GitHub (@github) header
GitHub (@github) profile picture

GitHub

@github

The AI-powered developer platform to build, scale, and deliver secure software.

 San Francisco, CA
github.com
Joined February 2008
  • Tweets11.1K
  • Following335
  • Followers2.7M
3.2KMedia
Photo by GitHub (@github)Photo by GitHub (@github)Photo by GitHub (@github)Photo by GitHub (@github)Photo by GitHub (@github)Photo by GitHub (@github)Photo by GitHub (@github)Photo by GitHub (@github)Photo by GitHub (@github)Photo by GitHub (@github)
Pinned Tweet
GitHub (@github) profile picture
GitHub
@githubOct 28
Frontier performance at a fraction of the cost. In the @ArtificialAnlys Coding Agent Index, Copilot Fusion Max scored within two points of Claude Code with Opus 5.5 Max at about half the API cost per task. Get 30% off through Nov. 30. Try it now. ⬇️ docs.github.com/copilot/conc…
Chart titled "Coding Agent Index vs. Cost per Task" by Artificial Analysis. The chart displays Artificial Analysis Coding Agent Index vs. average pay-per-token API cost per task (USD). It compares various agents, including some from Claude Code, Codex, Antigravity CLI, DeepSeek Harness, Grok Build, Opencode, Muse Code, Kimi Code CLI, and GitHub Copilot. The x-axis represents higher cost per task (USD) to lower cost per task (USD), and the y-axis represents the coding agent index. The chart highlights a "Most Attractive Quadrant" in green and uses dots to differentiate agents. Copilot Fusion (max) sits within the most attractive quadrant.

ALT Chart titled "Coding Agent Index vs. Cost per Task" by Artificial Analysis. The chart displays Artificial Analysis Coding Agent Index vs. average pay-per-token API cost per task (USD). It compares various agents, including some from Claude Code, Codex, Antigravity CLI, DeepSeek Harness, Grok Build, Opencode, Muse Code, Kimi Code CLI, and GitHub Copilot. The x-axis represents higher cost per task (USD) to lower cost per task (USD), and the y-axis represents the coding agent index. The chart highlights a "Most Attractive Quadrant" in green and uses dots to differentiate agents. Copilot Fusion (max) sits within the most attractive quadrant.

Bar chart titled "Artificial Analysis Coding Agent Index". Incorporates 3 benchmarks: FrontierCode v1.1, Terminal-Bench 4.0, SWE-Atlas-QnA-AA. A higher scroe denotes higher average intelligence across becnhmarks. Copilot Fusion Max from GitHub Copilot has a score of 60. The chart also includes various coding agents from Claude Code, Devin Fusion CLI, Antigravity CLI, Codex, Grok Build, DeepSeek Harness, Muse Code, Opencode, Antigravity CLI, and Kimi Code CLI, with scores ranging from 62 to 41. Source and logo of Artificial Analysis are included at the bottom.

ALT Bar chart titled "Artificial Analysis Coding Agent Index". Incorporates 3 benchmarks: FrontierCode v1.1, Terminal-Bench 4.0, SWE-Atlas-QnA-AA. A higher scroe denotes higher average intelligence across becnhmarks. Copilot Fusion Max from GitHub Copilot has a score of 60. The chart also includes various coding agents from Claude Code, Devin Fusion CLI, Antigravity CLI, Codex, Grok Build, DeepSeek Harness, Muse Code, Opencode, Antigravity CLI, and Kimi Code CLI, with scores ranging from 62 to 41. Source and logo of Artificial Analysis are included at the bottom.

