back
76 comments
Who would have thought that git worktree is the technology of the year 2026?
Yeah, when you had multiple agents working on the same machine, branch isolation was no longer sufficient.

A repository folder can only be on one branch at a time.

A worktree is basically equivalent to a cp -R + git branch, which allows this new workflow to occur.

I loved this particular historical insight as to why `git worktree` was added in 2015:

Before worktrees, kernel devs faced a major inconvenience when switching contexts, e.g., stopping feature work to fix an urgent bug on a release branch.

Running git stash and switching branches alters timestamps on thousands of files.

This forces `make` to perform a full re-compile, which can take up to an hour on large kernels.

And the team behind opencode is working on an alternative https://github.com/anomalyco/rift
I still don't understand how people use git worktrees with Docker. You need a full database and etc. For me it's simpler to have multiple checkouts.
I use a skill that basically boils down to 'keep track of ongoing work in a json file, create a new numbered clone for each separate thread of work, delete when done'. Worktrees are too opaque and not entirely isolated for my liking.
How small are people’s projects if they find worktrees useful? I use them for hobby stuff, but $DAYJOB is a different story because of testing
I set up multiple work trees in one vscode workspace last year and wrote in the agents.md how to merge branches - but I spend about a third of the time helping agents integrate and merge. I remember wishing the tooling would catch up
I used to create multiple local worktrees and mount the sub directories using Docker. This approach had significant limitations because many paths in the agent and .git files were hard-coded.
I can barely keep up with one single thread and branch, go figure.
i have some fun experiments i'm doing with full virtualization middle ware of all sys calls for agents tools/shell commands/io, still far from daily driver, but allows me to do a very rich overlay / virtual file system tom foolery in place
Worktrees don’t support git submodules and it’s killing me in my monorepo
I have moved from my own awkward scripts to lazyworktree TUI and I loved it
best tool yet!
Unrelated to the feature itself, but remember a few months ago when someone posted Github's beta feature for stacked PRs, and a ton of people slammed them for releasing a seemingly vibe-coded site? To quote Mitchell Hashimoto, "One of the most requested GitHub features in years and the website looks like it was designed by someone 9 years into a 2 year community college program."[1]

When opening the posted link, my first thought was "imagine if the stacked PRs site had the same amount of effort put into it as the Github Copilot App site". They clearly have other preview features on this site already, so maybe I'm just confused on why stacked PRs got some b-grade announcement site. The obvious answer is "copilot", but I'm still curious.

[1] https://x.com/mitchellh/status/2043788123008868600

Target market for stacked PRs are ICs who don't have much decision making power and let's be real do not care too much about the look and feel of a "launch site" for the feature. It's also something few if anyone is making a purchasing decision over.

Target market for copilot includes people with actual purchasing power and also many new users where this is an actual make or break feature. So this is worth the investment into design while stacked PRs is questionable. I actually question why they bothered with anything more than a blog post at all for stacked PRs (looking at the post it doesn't seem like too too much more than a blog post though).

Looks good, but after pricing change I have already used 26% this month with very light usage.

Last month I used Copilot heavily, much much more than I usually do, but did not manage to use more than 58%.

> Looks good, but after pricing change I have already used 26% this month with very light usage.

Forced me to switch to OpenCode Go (not Zen), which isn't quite as nice as Copilot Chat deeply integrated into VSCode / Intelli but the models (DeepSeek v4 Pro, GLM 5.1, & Qwen 3.7 Max) are able replacements for Claude Sonnet 4.x / GPT 5.x while being way cheaper (especially DeepSeek).

We had settled on Copilot's Sonnet 4.6 which incidentally is one of the models that got shanked in the pricing update.

Easily 7x or more for what amounts to self–serving work. At this point, we might just switch to 4.8 Opus.

Honestly, I would not spend a cent of my own money on a model that won't run on my PC, but still I feel like this is the end of this Microsoft product I hadn't used a month ago. We'll see if our sugar daddies keep funding it.

Use less effort and thus tokens.

I swear I did few tests and it's rare you need more than medium on mundane job work.

1 day and 26% of usage? wildly inflated!
That looks pretty close in shape to the early Ace project Maggie Appleton demonstrated last month.

