，你知道，这是另一个核心组件，而且是一个可以拆分出来的组件。呃，最后一个是沙箱，也就是智能体运行的环境。好了，这就是你的四个组成部分，嗯，确切地说，就是四个组件。所谓最大化 ROI，就是在这些层级中的每一层，尽可能抓住所有可以做选择的机会。你不一定非得在每一层都做出独一无二的选择，比如“哦，我在每一层都做了专属于自己的特殊选择”，但能够在任何时候，根据需要在任意层级做出选择，这一点真的很重要。呃，不同团队或不同的人可能会有不同的选择，对吧？你知道，这在组织内部可能会有很大差异。我完全无法想象整个工程团队都只靠 Slack 讨论串来写代码。So, uh, um, you know, it's another core component and it is a component that you can break out. Uh and then the last one is sandboxes just the environment in which the agent runs right so those are your four kind of uh you know four components really uh and to be ROI maxing uh means to be maxing your you know every opportunity that you have uh for choice to make a choice at one of those layers right you don't have to necessarily have a unique thing at you know oh I've made my bespoke special choice at every one of those layers but it's really important to be able to make a choice at any given layer that you need at any given time. Uh, and it might be different for different teams or different folks, right? It's, you know, it can be pretty different across the organization. I don't totally imagine like an entire engineering team just coding via, you know, slack thread.

听起来可能挺有意思，但我不太能想象那种情况，对吧？呃，嗯，不过你知道，整个营销团队可能都在一个 Slack 讨论串里工作，提出数据方面的问题，做其他类似的事情。所以，你知道，把这些事情区分开来真的很重要。对吧，所以我在 Tailscale 工作，负责一个 AI 网关。你知道，我来这里聊聊 AI 网关为什么能帮你做到这一点，大概也就不奇怪了。我不一定只是指使用我们的 AI 网关，我觉得它不错，不过你知道，任何 AI 网关对这件事都很重要。所以……Might be fun, but I don't totally imagine that, right? Uh, um, but, you know, the entire marketing team might be working entirely uh, you know, in a slack thread, asking data questions, doing other things like that. So it's really important to you know to be able to uh kind of separate these things and right so I I work at tail scale right I work on an AI gateway uh you know maybe no surprise that I'm here to talk a little bit about why an AI gateway uh will help you do that can help you do that and I don't just mean necessarily using our AI gateway I think it's nice but you know just any AI gateway is the um you know is important for this uh so

认识 ApertureMeet Aperture

我们的 G AI 网关叫 Aperture。它的作用是什么呢？对，可能也不出意料，对吧？它位于你的智能体与智能体的接口之间，也位于你的所有端点之间，包括 LLM 端点、数据端点，也就是 MCP 端点、API 端点，以及你拥有的任何其他端点。它处在中间，让你能够控制和监控正在发生的事情。你可以从安全角度进行管理，也可以从成本角度进行管理；还有一个我们经常做的事情，就是了解某个人或某个智能体正在做什么。它其实非常酷：当你有日志时，就可以告诉智能体：“嘿，我觉得它可能运行到一半就停了。”它就……嗯，好像没有得出答案。our g AI gateway is uh called aperture and um what it does uh is right it's maybe No surprise here, right? But it let you it sits in between your agents and that interface of that agent uh and you know all of your endpoints uh as well both like LLM endpoints and data you know kind of MCP endpoints API endpoints anything that you have uh and sits in the middle and let you both control and monitor what's happening from a that can be from a like security perspective that can be from a cost perspective that can be from a which we do a lot I want to learn about what somebody is doing or what an agent is doing uh perspective. It's actually really cool when you have logs uh and you can tell your agent to hey uh I it maybe it ran out. It kind of just kind of you know oh it it didn't reach an answer.

事情就这么逐渐失控了。呃，现在可能没那么常发生了。以前肯定经常发生。你知道，这种情况在一些比较便宜的模型上可能也更常见。呃，它们通常不太擅长及时停下来。不过，事后分析自己哪里出了问题，它们倒是很擅长。所以，如果你有像 AI 网关这样的东西，就很容易把它指回你当时做的事情，然后问：“发生了什么？为什么这没能……为什么这没能按我预期的方式运行？”呃，所以，你知道，如果你用过 AI 网关，怎么样……It just kind of spiraled out of control. Uh maybe happens less now. Definitely used to happen quite a bit. Happens with you know maybe cheaper models more often too. Uh they're usually not great at stopping themselves. Uh but they are great at analyzing where they went wrong after the fact. And so when you have something like an AI gateway, it's really easy to point it back at what you were doing and say, "What happened? Why did this not why did this not, you know, work the way I was expecting it to?" Uh, and so, you know, if you've used an AI gateway, how

