Home / News & insights / Product

New from Universe 2024: Get the latest previews and releases

Find out how we’re evolving GitHub and GitHub Copilot—and get access to the latest previews and GA releases.

·@mariorod
|
| 13 minutes

Welcome to your flow state.

This year marks our tenth GitHub Universe—and one theme has remained constant: our focus on developers and the developer experience. Over 10 years, that developer experience has evolved from inventing the pull request to building the world’s most widely adopted AI coding tool, GitHub Copilot.

Today, our platform serves more than 100 million developers, and through the power of this interconnected community combined with generative AI, we are enabling every developer to build, release, scale, and secure software rapidly.

We have a lot to cover. As developers, we’re not known for being patient. So, let’s jump in.

Introducing new, powerful AI-native experiences

The best model for the task: the power of developer choice

We are bringing developer choice to GitHub Copilot with Anthropic’s Claude 3.5 Sonnet, Google’s Gemini 1.5 Pro, and OpenAI’s o1-preview and o1-mini. These new models will be rolling out—first in Copilot Chat, with OpenAI o1-preview and o1-mini available now, Claude 3.5 Sonnet rolling out progressively over the next week, and Google’s Gemini 1.5 Pro in the coming weeks. From Copilot Workspace to multi-file editing to code review, security autofix, and the CLI, we will bring multi-model choice across many of GitHub Copilot’s surface areas and functions soon.

Whether it’s in VS Code or on GitHub.com, individual developers can now decide which models work best for them, while organizations and enterprises have full control over which models they enable for their team. Try multi-model Copilot today!

AI-native = GitHub Copilot Workspace + Code Review + Copilot Autofix

With Copilot Workspace in pull requests, you can rapidly refine, validate, and land Copilot-generated code suggestions coming from Copilot code review, Copilot Autofix, and third-party Copilot Extensions. Get your pull requests “ready to merge” faster than ever. Learn about GitHub Copilot Workspace and Copilot Code Reviews >

A screenshot of a GitHub Copilot Workspace editor for a pull request showing Copilot assisting a developer by suggesting code to fix an authentication error. On the left, there is a list of files in the pull request. On the right, a conversation between the developer and Copilot shows that Copilot has identified the syntax error in the code and is suggesting a fix for it, with a natural language explanation. The middle panel shows the failed build and the Typescript code, with Copilot suggested code inserted. At the top of the screen there is a green button labeled ‘Review and commit’ and a button showing three total suggestions.

Bring your ideas to life with GitHub Spark

It starts with an idea. It always does. When we’re kids, we have thousands of them. Many of them are silly. Some of them are crazy. Today, we are giving you a new product to try all of them. We call it GitHub Spark—it’s powered by natural language, and it sets the stage for our vision to help 1 billion people become developers. This is about fun and personal software, not about enterprise productivity apps. With live history, previews, and the ability to edit code directly, GitHub Spark allows you to create micro apps that take that crazy small, fun idea and bring it to life. Go and play… Learn about the GitHub Spark technical preview >

A screenshot of GitHub Spark, an experimental application by GitHub Next, on a mobile phone. The application enables people to build software with natural language prompts. The top of the application has a text box asking, ‘What do you want to create?’, a ‘Generate variants?’ checkbox, and a drop-down list with ‘GPT-4o’ selected. Below that, there is a list of recent sparks titled Carter Boys Allowance Tracker, Find my City, Spark News, and Tic-Tac-Taco.

Increasing your productivity with the Copilot-powered developer platform

Momentum is our oxygen. And that is why we are announcing a wide range of improvements to accelerate how you build, release, scale, and secure software. Get ready to unlock your creativity.

Raising the quality of your Copilot-powered experiences

These updates enhance your development workflow with new features like multi-model choice, improved code completion, implicit agent selection in GitHub Copilot Chat, better support for C++ and .NET, and expanded availability in Xcode and Windows Terminal. READ MORE ⤵️
  • Multi-model choice and access to OpenAI’s o1 model in GitHub Copilot. Toggle between different AI models during conversations, seamlessly switching from explaining APIs or generating boilerplate code to designing complex algorithms or analyzing logic bugs. Copilot users now have access to the o1-preview and o1-mini models in Copilot Chat and GitHub Models.

