GitHub Next investigates the future of software development.

We are a team of researchers and engineers at GitHub, exploring things beyond the adjacent possible. We prototype tools and technologies that will change our craft. We identify new approaches to building healthy, productive software engineering teams.

@agorischek @agorischek
@davidslater @davidslater
@dsyme @dsyme
@iamnbutler @iamnbutler
@idan @idan
@insop @insop
@krzysztof-cieslak @krzysztof-cieslak
@lpcox @lpcox
@lukeed @lukeed
@maggieappleton @maggieappleton
@mnkiefer @mnkiefer
@mrjf @mrjf
@pelikhan @pelikhan
@rahulpandita @rahulpandita
@szabta89 @szabta89
@terkelg @terkelg
Link
Don Syme

The Impact of Automated Repository Maintenance Assistance

https://github.com/githubnext/repo-assist-impact/blob/main/report.md

What happens when a proactive AI repository agent is deployed across 13 open source repositories? 578 issues closed, median 8x increase in issue closure velocity, and 10x in 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.

Read the full report from GitHub Next.

A black-and-white three-panel comic in a minimalist zine style showing the evolution of tooling and industrial scale. In the first panel, a small cat-like worker character uses a chainsaw to cut a log in a forest. In the second panel, the character operates a stationary sawmill cutting large timber beams with industrial machinery. In the third panel, the character, now wearing a hard hat, stands inside a massive automated lumber mill with conveyor belts, robotic arms, and full-scale production lines processing stacks of wood. Clean line art, no text, monochrome aesthetic.
Post
Peli de Halleux

Agents are power tools

A practical mental model for agents, workflows, and human-machine systems in agentic engineering.

Post
Alex Gorischek

Agency is the New Resilience

Agents can power robust workflows by intelligently reacting to unexpected conditions, creating a new form of flexible resilience.

Link
Don Syme

Understanding Repositories as Human/Agent Knowledge Factories

https://dsyme.net/2026/05/05/understanding-repositories-as-human-agent-knowledge-factories-%f0%9f%9a%80/

How do you maintain team velocity when AI-generated code needs cleanup? You have two choices: slow everyone down with more review hurdles, or let automated agentic processes clean things up after the fact. The second path is the key to velocity — and it’s now practical with repository automation.

Read more on the blog of our Principal Researcher Don Syme.

Little ideas
Idan Gazit

New site, who dis?

Ok, it’s not really a new site. But it’s an important refresh!

Glossy finished products are fun, but the real meat is hiding in the sketchbooks. Makers love to see the raw ideas, the struggle to make it work, and the tradeoffs made in service to shipping. Previously, we only had project pages, but we didn’t have a place to showcase those intermediate artifacts of our work.

Our new site makes it easy for any member of Next to share a learning, a screenshot, a thought, or a full-blown essay. It could be a tiny demo, or an update to an existing project. Working for the public good — and largely in the open — is one of the key perks we enjoy at Next. We’re looking forward to sharing more of our behind the scenes with you, without needing to fit everything into a tweet-shaped chunk of content.

Under the hood, we also wanted to transition to a static site framework like Astro for ease of maintenance. Shoutout to the Astro folks, it’s so good.

Enjoy the new site, we’re excited to share more with you!

Link
Don Syme

Lean Squad: Exploring Automated Software Verification with Near-Zero Human Labour

https://dsyme.net/2026/04/20/lean-squad-automated-software-verification-with-near-zero-human-labour/

What if formal verification could be fully automated — from researching the codebase, to writing specifications, to proving theorems in Lean 4 — all with near-zero human involvement? Lean Squad is a GitHub Agentic Workflow that does exactly this. Applied to three real-world codebases, it produced over 1,200 machine-checked theorems and found real bugs in a drone autopilot.

Read more on the blog of our Principal Researcher Don Syme.