GitHub Universe 2026：演进技术栈的每一层

作为开发者，我们的工作正在发生变化。短短几年间，我们从逐行编写代码，转变为与 AI 助手协作，再到统筹调度一群智能体。但目标始终没变：交付完成的软件成果。无论是一个功能、一项缺陷修复，还是一项安全修复。重要的产出是已完成的工作，而不是更多代码。Our jobs as developers are changing. In a couple of years, we’ve gone from writing every line of code to working with AI assistants to orchestrating fleets of agents. But the goal hasn’t changed: ship completed software work. A feature, a bug fix, a security fix. Completed work, not more code, is the output that matters.

今天在 GitHub Universe 上，我们分享了愿景：让 GitHub 成为全球最全面的软件交付系统。我们推出了能让这一愿景成为现实的产品，并展示了我们如何重建其底层基础设施。Today at GitHub Universe, we shared our vision for GitHub as the most comprehensive software delivery system in the world. We introduced products that bring that vision to life and showed how we’re rebuilding the infrastructure underneath it.

我们的愿景：从创意到软件交付完成Our vision: From idea to completed software

软件开发生命周期（SDLC）不再是从规划到编码、测试再到部署的线性流程。一次代码变更、同事提出的请求，或一项生产环境指标，都可能触发系统中任意环节的工作。我们大多数人（以及我们的智能体）都会根据手头的任务，在不同阶段之间切换。开发人员负责明确方向、做出决策，并对最终交付的内容承担责任。智能体负责实施变更并进行验证。而所有环节都会汇入并流经一个持续学习的系统，让下一个周期做得更好。The SDLC is no longer a linear path from planning to coding to testing to deployment. A code change, a request from a colleague, or a production metric can trigger work anywhere in the system. Most of us (and our agents) jump between different stages, depending on the task at hand. Developers set the direction, make decisions, and stay accountable for what ships. Agents implement and verify changes. And everything feeds into and out of a continuous learning machine that makes the next cycle better.

这个智能体软件交付系统解决了三个问题：This agentic software delivery system solves for three things:

• 速度：以尽可能快、高效且经济的方式，将想法转化为完成的软件。
  Velocity: get from idea to completed software as quickly, efficiently, and cost-effectively as possible
• 智能化：将整个平台的上下文与持续学习引擎相结合，让系统在使用过程中不断变得更好。
  Intelligence: combine context across the platform with a continuous learning engine, so the system gets better as you use it
• 质量：确保已完成的工作默认安全，并在漏洞发布前发现它们。
  Quality: make completed work secure by default and catch bugs before they ship

GitHub 为开发者及其智能体而构建。我们也开放底层基础组件，让你能够构建专属解决方案。工作内容、工具和成本都由你掌控。GitHub is built for developers and their agents. We’re also making the underlying primitives available, so you can build your own bespoke solutions. You stay in control of the work, the tools, and the cost.

推动工作向前发展的新功能和产品New features and products that move the work forward

今天在 Universe，我们展示了部分最新产品和功能的实际应用，首先介绍的是 GitHub Copilot 应用。Today at Universe, we showed some of the latest products and features in action, starting with the GitHub Copilot app.

GitHub Copilot 应用：从 Issue 到合并，尽在一个应用中GitHub Copilot app: From issue to merge, in one app

GitHub Copilot 应用从设计之初便致力于支持智能体驱动的软件交付。它将你在不同项目中的智能体和工具连接起来，让你能够统筹工作，无需事事亲自交接。它的用途也不止于编写代码：你可以在这个以智能体为先的平台中撰写规范、展示设计讨论内容，或分析遥测数据。The GitHub Copilot app is designed from the ground up for agentic software delivery. It connects your agents and tools across projects, so you can direct the work without making every handoff. And it’s for more than producing code: you can write specs, present design discussions, or analyze telemetry in one agent-first surface.

