Continuous AI for accessibility: How GitHub transforms feedback into inclusion
AI automates triage for accessibility feedback, allowing us to focus on fixing barriers—turning a chaotic backlog into continuous, rapid resolutions.
AI automates triage for accessibility feedback, allowing us to focus on fixing barriers—turning a chaotic backlog into continuous, rapid resolutions.
In February, we experienced six incidents that resulted in degraded performance across GitHub services.
GitHub Dependabot now natively supports automatic dependency updates for pre-commit hooks. By adding pre-commit as a package ecosystem in your dependabot.yml configuration, Dependabot will parse your .pre-commit-config.yaml, check each hook’s…
GitHub Agentic Workflows are built with isolation, constrained outputs, and comprehensive logging. Learn how our threat model and security architecture help teams run agents safely in GitHub Actions.
How Copilot code review helps teams keep up with AI-accelerated code changes.
You can now assign Jira issues to GitHub Copilot coding agent, our asynchronous, autonomous agent, and get AI-generated draft pull requests created in your GitHub repository. When you assign a…
Copilot code review now runs on an agentic tool-calling architecture and is generally available for all users with Copilot Pro, Copilot Pro+, Copilot Business, and Copilot Enterprise. For background, see…
Developers connected to Andela share how they’re learning AI tools inside real production workflows.
Copilot Memory is now enabled by default for all GitHub Copilot Pro and Copilot Pro+ users. Previously in public preview as an opt-in feature, Copilot Memory allows Copilot to build…
Here’s how we made the search experience better, faster, and more resilient for GHES customers.
Learn how to get organized and collaborate more efficiently with this step-by-step tutorial.
GitHub Copilot usage metrics is now generally available, giving you a single place to see how your teams adopt and use Copilot. This way you can track trends, make informed…
GitHub Copilot coding agent now includes a model picker, self-review, built-in security scanning, custom agents, and CLI handoff. Here’s what’s new and how to use it.
Claude by Anthropic and OpenAI Codex are now available as coding agents for Copilot Business and Copilot Pro customers. Copilot Enterprise and Pro+ customers received access earlier this month, and…
Live Coding Agent Notifications are now available on GitHub Mobile, making it easier to stay on top of your Copilot coding agent and supported third-party agent sessions while you’re on…
GitHub Copilot CLI—the terminal-native coding agent that brings the power of GitHub Copilot directly to your command line—is now generally available for all Copilot subscribers. Editor’s note (February 27, 2026):…
GitHub Enterprise Server (GHES) 3.20 enhances deployment efficiency, monitoring capabilities, code security, and policy management. Here are a few highlights in the 3.20 release: The improved merge experience on the…
Dependabot now supports grouping updates by dependency name across multiple directories, making it easier to manage dependency upgrades in repositories with more than one package or service. What’s changed Previously,…
Most multi-agent workflow failures come down to missing structure, not model capability. Learn the three engineering patterns that make agent systems reliable.
Copilot coding agent is our asynchronous, autonomous background agent. Delegate a task to Copilot, and Copilot works in the background in its own development environment in the cloud. Once Copilot…
Copilot coding agent is our asynchronous, autonomous background agent. Delegate a task to Copilot, and Copilot works in the background in its own development environment, powered by GitHub Actions. By…
Build what’s next on GitHub, the place for anyone from anywhere to build anything.
Join us October 28-29 in San Francisco or online for GitHub Universe, our flagship developer event uniting people, agents, and the world’s code.