大多数 AI 网关如何工作How most AI gateways work

很多人喜欢使用 AI 网关，已经部署了 AI 网关，也用过 AI？是的。如果你以前用过，可能已经习惯了这种做法：好，我把所有密钥都放到这个网关上了。现在，我得为手头所有东西创建一批虚拟密钥，对吧？所以就像是，我用一些密钥换来了一大堆其他密钥。呃，我们可以做点特别的事情。Aperture 构建在 Tailscale 之上。如果你不熟悉 Tailscale，它是一个基于身份的网状网络，构建于 WireGuard 之上。呃，你可以通过 Tailscale 实现的是，所有通过 Tailscale 网络建立的连接——呃，这就是一个 Tailscale 网络。你只要在需要的地方安装 tailnet 代理就行了。可以是容器、笔记本电脑、GPU 服务器，都没关系。嗯，安装好它就行。many people like have an AI gateway, have deployed an AI gateway, use an AI? Yeah. So, if you've used one before, you're probably used to, okay, so I've put all my keys on this gateway. Now, I need to go create synthetic keys for everything that I have, right? So, it's like, okay, I've traded some keys for a bunch of other keys. uh we get to do something a little special. So Aperture is built on tail scale and if you're not familiar with tail scale, tail scale is an identity based mesh network. It's built on wire guard. Uh and what you get to do with tailscale is uh every connection that is made over a tail. So it's a tail scale network uh you know you install the tail net agent everywhere that you need. It can be containers, laptops, GPU servers, doesn't matter. um you install it

来自 tailnet 的身份Identity from the tailnet

现在，在任何地方，通过那个 tailnet 建立的每个连接，都会带有另一端机器或用户的身份标识。所以这可以是一个标签，对吧？比如说，这是一个机器 ID。这是一个 PR 审查机器人，对吧？然后它下面还会有一个单独的节点 ID。这就是这个 PR 审查机器人的一个实例，对吧？所以你可以这样做，也可以是用户，对吧？比如只是我在笔记本电脑上使用 Cloud Code。它也可以带上这个信息。另外，如果你使用 Entra 或 Okta 这样的服务，我们实际上可以同步所有群组，这样你就能看到这个人属于哪个群组。这样，另一端的某个东西就能够——everywhere and every connection that's now made over that tail net uh comes with the identity of the machine or the user on the other side. So that can be a tag, right? So that can be like hey this is a machine ID. This is a PR review bot, right? Uh and then it would get a separate node ID underneath. This is the instantiation of that PR review bot, right? So you can do that or it can be the user, right? So it's just me using cloud code on my laptop. Uh that can come with it as well. uh in addition to if you're using something like Entra or Octa uh we can actually sync all the groups in uh so you can see the group that that person is associated with. So something on the other side is able to

使用 tsnet 构建Built with tsnet

看到了所有这些。我们有一个非常酷的库，叫作 TSNet。它是一个开源库，你可以用它来构建这类应用。我们就是用它来构建 Aperture 的。这里实际发生的就是这样。它能够识别另一端的用户或代理，也就是连接另一端的身份。再提醒一下，内部 AI 部署通常包含几个组成部分：LLM、数据、接口，以及运行各项内容的沙箱和环境。说到使用 Aperture，在 LLM 方面，我觉得它和其他 AI 网关大体上差不多，应该符合你的预期，只不过现在这里有一个已经配置好的网关。see all of that. We have this really cool library. It's called TSNet. It's an open source library. You can use it to build these sorts of apps. That is what we use to build aperture. That is what is actually happening here. So it is able to see the uh it is able to see the identity of that user or that agent on the other side of the thing on the other side of the connection. And so you know again just reminder components of a you know an internal you know AI deployment uh right so there's the LLM side of things there's the data side of things the interface side of things and the actual sandboxes uh sandbox and environment in which things run uh side of things. So, um, when it comes to using Aperture, uh, you know, as far as LLMs go, this is pretty similar, I think, to, you know, what you might expect from other other AI gateways, except now, you know, here I have a, you know, a configured gateway.

