The next frontier of agentic development is here, and you are in control.
Today we announced releases that will keep you in the flow with your agents, all on the GitHub platform. ⬇️
The key was separating noise from real risk, validating active credentials, finding owners, and making remediation a shared responsibility across engineering.
📣 GPT-5.5 this weekend: 60% off for Copilot Max users and 40% off for Pro+ users. 🎉
Put it toward a tricky bug, a larger change, or updates across multiple files — wherever you use Copilot.
No code or opt-in required. Happy coding. ✅
You can now use Vercel Plugin with @github Copilot CLI and VS @code:
• 30 platform skills
• 3 specialized agents
• 4 built-in commands
• Real-time code validation
Get started ↓
Repository admins can now archive pull requests 🚀
If spammy or low-quality PRs are piling up, admins can now clean things up without losing that history.
Another step toward giving maintainers more control over contributions in their repositories.
Ghana is exploring how to make open source a sustainable default across government.
GitHub and UNDP brought together public-sector and community leaders to assess the policies, skills, and coordination needed to make it happen.
We've put all of our GitHub for Beginners guides into one roadmap for anyone still filling in that blank.
Bookmark this, or share with a friend who's just getting started 👇
GitHub Copilot for @Atlassian's Jira is now generally available.
With Copilot in Jira, you can:
• stream agent progress to Jira
• provide follow-up instructions directly in the Jira chat panel
• connect your GitHub org and repos to the Jira app faster with fewer steps at the
Stay connected to your Copilot CLI sessions from anywhere.
GitHub Mobile now supports live notifications for remote Copilot CLI sessions. Track progress, know when input is needed, and jump back into session logs to unblock right from your phone.
Get faster, more reliable coding sessions in GitHub Copilot CLI.
We implemented smarter subagent delegation that cut tool failures 23%, search failures 27%, and edit failures 18%, with no quality regression.
