Search results for: repository

GitHub Models evaluations tooling now supports multiple variables with any names, not just {{input}}! Previously, the tooling only recognized a single variable named {{input}}. Prompts using variables like {{experience}} or…

Following last month’s change that added the ability to turn off dependency graph, the setting for newly-created public repositories will now default to off. In addition, we’ve begun disabling it…

The open source Git project just released Git 2.50. Here is GitHub’s look at some of the most interesting features and changes introduced since last time.

GitHub Team plans can now configure and enforce organization-level rulesets! Previously, this powerful governance capability was limited to Enterprise plans, but now Team plan customers can scale their use of…

Copilot code review now supports the same custom instructions used by Copilot Chat and coding agent—unlocking personalized, consistent AI reviews across your workflow.

You can now save and evaluate multi-turn conversations in the GitHub Models prompt editor and evaluations tooling! Until now, the evaluations tooling only supported a single user prompt. With this…

The GitHub MCP Server allows AI tools like GitHub Copilot in VS Code and Visual Studio, Claude Desktop, and others to seamlessly access live GitHub context and tools—like issues, pull…

Tech debt is a big problem that no one has time to solve. GitHub Copilot coding agent can help.

We’ve enhanced scheduled reminders for Slack and Microsoft Teams to give you more control and ensure you’re focused on what matters most. These updates include: Receiving reminders for up to…

Delegated alert dismissal allows you to require a review process before secret scanning alerts are closed. This helps you better manage security risk, as well as meet audit and compliance…

You can now run prompt evaluations from the command line using the new gh models eval command. This evaluates prompts defined in a .prompt.yml file using the same built-in evaluators…

Have you tried the new coding agent in GitHub Copilot? Here’s how developers are using it to work more efficiently.

Evaluators are like continuous integration for your AI. They help you catch quality issues early and keep outputs aligned with your goals. Today, GitHub Models is adding two new scoring…

Learn how to spin up a GitHub Issue, hand it to Copilot, and get a draft pull request in the same workflow you already know.

We have improved the metrics for CodeQL pull request alerts and Copilot autofixes on the security overview dashboard. This change enables you to gain a better understanding of how Copilot…

The latest version of DeepSeek-R1, DeepSeek-R1-0528, is now available on GitHub Models. DeepSeek-R1-0528 is an updated version of DeepSeek-R1 with improved reasoning, inference, and performance via optimizations and enhanced computational…

GitHub Enterprise Server (GHES) 3.17 enhances deployment efficiency, monitoring capabilities, code security, and policy management. Here are a few highlights in the 3.17 release: GitHub Advanced Security (GHAS) is now…

If your organization hosts dependencies in private or internal GitHub repositories, you can give Dependabot access to the host repository, allowing Dependabot to update the dependency version. GitHub Advanced Security…

Dive into the novel security challenges AI introduces with the open source game that over 10,000 developers have used to sharpen their skills.

You can now define a required JSON schema directly in the prompt editor UI, just like in the Models playground. This helps ensure model responses follow a consistent structure, reducing…

Today’s engineering teams struggle with fragmented knowledge. Having critical context scattered across code, documentation, and inside of team members’ heads can make it hard to get up to speed in…