GitHub Universe 2026 发布 GitHub Copilot app、Copilot Fusion 等智能体产品

来源:GitHub Blog 2026年10月28日 00:09 AIHOT 评分:71 精选
摘要:GitHub 在 GitHub Universe 2026 上提出把 GitHub 打造为完整软件交付系统的愿景,并发布多项产品:GitHub Copilot app 面向智能体交付。
推荐理由:原文是 GitHub 官方对 Universe 2026 新品的集中说明,给出各功能的定位和关键数据,便于读者评估对现有工作流的影响。
# GitHub Universe 2026 发布 GitHub Copilot app、Copilot Fusion 等智能体产品 > 原标题:GitHub Universe 2026: Evolving every layer of the stack - 来源:GitHub Blog - 发布时间:2026-10-28T16:09:28.000Z - AIHOT:https://aihot.news/items/xonc43xgcx39303i40k8022rl - 原文:https://github.blog/news-insights/company-news/github-universe-2026-evolving-every-layer-of-the-stack/ ## 摘要 GitHub 在 GitHub Universe 2026 上提出把 GitHub 打造为完整软件交付系统的愿景,并发布多项产品:GitHub Copilot app 面向智能体交付。 ## 推荐理由 原文是 GitHub 官方对 Universe 2026 新品的集中说明,给出各功能的定位和关键数据,便于读者评估对现有工作流的影响。 ## 正文 · 中文译文 作为开发者的工作正在发生变化。短短几年间,我们从逐行编写每一行代码,发展到与 AI 助手协作,再到编排成群的智能体。但目标始终未变:交付完成的软件工作。一个功能、一个缺陷修复、一个安全修复。真正重要的产出是完成的工作,而不是更多的代码。 今天在 [GitHub Universe](https://github.com/events/universe/recap?utm_source=gh-universe-blog-k2k&utm_medium=blog&utm_campaign=universe-2026) 上,我们分享了将 GitHub 打造为全球最全面的软件交付系统的愿景。我们推出了让这一愿景落地的产品,并展示了我们如何重建其底层基础设施。 ## 我们的愿景:从想法到完成的软件 [SDLC 不再是一条线性](https://commandline.microsoft.com/new-agentic-software-delivery-primitives/)的从规划到编码、测试再到部署的路径。一次代码变更、一位同事的请求,或一项生产指标,都可能触发系统中任意位置的工作。我们大多数人(以及我们的智能体)会根据手头的任务在不同阶段之间跳转。开发者把握方向、做出决策,并对最终交付的内容负责。智能体负责实施和验证变更。而一切都汇入并出自一台持续学习的机器,让下一个周期变得更好。 这套智能体软件交付系统解决三件事: - **速度:**尽可能快速、高效、低成本地从想法走向完成的软件 - **智能:**将平台各处的上下文与持续学习引擎相结合,让系统随着你的使用而不断变好 - **质量:**让完成的工作默认安全,并在缺陷交付前将其捕获 GitHub 为开发者及其智能体而构建。我们还将底层原语开放出来,让你可以构建自己的定制化解决方案。工作内容、工具和成本始终由你掌控。 ## 推动工作向前的新功能与产品 今天在 Universe 上,我们展示了一些最新产品和功能的实际应用,首先是 GitHub Copilot 应用。 ### GitHub Copilot 应用:从 issue 到合并,一个应用搞定 [GitHub Copilot 应用](https://github.com/features/ai/github-app?utm_source=gh-universe-blog-app-feature&utm_medium=blog&utm_campaign=universe-2026)从设计之初就面向智能体软件交付。它跨项目连接你的智能体和工具,让你无需亲自完成每一次交接即可指挥工作。而且它不止用于产出代码:你可以在一个智能体优先的界面中编写规格、进行设计讨论或分析遥测数据。 ### Copilot Fusion:多模型编排的极致 不同的任务需要不同的模型。开发者不应为了以合适的价格获得合适的结果而必须管理每一个模型选择。[Copilot Fusion](https://docs.github.com/copilot/concepts/models/copilot-fusion?utm_source=gh-universe-blog-fusion-docs&utm_medium=blog&utm_campaign=universe-2026) 会评估任务在推理、代码生成、调试和工具使用方面的需求,然后决定如何在一个或多个模型上执行。在 Artificial Analysis Coding Agent Index 中,Fusion Max 的得分与 Opus 5.5 Max 相差不到两分,而成本减半,每个任务耗时减少 40%。 ### Copilot projects:给 Copilot 一个目标 从今天起在 GitHub Copilot 应用中原生提供,[Copilot projects](https://docs.github.com/copilot/how-tos/github-copilot-app/working-with-projects?utm_source=gh-universe-blog-projects-docs&utm_medium=blog&utm_campaign=universe-2026) 让你在完全托管、并行的会话中跨多个仓库运行智能体工作。你可以在一个地方跟踪进度、做出决策并指挥下一步。这意味着你可以少花时间管理执行,多花时间决定什么值得构建。 ### 会话连续性:跨界面持续工作 你的工作不应在切换设备或工具时重新开始。[会话连续性](https://docs.github.com/copilot/how-tos/copilot-on-github/use-copilot-agents/manage-and-track-agents?utm_source=gh-universe-blog-session-continuity-docs&utm_medium=blog&utm_campaign=universe-2026#continue-a-session-from-another-client)让你可以在 GitHub 应用、VS Code、CLI 和网页端启动并跟进同一个云端智能体会话。在站会上用手机启动,在办公桌前用 VS Code 引导它,午餐时从 github.com 查看进展。智能体持续在云端工作。支撑这一切的多模型 harness 强大、快速且经济高效。 ### Copilot automations:从结果中学习 [Copilot automations](https://docs.github.com/copilot/concepts/agent-capabilities/agent-powered-workflows-and-operations/about-automations?utm_source=gh-universe-blog-automations-docs&utm_medium=blog&utm_campaign=universe-2026) 让你在仓库内创建 AI 驱动的工作流。它们在云端运行,你可以手动触发,也可以设置为响应事件或按计划运行。这样你就能协调智能体处理问题分类和代码审查等任务。