126
68
78
635
115,104
If you're into 3D printing, GitHub Copilot could help you out. ✨ @cassidoo shares the prompt she used to customize this GitHub-y microphone stand 🎤
18
9
1
115
28,066
💡 Bring all your related work together with projects in the GitHub Copilot app. Give Copilot a goal and it will coordinate the work. Your project can span one or more repos or focus on tasks that don't require one. Copilot can start sessions, set up recurring automations, or create artifacts; they'll show up in your project. 🗂️ Keep your sessions together to work toward one objective. Get started 👇 docs.github.com/copilot/how-…
66
32
14
323
56,448
Through internal testing, GitHub’s new Git storage architecture supported 5,000 concurrent agents working on a repo, sending 7,200 pushes per second, all while serving read traffic with consistently low latency.
Inside GitHub’s new Git storage architecture

Inside GitHub’s new Git storage architecture

Article · @github
113
105
70
1,075
93,762
What's the best way to learn? Give yourself permission to play, but time-box it. In our latest episode of the GitHub Podcast, @martinwoodward discusses how AI is changing open source, developer skills, and the joy of building things. Find it wherever you listen to podcasts or 👉 the-github-podcast.simplecas…
32
11
4
82
26,323
Here's a new way to assess your Copilot skills 💡 GitHub Copilot Verified Proficiency measures your demonstrated capability continuously as you do your work with Copilot. No exam, just data 📊 Learn more about calculating your proficiency level ⬇️ learn.github.com/proficienci…
Assess your skills with GitHub Copilot Verified Proficiency. Get evidence-based suggestions about how effectively you work with GitHub Copilot.

ALT Assess your skills with GitHub Copilot Verified Proficiency. Get evidence-based suggestions about how effectively you work with GitHub Copilot.

48
35
14
301
48,588
GitHub retweeted
David Poll (@depoll) profile picture
David Poll
@depollNov 5
Confession: I’ve scrolled past dozens of comments on a PR just to find out why I couldn’t merge it. More times than I’d like to admit. Agents have made this a lot worse. They push commits and leave review comments of their own, and all of it lands in the timeline. PR timelines have gotten dramatically noisier, and the few things you actually need to know get buried. My team is rethinking the foundations of the PR experience around that problem, and today the first piece went into public preview. The new Overview page puts merge readiness and your next step right at the top. A summary catches you up on review activity, and you can filter the conversation down to unresolved threads. It’s opt-in and rolling out through the weekend. This is a much-needed start, and there’s a lot more coming as we modernize PRs for the way software gets built now. If you try it, we’d love to hear what still sends you back to the classic view. github.blog/changelog/2026-1…
51
35
12
496
79,389
How we can secure 50% of the world's software. Traditionally, formal methods have been mostly used for safety-critical systems like operating systems, hypervisors, and databases. We're extending this to formally and empirically verify code correctness and security for full-stack web apps, one of the most common types of applications*, using the Proof-Driven Development Kit (PDD Kit). Coding agents now write code faster than anyone can review effectively. PDD Kit turns what the developer meant into a Verus specification. It then proves the AI-generated code meets that spec for every input. Researchers @alexlavaee, @MatthaiP39719, @Mappletons, and @k_cieslak break down Proof-Driven Development x Chopin in the blog here: githubnext.com/projects/pdd-… *44.4% of respondents work as full-stack (27.3%), back-end (13.5%), or front-end (3.6%) developers. Stack Overflow Developer Survey 2026, n = 25,767.
PDD Kit

PDD Kit

Building trust in the code that your agents wrote

githubnext.com
11
47
5
311
28,542
Instead of picking the model for each and every task, let Copilot Fusion route and orchestrate which model to use. ✅ Copilot Fusion balances performance and cost efficiency, picking from three execution patterns for the job: Single, Cascade, or Critique. All you need to do is choose the effort level. Try it in the GitHub Copilot app, Copilot CLI, and @code, now 30% off through November 30.
Diagram titled "Three execution patterns in Copilot Fusion," comparing three workflows: Single, where a primary model uses tools to request an answer; Cascade, where a primary model makes a first pass before a judge model either accepts its result as the answer or escalates to a repair model for a fresh-start answer; and Critique, where a primary model drafts an answer and a read-only critic either approves it as-is or requests a revision by the primary model.

ALT Diagram titled "Three execution patterns in Copilot Fusion," comparing three workflows: Single, where a primary model uses tools to request an answer; Cascade, where a primary model makes a first pass before a judge model either accepts its result as the answer or escalates to a repair model for a fresh-start answer; and Critique, where a primary model drafts an answer and a read-only critic either approves it as-is or requests a revision by the primary model.