  • Custom instructions. Specify custom instructions to personalize Copilot Chat responses in VS Code and Visual Studio, based on your preferred tools, organizational knowledge, and coding conventions.

  • Improvements to code completion and chat quality. Enjoy enhanced contextual performance along with a preview of a new debugging experience initiated through Copilot Chat.

  • Selection of agents in Copilot Chat. Copilot Chat in VS Code can automatically invoke internal and external agents—such as @workspace, @github, and other installed Copilot extensions—to provide more relevant responses.

  • Better language support for C++ and .NET. Improved C++ completion quality in VS Code and Visual Studio with more relevant context. Plus, Copilot Chat now has increased performance in project-specific properties for C++ and .NET in Visual Studio.

  • GitHub Copilot for Xcode. GitHub Copilot code completion is now available in Xcode, enabling macOS and iOS developers to leverage its capabilities.

  • GitHub Copilot in Windows Terminal. Interact with GitHub Copilot directly from the Windows Terminal through a chat-based interface.

Enhancing how you work in your IDE

We’re introducing several updates to GitHub Copilot to boost productivity across various IDEs, including new @github skills, error explanations, and improved code assistance. READ MORE ⤵️
  • Improved skills and search in Copilot Chat. Search across GitHub for commits, issues, pull requests, repositories, and releases directly from Copilot Chat in VS Code.

  • Explain and fix C++ and C# errors in Visual Studio. Use GitHub Copilot to understand and resolve C++ and C# errors within Visual Studio.

  • Quick info on C++ and C# in Visual Studio. Instantly learn about C++ and C# symbols by hovering to invoke Copilot in the Quick Info dialog.

  • Improved code referencing. Easily see if a code suggestion matches public code, including file locations and licensing information.

  • Bing integration in Copilot Chat. Search with Bing directly from Copilot Chat in VS Code and Visual Studio for Individual and Business users.

  • .NET test debugging. Debug .NET code tests seamlessly within Visual Studio.

Simplifying your workflows with GitHub Copilot Extensions

Whether you’re an individual developer looking to streamline your workflow or an organization aiming to integrate proprietary tools, GitHub Copilot Extensions now offers a platform to make that happen and to share your creations on the GitHub Marketplace. READ MORE ⤵️
  • GitHub Copilot Extensions. Extend GitHub Copilot with ready-to-use extensions, build your own, and get access to third-party applications and internal systems for a more personalized experience.

  • Copilot Extensions in GitHub Mobile. You can now access extensions in Copilot Chat while on the go, right from your phone.

  • GitHub Copilot for Azure. Deploy and manage Azure services, find and deploy application templates, and diagnose and troubleshoot application issues.

Making it easy to build generative AI applications with GitHub Models

GitHub Models makes it simple to use, compare, experiment, and build with AI models from OpenAI, Cohere, Microsoft, Mistral, and more. Starting today, developers and AI engineers can access new capabilities on GitHub Models, including side-by-side model comparison, support for multi-modal models, the ability to save and share prompts and parameters, and new cookbooks and SDK support in GitHub Codespaces.

⭐️ Explore what’s new with GitHub Copilot ⭐️

A more secure developer experience where found means fixed

Security should never be a bottleneck for developers. That’s why we’re making it part of the development process with GitHub Copilot Autofix. Our goal is simple: when a vulnerability is found, it gets fixed—fast.

More secure code from the IDE to production

We know developers are often on the front lines of security. That’s why we want to make it easier for you to write more secure code from start to finish with Copilot Autofix, our Copilot-powered vulnerability remediation tool, now reaching further into your workflows and code. READ MORE ⤵️
  • Improved CodeQL coverage. Address security debt and historical CodeQL alerts with Copilot-generated fixes that cover more than 90% of alert types in JavaScript, Typescript, Java, Python, Ruby, C#, C/C++, and Go.

  • Copilot secret scanning. Copilot secret scanning, which detects generic passwords using AI, offers greater precision for unstructured credentials that can cause security breaches if exposed. Over 350,000 repositories have already enabled this password detection.

  • New partner integrations. Integrate Copilot Autofix natively with supported partner code scanning tools of your choice, starting with ESLint, JFrog SAST, and Black Duck’s Polaris™ platform (powered by Coverity®).