Edit: This short talk – https://maggieappleton.com/zero-alignment

I was thinking of the Codex app.

Particularly the left sidebar and conversation view look near identically structured.

Cool talk, thanks for sharing. What happened to the project? I see no mention to it on the Github Next website and even internal links to it like on page [1] go to a 404 - https://githubnext.com/projects/ace/

[1] https://githubnext.com/posts/micro-ace-traffic-lights/

I rather like Ace better because the key problem right now is teams not working together and shipping the wrong things. When AI can generate the code, then it feels like product should be bringing the functional vocabulary and grammar while the engineering team provides the technical grammar to build the right thing.

This app is just another "let me talk to product, copy their convo, go off and build this in isolation with an agent" which I think is directionally wrong.

The "rooms" or "streams" should be multi-player instead of product looking at it at the end saying "no, go fix that" and dev copies text from one source and pastes into another.

ace appears to be an experiment to make a multi-user experience on top of the codex UI.

the copilot app looks more like just a straight clone of the codex UI (and the new antigravity UI, which is also a straight clone of the codex UI)

Oh nice! I guess they're back to features after finishing tackling their availability issues [1].

[1]: https://github.blog/news-insights/company-news/an-update-on-...

I noticed the availability issues dropped off really fast in line with the pricing hike!
It is nice.

But!

The reason these tools exist is not because of non-professional developers, but quite the opposite.

A lot more professionals are now working on more projects simultaneously- something that was not practical just a year ago.

Though, while this is nice, considering that all of the action is happening on the same device, I am worried this is going to increase supply chain risks. Before, a developer would work on clearly designated projects for practical reasons. Now, the same developer can work across many projects that are quite different - for example, the marketing site and the backend - and because of an obscure and unimportant component on the marketing site, there can be an impact on backend systems.

I wrote more about this here: https://chatbotkit.com/reflections/everyone-is-a-vip-now

If I'm interpreting this correctly, GitHub will use their existing actions infrastructure to run versions of the code in isolated worktrees. I think this could be a very beneficial process.

What I've done on my end is created a project where I have a remote Linux workstation. I can create multiple worktrees for each repo in that workstation, and then my agent can push PRs to GitHub and use the actions infrastructure to see if the integration tests that it writes for itself are successful without needing to run those integration tests on the local environment. It's expensive in terms of runner hours, but the automaticity of it is incredible.

As a side note, has anyone else noticed that GitHub have leaked what looks like a sequential customer number on their Billing - Usage page?

Go here and you’ll be redirected with a query string including a customer parameter. That looks like trouble.

https://github.com/settings/billing/usage

How is this different than the separate Agents app shipping with VS Code?

Other than fewer features.

More evidence that GitHub is chasing features over stability of their platform.
It's weird. I still remember 2008, when GitHub's claim to fame was that it was "the easiest (and prettiest) way to participate in the collaborative development of software."

Now they want to end that collaboration, and turn it into automation. Many C-suite executives right now are smiling bigly. Meanwhile, we're leading the exodus. Turns out, we still want the easiest and prettiest way to participate in the collaborative development of software, and GitHub ain't it!

I know it has the same functionality, but it also looks like the Codex app which looks like Cursor Agents! Are they sharing some VS Code primitive here?
looks like google antigravity 2.0, a standalone app instead of a vscode plugin.
VSCode just released their Agents Mode, this is pretty much the same thing. Surprised they decided to do a split like this all of a sudden.
It's kind of interesting that everyone is going for the desktop app format now.

These desktop agentic coding tools are a large UX step up from the CLIs, but I still think the future is going to be remote development as the coding agents start running for hours at a time. Building a desktop app seems short-sighted as it would just lock them out of the remote option completely.

copilot had such a lead when this whole ai coding thing started. what happened?
So, it's not open source?
they should have spent this engineering time on stability.
Let me guess: some ElectronJS crap instead of a native UI?
Windows App, Copilot, GitHub Copilot…

I predict next “Windows Copilot App” (not to be confused with any of the others), Microsoft’s AI that controls your computer (like OpenAI Operator and Claude Computer)

Here is the kind of crap they are building instead of focusing on stabilizing their core business features.

And after they will accuse the growth and all to be responsible for their stability issues...

"This page is slowing down firefox"