现在,automations 可以从结果中学习,并提出改进建议供你审查和批准。这就是实践中的学习引擎。利用已完成工作的结果让下一次运行更好。 ### Copilot code review Max:更深入地审视交付内容 更多代码意味着更多拉取请求和更多审查需求。只有保持交付质量,提速才有意义。[Copilot code review](https://docs.github.com/copilot/concepts/agent-capabilities/agent-powered-workflows-and-operations/code-review?utm_source=gh-universe-blog-code-review-overview-docs&utm_medium=blog&utm_campaign=universe-2026) 能揭示开发者需要捕捉的有意义、可操作的缺陷。今天,我们推出了 Copilot code review 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;新的 Max 则在变更需要时提供更深入的分析。 ### 无需单独企业订阅即可使用 Copilot 功能 从今天起,GitHub Enterprise 客户无需购买单独订阅即可使用所有 Copilot 功能。这包括 GitHub Copilot 应用、代码审查、automations 等。你只需为使用的 AI 额度付费。 该服务今天可通过 [GitHub Sales](https://github.com/enterprise/contact?utm_source=gh-universe-blog-contact-sales-form&utm_medium=blog&utm_campaign=universe-2026) 获取,自助购买即将推出。现有的 Copilot Business 和 Copilot Enterprise 客户可以保留当前计划,或在准备好时迁移。GitHub 也保持开放和可扩展。继续使用你团队依赖的工具,包括 Cloudflare、Datadog、Figma 等。 ## 我们持续的基础设施投入 所有这些都依赖于一个快速、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。增加容量很重要,但仅有容量还不够。我们还必须改变架构。 今年到目前为止,我们新增了: - 400 万个 CPU 核心 - 160 PB 高速存储 - 50 Tb/s 网络容量 我们还在[迁移到 Azure 的多区域部署](https://github.blog/engineering/architecture-optimization/the-bridge-to-agent-scale-git-infrastructure/?utm_source=gh-universe-blog-git-infra-blog&utm_medium=blog&utm_campaign=universe-2026),同时继续为全球开发者提供极高水平的流量服务。我们预计明年年初完成迁移。这些投入为我们提供了更多增长空间。下一步是构建处理这些工作的系统。 多年来,随着 GitHub 上活动的增长,我们一直在扩展 Git。智能体时代需要不同的吞吐量和可靠性上限。三条原则指导我们新的 [Git 架构](https://github.blog/engineering/architecture-optimization/building-git-infrastructure-for-agent-scale-development/?utm_source=gh-universe-blog-git-architecture-blog-1&utm_medium=blog&utm_campaign=universe-2026):简化原语、将存储与计算解耦、最小化协调。 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、harness 以及更多方面做了大量工作。 ## 超越最初的 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,迄今为止我们编写的所有软件,加起来还不到未来五年我们将编写的软件的 1%。机会不仅在于产出更多代码,更在于解决我们以前无法解决的问题。 这就是为什么我们正在连接完整的软件交付系统,为开发者提供与 agent 协作的更好方式,并为未来演进基础设施。我们正在 GitHub 上做这件事,在这里我们可以共同构建。 文章 [GitHub Universe 2026:演进技术栈的每一层](https://github.blog/news-insights/company-news/github-universe-2026-evolving-every-layer-of-the-stack/) 首次出现在 [The GitHub Blog](https://github.blog/)。 ## 正文 · 原文 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. Today at [GitHub Universe](https://github.com/events/universe/recap?utm_source=gh-universe-blog-k2k&utm_medium=blog&utm_campaign=universe-2026), 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. ## Our vision: From idea to completed software The [SDLC is no longer a linear](https://commandline.microsoft.com/new-agentic-software-delivery-primitives/) 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. This agentic software delivery system solves for three things: - **Velocity:** get from idea to completed software as quickly, efficiently, and cost-effectively as possible - **Intelligence:** combine context across the platform with a continuous learning engine, so the system gets better as you use it - **Quality:** make completed work secure by default and catch bugs before they ship 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. ## New features and products that move the work forward Today at Universe, we showed some of the latest products and features in action, starting with the GitHub Copilot app. ### GitHub Copilot app: From issue to merge, in one app The [GitHub Copilot app](https://github.com/features/ai/github-app?utm_source=gh-universe-blog-app-feature&utm_medium=blog&utm_campaign=universe-2026) 