呃，它接入了 Anthropic、OpenAI、Vercel，你知道，还接入了 Anthropic OAuth、Bedrock、Codex，所有你能想到的服务都有。呃，我把所有这些密钥都放到了那个网关上。现在，当我想以代理或用户的身份连接到那个 LLM 提供商时，我不需要……如果我有这个扩展功能的话，也不会有额外的界面让我创建这些 API 密钥、创建这些身份之类的东西。一旦我连接到……一旦我真正连上网关，它就知道我是谁、我的身份是什么，然后它就会说：“哦，你有权限访问这些模型和这个提供商，对吧？你可以……”Uh, it's got anthropic, open eye, versel, you know, it's got even anthropic oath, uh, you know, bedrock codex, everything, uh, that you can imagine. I put all those keys on that gateway and then now when I want to actually connect to that LLM provider as an agent or a user there's no I don't have there's if I had this expanded there's there's no extra screen for create these API keys create these identities create this once I connect to the once I actually connect to the gateway it knows who I am it knows what I am and it's like oh you have access to this models this provider right you can

每个模型的预算Budgets per model

用 GLM 5.2，呃，你用 GLM 5.2 也能获得这样的预算，对吧？用便宜的模型，你能获得无限预算；用 Frontier 模型，你的预算就会非常有限，对吧？诸如此类。呃，这里没有额外的设置。只要添加你的 API 密钥，就可以开始使用。所以再说一次，我们把整个 LLM 层都整合到一个地方，这样你就可以在组织内部逐步扩展。再说一次，无论你是想切换模型还是服务提供商，都可以做到。呃，接下来要说的是数据方面。也就是说，除了作为 LLM 网关之外——这其实就是为什么我一开始说它是 AI 网关。所以我知道这听起来有点模糊，呃，use GLM 5.2 uh you get this budget with GLM 5.2 too, right? You get unlimited budget with a cheap model and you get an extremely narrow budget with a Frontier model, right? Those sorts of things. Uh there's no extra setting here. It's just add your add your API key and go. So again, we've taken all the LLM layer and we've put it into a you know, put it into one place that you can then, you know, kind of expand out within your organization. Again, doesn't matter if you're trying to switch models or providers, you can do that. Uh the next thing is the data side of things. So, uh, in addition to, you know, being an an LLM gateway, and this is actually why I said AI gateway at the beginning. So, I know that seems kind of nebulous, uh,

LLM 和 MCP 网关LLM and MCP gateway

但我其实是特意选择这个术语的，因为我们既是 LLM 网关，也是 MCP 网关，甚至还会为标准 API 做认证注入，然后将它们重新暴露为 MCP。所以，你知道，我们是有意在这里选择了一个更宽泛的术语。不过，正如你在这里看到的，作为管理员，你可以在 Aperture 中配置任意 MCP 服务器。我们内置了一些 MCP 服务器，都是我们检查过的，确保它们易于使用，诸如此类。如果你曾在组织内部署过 MCP，或者使用过 MCP，你就会知道，虽然有一个标准，但每个人遵循的标准版本都不一样。你知道，只要看他们决定如何实现认证，就能准确判断出 MCP 服务器是什么时候构建的。but I'm actually I very specifically chose that term because we're both an LLM gateway and an MCP gateway and we even do off like, uh, injection for just standard APIs and reexpose those as MCPs, too. So, uh, you know, kind of intentionally choosing the broader term here. Um, but with this, as you can see here, uh, in Aperture as an admin, you can go in and configure whatever MCP servers you want. We have kind of built-in ones where we've, you know, checked them out, make sure they're easy to easy to work with, all those sort of things. If you've ever deployed an MCP or used MCPS within your organization, you'll know that, uh, there's a standard, but everybody follows a different version of that standard. Uh, you know, you can tell exactly when an MCP server was built by exactly how they decided to do off.

嗯，是的，设置 MCP 服务器的过程确实是一次很棒的、某种意义上的考古课。不过我们尽量让这个过程变得非常简单，对吧？我们大致已经走过一遍了。嗯，作为管理员，你可以说：“嘿，我已经配置好了这些。这些就是允许使用的。”你可以用同样的身份信息来设置：“嘿，市场营销团队可以访问 Google Calendar 和 Gmail，而工程团队还可以访问 GitHub，对吧？嗯，你甚至可以设置各种规则，比如工程团队里的这一部分可以访问 GitHub，或者只能以只读方式访问 GitHub。你可以在这里做各种各样的事情，而且特别棒的是……”Uh yeah, it's it's a great uh you know kind of archaeology lesson uh when you go through when you go through setting up MCP servers, but we try to make that a very simple process here, right? We've kind of gone through this. Uh so you as an admin can say, "Hey, I've configured these. These are the ones that are allowed." You can use that same identity information to say, "Hey, the marketing team, you know, they get access to Google Calendar and Gmail, but the engineering team, they'll also get access to GitHub, right? uh you can even say things like oh the engineering you know this side of the engineering team gets access right access to GitHub or readonly access to GitHub you can do all all sorts of things here and what's really nice and

