GitHub Next

A new report from GitHub Next! The Impact of Automated Repository Maintenance Assistance githubnext.com/posts/dsyme-im… What happens when a proactive AI repository agent is deployed across 13 open source repositories? Hundreds of issues closed, median ~8x increase in issue closurea nd PR merge velocity - transforming largely dormant projects into actively maintained ones. The single most important factor? The rate at which human maintainers decide to act. #ContinuousAI #RepoAssist #GitHubNext

Agents Need Boundaries Too! Read about this GitHub Next exploration of reusable harm gates, to keep the agents in the channel to success, even when subverted by attackers. githubnext.com/posts/canary-h… #GitHubNext #AgenticAI

Read about "Agent Functions", a new agentic design pattern for structuring agents, from GitHub Next githubnext.com/posts/agent-fu… Prompts are programs. You wouldn’t write a complex program completely from scratch, in a big, soupy loop without subroutines, and then write it again the next time you wanted to run it. Why let your agent work that way?

At GitHub Next, the Autoloop agent is porting Pandas to Typescript Read about this experiment in simple, declarative goal-directed repository automation! githubnext.com/posts/tsb/

Ace👀

We have a draft of new report from GitHub Next! 🚀 github.com/githubnext/rep… The Impact of Automated Repository Maintenance Assistance - We analyze the impact of 🌈 Repo Assist, a proactive AI repository agent implemented as a GitHub Agentic Workflow, across 13 open source repositories in early 2026. - The agent reduced open issue counts in every repository - 578 issues total. - The repositories, which were largely dormant, achieved median velocity increases of 8× for issue closure and 10× for PR merges, transforming largely dormant projects into actively maintained ones. - We model repositories as human-agent software factories - the factory’s throughput is gated by human decision-making. Read the draft in our repository github.com/githubnext/rep…

Thanks for the feedback. We will add notes along these lines: * The rate of "/repo-assist" human guided agentic intervention is mentioned in the report. * There was little other review override - some but not much. * Reopen rate was essentially zero. * Learning memory repo norms is not part of the spec of repo-assist, it could be added through memory.

@GitHubNext The useful signal is not just merged PRs; it is maintenance debt avoided. I would want to see reopen rate, reviewer override rate, and whether Repo Assist learns repo-specific norms without turning every maintainer preference into hidden policy.

Post #7 in Peli's Agent Factory - Continuous Documentation! github.github.io/gh-aw/blog/202…

Post #6 in Peli's Agent Factory - Continuous Improvement! github.github.io/gh-aw/blog/202…

Agentic repository automation changes almost everything about how we engineer software. We've discovered this at GitHub Next over the last 6 months, and the rest of the world will (re)discover it too, over the coming years. To help you take the journey faster, and be ahead of the wave, we've prepared a blog series for you called Peli's Agent Factory, where @pelikhan takes you on a journey through repository automation and its uses github.github.com/gh-aw/blog/202…

Animating the native traffic lights in Ace

👀