  • Copilot Autofix for Dependabot. Get natural language explanations and pull request code suggestions to update between major versions of dependencies seamlessly.

⭐️ Explore what’s new with GitHub Advanced Security ⭐️

Enterprise-grade experiences that put you in control

From powerful new GitHub Actions runners to enhanced project management tools (and a whole lot more), we’re investing in increasing your iteration velocity while keeping you compliant at every step.

Improved controls for governance and compliance

We know maintaining governance and compliance is critical for you—and definitely for your administrators. That’s why we’re introducing new features to give admins more control over user management, repository policies, and security workflows. This is governance at scale. And happy admins mean happy devs. READ MORE ⤵️
  • Bring your own identity provider to Enterprise Managed Users (EMUs). Use the SSO and SCIM providers of your choice, separate from one another, for a more flexible approach to user life cycle management.

  • Prevent commits that include specific changes with push rulesets. Limit updates to sensitive files like actions workflows and help enforce code hygiene by keeping unwanted objects out of your repositories with push rulesets.

  • Enterprise repository policies. Manage repository lifecycles with granular governance of repository configurations across your enterprise and its organizations.

  • Enterprise custom repository properties. Create and manage custom repository properties across your organizations, and promote existing organization properties to the enterprise.

  • Immutable GitHub Actions. Secure your supply chain with semantically versioned, immutable actions stored in GitHub Packages.

  • Create custom organization roles. Use repository-level permissions and roles at the organizational-level across all repositories in an organization.

  • GitHub Apps for your organization. Create enterprise-owned, internal-visibility GitHub Apps for installation across your organizations.

  • PATs and fine-grained PATs lifetime requirements policy. Set maximum lifetime requirements for Personal Access Tokens (PATs) that access enterprise resources.

  • The new GitHub Enterprise Trust Center. Find information on key topics for your enterprise like privacy, security, and data protection all in one place.

More compute resources and better insights for your workflows

No matter what you’re doing, compute power matters—and so do performance and API insights. That’s why we’re introducing new Arm64-powered runners and improving performance tracking across your workflows and CI/CD pipelines on GitHub Actions and API activity on GitHub. READ MORE ⤵️
  • Arm64 GitHub-hosted runners. Build, test, and deploy on Arm64 GitHub-hosted runners on GitHub Free plans to unify your CI/CD workflow and optimize compute costs. This feature will be released broadly in early 2025.

  • Performance metrics for GitHub Actions. Monitor and optimize your GitHub Actions workflows and job performance to eliminate inefficiencies.

  • API insights. Investigate and resolve API rate-limiting of your GitHub integrations via an in-product dashboard with insights to help monitor API activity.

⭐️ Explore what’s new with GitHub Enterprise ⭐️

Your multi-model, AI-native developer experience starts today

Thank you for building with GitHub. If there’s one takeaway we want you to leave with, it’s that software development has never been more exciting.

Today we’re giving you choices with AI models from OpenAI, Anthropic, and Google—so you can pick the right tool for the task. This choice is also powering AI-native developer experiences designed to enable new ways of thinking and coding.

With GitHub Copilot Workspace and GitHub Spark, natural language is taking center stage and powering a future where we merge the developer canvas with powerful agents that simplify your workflows and unlock your creativity at scale. This is the innovation we need to foster the next 1 billion developers, and help them continue to accelerate human progress.

To GitHub Universe, happy birthday. 🎉 And to our global developer community, we ❤️ you, and we’ll see you all again next year. Let’s build from here—together.

Want the most recent updates?
Stay informed about the latest in software development by subscribing to the GitHub Changelog.

Explore the Changelog >

Tags:

Written by

Mario Rodriguez

Mario Rodriguez

@mariorod

Mario Rodriguez leads the GitHub Product team as Chief Product Officer. His core identity is being a learner and his passion is creating developer tools—so much so that he has spent the last 20 years living that mission in leadership roles across Microsoft and GitHub. Mario most recently oversaw GitHub’s AI strategy and the GitHub Copilot product line, launching and growing Copilot across thousands of organizations and millions of users. Mario spends time outside of GitHub with his wife and two daughters. He also co-chairs and founded a charter school in an effort to progress education in rural regions of the United States.

Related posts