在一个地方进行身份验证Auth in one place

再说到解耦，所有身份验证都在这里完成。所以，如果有人想用 Cursor、Claude Code、Codex，或者某种特殊的智能体框架——也就是他们发现或开发出来的某个新热门工具——他们只需要访问那个端点。如果他们在 Tailnet 上，一切都会以他们本人、相应的智能体，或者相应的标记设备的身份完成身份验证。这样就不用先对所有东西重新进行身份验证，再对所有东西重新认证，然后还得对这个新工具重新认证。通过这种方式，我们大大降低了尝试新工具、尝试不同工作流程和体验的切换成本。正是这些细小的摩擦点，导致人们根本不会去尝试新的用例。again talking about decoupling is all of the authentication happens here so if you have folks that want to use cursor or they want to use cloud code or they want to use codeex or they want to use some special agent framework that they're you know some new hot thing that they've you know they've discovered or built or whatever uh all they have to do is hit that endpoint and if they're on the tail net everything's authenticated as them or as whatever the agent or as whatever you know the tag device is. Uh there's no like oh I have to go reth into everything and then reauth into everything and then reth into this new tool. Uh we make the switching cost right of like actually trying out tools and trying different workflows and different experiences a lot a lot easier with this sort of thing. It's all those little points of friction uh that lead to use cases where like you know people just don't try new use cases.

他们不会尝试，呃，你知道，想着“哦，也许我该试试看，也许我能把成本降下来，也许我能让它变快”。嗯，接下来聊聊界面。Aperture 实际上内置了一个聊天 UI，没错，你知道，好像大家都有聊天 UI，我们也有一个内置的聊天 UI。不过，它是基于你也可以自行调用的 API 构建的。Aperture 的整体目标，就是为你提供与我们所用相同类型的工具和界面，或者说，提供构建界面的工具。所以，不管你想构建 Slackbot、聊天 UI，还是某种没人想过的新东西，比如语音交互的移动应用之类的，你都可以做到。重点是，你可以用 Aperture 做到这些。They don't try to uh you know oh maybe I should experiment maybe I can make this cheaper maybe I can make this faster. Um you know next thing talking about the interface so uh with Aperture we actually have a built-in chat UI surprise uh you know everybody seems to have a chat UI we have a built built-in chat UI um however it is built on top of APIs that you can also leverage yourself. Uh so our whole goal with Aperture is to actually provide you with the same sort of you know tools and interfaces and or tools to build interfaces that we can. So whether or not you want to build a Slackbot or you want to build uh chat UI or you want to build you know some new thing that nobody's thought of some mobile app kind of thing you know it's voice only interface right uh you can you can do that. The whole point is you're going to be able to do that with Aperture.

我们希望能够支持所有这些不同的具体用例。不过你也能看到，它有连接器。这些连接器都是通过 Aperture 本身配置的，不是在聊天界面里配置的。你只是通过 Aperture 来使用它们。最后还有一件事，我们刚才稍微谈到了界面。能够使用所有这些东西非常重要。其实还有一项功能很快就会上线：不知道有没有人试过搭建 Open WebUI，或者 LibreChat 之类的界面。搭建这类界面时有一个很大的问题：你总是会丢失身份信息，然后突然间，所有内容都来自界面，对吧？就好像一切都只是来自系统。我们实际上会加入完整的 O 透传功能，这样一来，如果用户因为某些原因使用你提供的任何界面，你就能够看到所有用户身份和机器身份。We want to support all of those different individual uh use cases. But again you can see it has connectors. Those are all again set up through Aperture itself. They're not set up in the chat UI. You're just getting them uh by way by way of Aperture. Uh and then the last thing, so this is uh you know, so we talked about interfaces, you know, a little bit. It's, you know, it's again, it's very important uh that you be able to kind of use all of that. Uh actually one other thing that's coming very soon here is um uh if you've ever I don't know if anybody's ever tried to set up like open web UI or you know or like Libra like or any of the like kind of like any of the like oh I'm going to set up like a hey this like you know this interface or this interface uh one big thing is you always lose identity information and then suddenly all of the you know everything's coming from the UI right everything's it's like oh everything's just coming from the system uh we're actually going to be adding a full like pass through O uh so you'll be able to actually see all of the like user identities and machine identities if for some reason they're using whatever interface that you have.

