HackerNews中文版

大家好，我是 Eric，Trigger.dev 的首席技术官 (<a href="https://trigger.dev">https://trigger.dev</a>)。我们是一个开发者平台，用于构建和运行 AI 智能体和工作流，采用 Apache 2.0 许可证开源 (<a href="https://github.com/triggerdotdev/trigger.dev" rel="nofollow">https://github.com/triggerdotdev/trigger.dev</a>)。我们提供在你的代码库中创建生产级智能体所需的一切，并负责部署、运行、监控和调试。你可以单独使用我们的基础组件，也可以与 Mastra、LangChain 和 Vercel AI SDK 等工具结合使用。你可以自托管或使用我们的云服务，我们将为你处理扩展问题。这里有一个快速演示：(<a href="https://youtu.be/kFCzKE89LD8" rel="nofollow">https://youtu.be/kFCzKE89LD8</a>)。我们始于 2023 年，旨在可靠地在 TypeScript 中运行异步后台任务/工作流 (<a href="https://news.ycombinator.com/item?id=34610686">https://news.ycombinator.com/item?id=34610686</a>)。最初，我们不部署你的代码，只是进行编排。但我们发现，大多数开发者难以编写具有隐式确定性的可靠代码，将工作分解成小的“步骤”也很棘手，而且他们希望安装所需的任何系统软件包。无服务器超时让这个问题变得更加痛苦。我们还希望让你能够等待事情发生：外部事件、其他任务完成，或者仅仅是时间的流逝。这些等待可能需要几分钟、几小时，或者在事件发生的情况下可能永远持续，所以你不能仅仅让服务器一直运行。解决方案是构建和运营我们自己的无服务器云基础设施。实现这一突破的关键在于我们意识到可以对 CPU 和内存状态进行快照。这使我们能够暂停正在运行的代码，存储快照，然后在不同的物理服务器上恢复它。我们目前使用 Checkpoint Restore In Userspace (CRIU)，谷歌自 2018 年以来一直在 Borg 内部大规模使用它。从那时起，我们的应用得到了迅速发展，尤其是在 AI 智能体/工作流方面。这开辟了大量新的用例，例如使用 AI 生成视频（Icon.com）、实时计算机使用（Scrapybara）、AI 增强管道（Pallet、Centralize）和氛围编码工具（Hero UI、Magic Patterns、Capy.ai）等计算密集型任务。你可以开始使用 Trigger.dev 云服务 (<a href="https://cloud.trigger.dev">https://cloud.trigger.dev</a>)，自托管 (<a href="https://trigger.dev/docs/self-hosting/overview">https://trigger.dev/docs/self-hosting/overview</a>)，或阅读文档 (<a href="https://trigger.dev/docs">https://trigger.dev/docs</a>)。这里抢先预览一些即将到来的变化：1) 自托管的预热启动 2) 切换到 MicroVMs 进行执行——这将是开源的、可自托管的，并将包括检查点/恢复。我们很高兴与 HN 分享这些，并欢迎所有反馈！

查看原文

Hi HN, I’m Eric, CTO at Trigger.dev (<a href="https://trigger.dev">https://trigger.dev</a>). We’re a developer platform for building and running AI agents and workflows, open-source under the Apache 2.0 license (<a href="https://github.com/triggerdotdev/trigger.dev" rel="nofollow">https://github.com/triggerdotdev/trigger.dev</a>).We provide everything needed to create production-grade agents in your codebase and deploy, run, monitor, and debug them. You can use just our primitives or combine with tools like Mastra, LangChain and Vercel AI SDK. You can self-host or use our cloud, where we take care of scaling for you. Here’s a quick demo: (<a href="https://youtu.be/kFCzKE89LD8" rel="nofollow">https://youtu.be/kFCzKE89LD8</a>).We started in 2023 as a way to reliably run async background jobs/workflows in TypeScript (<a href="https://news.ycombinator.com/item?id=34610686">https://news.ycombinator.com/item?id=34610686</a>). Initially we didn’t deploy your code, we just orchestrated it. But we found that most developers struggled to write reliable code with implicit determinism, found breaking their work into small “steps” tricky, and they wanted to install any system packages they needed. Serverless timeouts made this even more painful.We also wanted to allow you to wait for things to happen: on external events, other tasks finishing, or just time passing. Those waits can take minutes, hours, or forever in the case of events, so you can’t just keep a server running.The solution was to build and operate our own serverless cloud infrastructure. The key breakthrough that enabled this was realizing we could snapshot the CPU and memory state. This allowed us to pause running code, store the snapshot, then restore it later on a different physical server. We currently use Checkpoint Restore In Userspace (CRIU) which Google has been using at scale inside Borg since 2018.Since then, our adoption has really taken off especially because of AI agents/workflows. This has opened up a ton of new use cases like compute-heavy tasks such as generating videos using AI (Icon.com), real-time computer use (Scrapybara), AI enrichment pipelines (Pallet, Centralize), and vibe coding tools (Hero UI, Magic Patterns, Capy.ai).You can get started with Trigger.dev cloud (<a href="https://cloud.trigger.dev">https://cloud.trigger.dev</a>), self-hosting (<a href="https://trigger.dev/docs/self-hosting/overview">https://trigger.dev/docs/self-hosting/overview</a>), or read the docs (<a href="https://trigger.dev/docs">https://trigger.dev/docs</a>).Here’s a sneak peek at some upcoming changes: 1) warm starts for self-hosting 2) switching to MicroVMs for execution – this will be open source, self-hostable, and will include checkpoint/restoring.We’re excited to be sharing this with HN and are open to all feedback!

Launch HN: Trigger.dev (YC W23) – Trigger.dev 平台发布（YC 冬季 23）—— 用于构建可靠 AI 应用的开源平台