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
View all
Little ideas
Terkel Gjervig

Animating the native traffic lights in Ace

Post
Russell Horton

Agent Functions

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?

Little ideas
Terkel Gjervig

A loader with level of detail

Borrowed from 3D rendering: level of detail. The loader shows more as it grows and strips back as it shrinks, so it reads cleanly at any size.

Post
Tamás Szabó

Canary: a harm gate for agentic systems

Canary puts a small, auditable gate in front of agentic workflows so untrusted artifacts are classified before powerful agents act on them.

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.