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: Multi-model orchestration at its finest 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](https://docs.github.com/copilot/concepts/models/copilot-fusion?utm_source=gh-universe-blog-fusion-docs&utm_medium=blog&utm_campaign=universe-2026) 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 projects: Give Copilot a goal Available natively in the GitHub Copilot app starting today, [Copilot projects](https://docs.github.com/copilot/how-tos/github-copilot-app/working-with-projects?utm_source=gh-universe-blog-projects-docs&utm_medium=blog&utm_campaign=universe-2026) 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. ### Session continuity: Keep working across surfaces Your work shouldn’t restart when you switch devices or tools. [Session continuity](https://docs.github.com/copilot/how-tos/copilot-on-github/use-copilot-agents/manage-and-track-agents?utm_source=gh-universe-blog-session-continuity-docs&utm_medium=blog&utm_campaign=universe-2026#continue-a-session-from-another-client) 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 automations: Learning from the results [Copilot automations](https://docs.github.com/copilot/concepts/agent-capabilities/agent-powered-workflows-and-operations/about-automations?utm_source=gh-universe-blog-automations-docs&utm_medium=blog&utm_campaign=universe-2026) 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 code review Max: A deeper look at what ships 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](https://docs.github.com/copilot/concepts/agent-capabilities/agent-powered-workflows-and-operations/code-review?utm_source=gh-universe-blog-code-review-overview-docs&utm_medium=blog&utm_campaign=universe-2026) 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. ### Copilot features without a separate enterprise subscription 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. This is available through [GitHub Sales](https://github.com/enterprise/contact?utm_source=gh-universe-blog-contact-sales-form&utm_medium=blog&utm_campaign=universe-2026) 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. ## Our continued infrastructure investments 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. So far this year, we’ve added: - 4 million CPU cores - 160 PB of high-speed storage - 50 Tb/s network capacity We’re also migrating [to a multi-region deployment in Azure](https://github.blog/engineering/architecture-optimization/the-bridge-to-agent-scale-git-infrastructure/?utm_source=gh-universe-blog-git-infra-blog&utm_medium=blog&utm_campaign=universe-2026), 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. 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](https://github.blog/engineering/architecture-optimization/building-git-infrastructure-for-agent-scale-development/?utm_source=gh-universe-blog-git-architecture-blog-1&utm_medium=blog&utm_campaign=universe-2026): simplify the primitives, decouple storage from compute, and minimize coordination. 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. ## Beyond the first 1% 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. 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. The post [GitHub Universe 2026: Evolving every layer of the stack](https://github.blog/news-insights/company-news/github-universe-2026-evolving-every-layer-of-the-stack/) appeared first on [The GitHub Blog](https://github.blog/).