Copilot Fusion：多模型编排的典范Copilot Fusion: Multi-model orchestration at its finest

不同任务需要不同的模型。开发者不应该为了获得理想结果和合适价格，而不得不管理每一项模型选择。Copilot Fusion 会评估任务在推理、代码生成、调试和工具使用方面的需求，然后选择使用一个或多个模型来执行任务。在 Artificial Analysis Coding Agent Index 中，Fusion Max 的得分与 Opus 5.5 Max 相差不到两分，成本仅为其一半，且每项任务耗时减少 40%。Different tasks need different models. Developers shouldn’t have to manage every model choice to get the right result at the right price. Copilot Fusion evaluates what a task needs across reasoning, code generation, debugging, and tool use, then chooses how to execute across one or more models. In the Artificial Analysis Coding Agent Index, Fusion Max scored within two points of Opus 5.5 Max at half the cost and 40% less time per task.

Copilot 项目：为 Copilot 设定一个目标Copilot projects: Give Copilot a goal

从今天起，GitHub Copilot 应用原生支持 Copilot 项目，让你能够在完全托管的并行会话中，跨多个代码仓库运行智能体任务。你可以在一个地方跟踪进度、做出决策，并安排接下来的工作。这意味着你可以减少管理执行过程的时间，把更多精力放在决定值得构建什么上。Available natively in the GitHub Copilot app starting today, Copilot projects let you run agent work across multiple repos in fully managed, parallel sessions. You have one place to track progress, make decisions, and direct what happens next. That means you can spend less time managing execution and more time deciding what’s worth building.

会话连续性：跨界面持续工作Session continuity: Keep working across surfaces

切换设备或工具时，你的工作不应从头开始。会话连续性让你能够在 GitHub 应用、VS Code、CLI 和网页端启动并继续同一个云端智能体会话。早会时用手机启动会话，在办公桌前通过 VS Code 指引它，午餐时再从 github.com 查看进度。智能体会在云端持续工作。为此提供支持的多模型框架功能强大、速度快且成本效益高。Your work shouldn’t restart when you switch devices or tools. Session continuity lets you start and follow the same cloud agent session across the GitHub app, VS Code, the CLI, and the web. Start from your phone at standup, steer it from VS Code at your desk, and check in on it from github.com at lunch. The agent keeps working in the cloud. Our multi-model harness that enables it is powerful, fast, and cost-efficient.

Copilot 自动化：从结果中学习Copilot automations: Learning from the results

Copilot 自动化功能让你可以在代码仓库中创建由 AI 驱动的工作流。它们在云端运行，你可以手动启动，也可以设置为响应某个事件或按计划运行。这样，你就能协调多个智能体来处理问题分类、代码审查等任务。现在，自动化还可以从执行结果中学习，并提出改进建议供你审查和批准。这就是学习引擎的实际应用：利用已完成工作的结果，让下一次运行做得更好。Copilot automations let you create AI-powered workflows within your repo. They run in the cloud, and you can kick them off manually or set them up to respond to an event or run on a schedule. That lets you coordinate agents to handle tasks such as issue triage and code review. And now, automations can learn from their outcomes and propose improvements for you to review and approve. That’s the learning engine in practice. Use the results of the completed work to make the next run better.

Copilot 代码审查 Max：深入了解上线内容Copilot code review Max: A deeper look at what ships

代码越多，拉取请求就越多，对代码审查的需求也越大。只有在能够保证交付质量的前提下，加快速度才有意义。Copilot 代码审查能发现开发者需要及时捕捉的、有实际意义且可采取行动的错误。今天，我们推出了 Copilot 代码审查 Max，它在 ReviewBench 的高严重性问题评测中取得了最高的 F1 分数。Lite 和 Balanced 让日常审查保持快速；当变更需要更深入的审查时，新的 Max 能提供更全面的分析。More code means more pull requests and more demand for review. Moving faster only helps if we can maintain the quality of what ships. Copilot code review surfaces meaningful, actionable bugs that developers need to catch. Today, we introduced Copilot code review Max, which posted the highest F1 score on ReviewBench for high-severity issues. Lite and Balanced keep everyday reviews fast; the new Max provides a deeper look when a change needs it.