56
39
14
360
50,642
Learn more about Copilot Fusion 💡 docs.github.com/copilot/conc…
About GitHub Copilot Fusion - GitHub Docs

About GitHub Copilot Fusion - GitHub Docs

Automatically select the right models and execution pattern for each task.

docs.github.com
1
1
14
8,982
Makerspace + Hack the Badge = two of my favourite activities at #GitHubUniverse! 🚀 Couldn't stop hacking when I got home. Now I can control the Octolamp from my conference badge over my home network. The fun doesn't end when the conference is over!
Virtual badger controlling virtual octolamp

ALT Virtual badger controlling virtual octolamp

2
4
21
9,914
Built my first mechanical keyboard! Some mistakes were made but I got it all working eventually! 😂
Image from Charlie Gerard (@devdevcharlie)
24
4
132
18,640
Only at #GitHubUniverse does @martinwoodward get an entire stage to bring plushies to life with machine learning models 🐿️
35
38
6
362
78,591
After we shipped PR limits, you asked for more control over who they apply to. Now you can apply limits only to contributors who don’t meet your account age or merged PR history thresholds. Quick demo below 👇
Nicholas C. Zakas (@slicknet) profile pictureNicholas C. Zakas
@slicknetMay 25
Replying to @moraes_c_ @github
This is a good start. I’d still like a way to say “automatically allow PRs from people who have had at least X PRs merged already.”
6
9
2
39
14,283
There's nothing like the magic of #GitHubUniverse ✨ Thanks for joining us in 2026. We can't wait to see what you build next 🚀
22
23
1
118
32,236
GitHub retweeted
GPS (@madebygps) profile picture
GPS
@madebygpsNov 2
GitHub just shipped exemption rules for pull request limits. Automatically let established contributors open PRs beyond your limit, by account age or merged PRs. Here's how to configure it.
8
8
1
49
16,415
All the new Copilot features and experiences we announced at #GitHubUniverse 🚀
October Ship Log (GitHub Universe edition)

October Ship Log (GitHub Universe edition)

Article · @github
27
19
7
141
50,253
🆕 Enterprises working with a GitHub or Microsoft account team can now get GitHub Copilot included with GitHub Enterprise for every licensed user. github.blog/changelog/2026-1…
GitHub Enterprise now includes access to GitHub Copilot - GitHub Changelog

GitHub Enterprise now includes access to GitHub Copilot - GitHub Changelog

Enterprises working with a GitHub or Microsoft account team can now get Copilot included with GitHub Enterprise for every licensed user. Previously, you had to manage two things: how many…

github.blog
1
11
1
79
16,957
users have been asking for "hide whitespace" to stick. now it does - set it once and your preference will be saved for future PR reviews github.blog/changelog/2026-1…
Pull requests: Saved whitespace preferences and improved split view - GitHub Changelog

Pull requests: Saved whitespace preferences and improved split view - GitHub Changelog

Two improvements make it easier to review pull requests in the “Files changed” page: You can save your whitespace visibility preference across pull requests New and deleted files now use…

github.blog
Jacob 'kurtextrem' Groß (@kurtextrem) profile pictureJacob 'kurtextrem' Groß
@kurtextremAug 1
Replying to @cassidoo
A setting that remembers that you turned on "Hide whitespace".
7
3
1
19
12,219
time to add the nameplate from @github universe to the book shelf
4
1
45
11,313
Mondays, right? 🥱
A cat with black and white fur is lying on a person's arm, which is on a computer desk next to a keyboard.

ALT A cat with black and white fur is lying on a person's arm, which is on a computer desk next to a keyboard.

A relaxed cat lays sprawled on a wooden desk, resting its head near an open laptop.

ALT A relaxed cat lays sprawled on a wooden desk, resting its head near an open laptop.

A black and white cat is sleeping on its side on a wooden desk.

ALT A black and white cat is sleeping on its side on a wooden desk.

A cat is sleeping on a wooden desk beside a laptop and keyboard.

ALT A cat is sleeping on a wooden desk beside a laptop and keyboard.

34
29
2
333
45,659
Load more