呃，你应该可以把它配置成透传 O，同时仍然获得你对 AI 网关所期待的所有可见性。嗯，然后，是的，最后一点是，没错，我觉得这实际上是大家做得相当不错的一个领域。现在已经有很多选择了，人们正在尝试……Uh you should be able to set it up so that you can pass through the O and you still get all of the same visibility that you're kind of expecting from a from an AI gateway as well. Um and then yeah the last thing is right this is actually the I think the area in which um folks are doing pretty good. There's actually a lot of choice already people are trying to do

沙盒Sandboxes

这个。呃，我觉得这是因为，沙箱的定义嘛，我敢肯定，要是我在这里问一圈，每个人对沙箱究竟是什么、他们需要沙箱做什么，或者希望沙箱能做什么，都会有不同的定义。呃，所以你知道，我们现在有点处于“让一千朵花齐放”的阶段：市面上有各种各样的沙箱提供商，能满足各种突发奇想、需求和愿望。嗯，不过你知道，大家在把它们集成起来这方面做得相当不错，但这仍然是一件非常重要的事。实际上，我们也要在网关中为沙箱增加一个编排层。this. Uh I think that's because uh the definition of a sandbox I'm sure I could poll everybody here and would have a different everybody would have a different definition of exactly what a sandbox is uh or what they need from a sandbox or what they want from a sandbox. Uh and so you know there's we're kind of in that let a thousand flowers bloom phase of you know there's a sandbox provider for every sort of whim and need and you know and want out there. Um but uh you know and folks are doing a pretty good job of integrating them but again it's a really important thing. We're actually going to be adding kind of an orchestration layer as well for sandboxes to a gateway.

呃，再说一次，我是有意非常宽泛地使用“AI 网关”这个术语，因为要为各种不同的端点做出最佳选择——比如你的环境、LLM、数据连接器之类的——你确实需要一个地方来查看所有这些东西，还需要一个地方把它们整合起来，这样你就可以使用其中任何一个。所以，它在某种程度上几乎可以算是一种通用转换层。嗯，不过，大致就是这样。正如我所说，这里也提醒一下：最大化 ROI，归根结底就是尽可能扩大选择空间，避免被锁定。所以，即使你不用 Aperture，我也强烈建议你开始使用。uh again trying to use that term AI gateway very loosely intentionally very loosely because in order to again kind of make the best choices for all of the different endpoints that you're you know environments LLMs data connectors all that sort of thing uh you really do need uh to kind of have a place to sort of see them all uh and then a place that brings them all together such that you can then use any other one so right kind of a almost a universal translation layer in a way um but yeah so that's that's mostly that and you know like I said is a reminder here uh is you know ROI maxing really is all about maximizing choice uh to prevent lock in right so you know even if you don't use Aperture I do highly recommend you start

为什么需要网关Why you need a gateway

说到 AI 网关，你会发现 AI 网关确实很不错。当然，它的好处不只是让你不必配置三个不同的服务提供商，也不必在它们之间来回切换，对吧？它对了解智能体在做什么也很有帮助，即使你只是个人用户也是如此。很多人会把自己的用量接入 AI 网关，只是为了弄清楚自己的智能体在做什么。因为很常见的一种情况是，人们在 Tailscale 上运行类似 OpenClaw 这样的东西，让它接入自己的 tailnet，然后让它在后台运行。接着他们就会惊呼：“天哪，它做了什么？我不确定它做了什么，但它确实做了些不该做的事。”借助 AI 网关，你就可以回过头查看，弄清楚它哪里出了问题、发生了什么。所以，这不只是为了避免被某个服务商绑定，对吧？它还关乎尝试和全面了解情况；因此，使用 AI 或 LLM 网关非常重要。considering an AI gateway you look at an AI gateway it's good just beyond like actual you know oh you know I don't have to you know uh have three different providers configured or switch between them this way you know uh it's good beyond that right it's great for just you know understanding what agents are doing even if it's just you as an individual we have so many people who or just as an individual they have their usage behind an AI gateway just to have an idea as to what their agents are doing because you know if you're running uh very commonly uh is people are running something like openclaw with on tail scale and it's on their tail net and they and it's just running in the background and they're like oh my god it did something I'm not sure what it did it did something it was not supposed to do with something like an AI gateway you can actually go back and you can see and you can look and you can actually diagnose where it went wrong what happened Um so you know it's it's not just lock in right it's actually just experimentation and understanding as a whole uh is you know is very important to use something uh like a like an AI or LLM gateway.

嗯，我的演讲就到这里，简短而精炼。非常感谢大家前来参加。这是今天这里的最后一场演讲，希望大家都度过了一场非常棒的会议。我很喜欢 AI Engineer World Fair，也希望你们同样喜欢。谢谢大家。So um that's it uh for my talk just short and sweet uh thank you very much for attending I this is the the last talk in here of the day so uh I hope everybody's had a really great conference I know I love the AI engineer world fair uh and I hope you do too. So thank you