无需单独企业订阅即可使用 Copilot 功能Copilot features without a separate enterprise subscription

从今天起，GitHub Enterprise 客户无需购买单独的订阅，即可使用所有 Copilot 功能，包括 GitHub Copilot 应用、代码审查、自动化等。您只需为实际使用的 AI 点数付费。Starting today, GitHub Enterprise customers can use all Copilot features without buying a separate subscription. That includes GitHub Copilot app, code review, automations, and more. You pay for the AI credits you use.

目前可通过 GitHub 销售团队获取，自助服务即将推出。现有 Copilot Business 和 Copilot Enterprise 客户可以继续使用当前方案，也可以在准备好后迁移。GitHub 也将继续保持开放和可扩展。继续使用团队所依赖的工具，包括 Cloudflare、Datadog、Figma 等。This is available through GitHub Sales today, with self-serve coming soon. Existing Copilot Business and Copilot Enterprise customers can keep their current plans or move over when they’re ready. GitHub also remains open and extensible. Keep using the tools your team depends on, including Cloudflare, Datadog, Figma, and more.

我们持续进行的基础设施投资Our continued infrastructure investments

这一切都依赖于一个快速、可靠且可扩展的基础。智能体正在改变软件开发的规模和形态。增加产能固然重要，但仅靠产能还不够。我们还必须改变架构。All of this depends on a foundation that’s fast, reliable, and built to scale. Agents are changing the volume and shape of software development. Adding capacity matters, but capacity alone won’t get us there. We’ve also had to change the architecture.

截至目前，今年我们新增了：So far this year, we’ve added:

• 400 万个 CPU 核心
  4 million CPU cores
• 160 PB 高速存储空间
  160 PB of high-speed storage
• 50 Tb/s 网络容量
  50 Tb/s network capacity

我们也在将部署迁移到 Azure 的多区域架构，同时继续为全球开发者承载惊人的流量。我们预计明年年初完成迁移。这些投入为我们提供了更大的发展空间。下一步是构建能够处理这些工作负载的系统。We’re also migrating to a multi-region deployment in Azure, while continuing to serve incredible levels of traffic from developers around the world. We expect to complete the migration early next year. Those investments give us more room to grow. The next step is building the systems that handle the work.

随着 GitHub 上的活动不断增长，我们多年来持续扩展 Git。智能体时代对吞吐量和可靠性提出了更高要求。我们全新的 Git 架构遵循三项原则：简化基础构件、将存储与计算解耦，以及尽量减少协调开销。We’ve scaled Git for years as activity on GitHub has grown. The agentic era calls for a different ceiling on throughput and reliability. Three principles guide our new Git architecture: simplify the primitives, decouple storage from compute, and minimize coordination.

Git 只是我们为扩展平台所做工作的一个例子。我们在 GitHub 的 AI 网关、运行框架等方面做了大量工作。Git’s just one example of the work we’re doing to scale the platform. We’ve done a lot of work across GitHub’s AI gateway, the harness, and much more.

超越最初的 1%Beyond the first 1%

我们的工作正在发生变化，但开发者比以往任何时候都更加重要。我认为，我们迄今编写的所有软件，加起来还不到未来五年内我们将编写的软件总量的 1%。机遇不只是编写更多代码，而是解决过去无法解决的问题。Our jobs are changing, but developers are more important than ever. I think all the software we’ve written to date will amount to less than 1% of the software we’ll write in the next five years. The opportunity isn’t just to produce more code. It’s to solve problems we couldn’t solve before.

这就是我们要打通整个软件交付体系、为开发者提供更好的智能体协作方式，并不断演进基础设施以迎接未来的原因。而这一切都将在 GitHub 上实现，让我们携手共建。That’s why we’re connecting the full software delivery system, giving developers better ways to work with agents, and evolving the infrastructure for what comes next. And we’re doing it on GitHub, where we can build together.