I love Markdown but collaboration is a pain. Whenever I work on a document with others, I end up switching to Google Docs, then exporting to Markdown, copying it into the right repository, and committing it locally.

Why Google docs? .md misses annotations, discsusions, Richttext that everybody (also non techies) know how to work with...

Thats why I build colibri, a Google Docs-like experience for any GitHub Markdown files. Accessible and usable for everyone, with or without a GitHub account.

Just replace the g of github.com with tune "tuneithub.com".

https://github.com/Legit-Control/get-colibri -> https://tuneithub.com/Legit-Control/get-colibri

and you can start to collaborate - press open PR - to get your changes merged back in.

Feedback, I’d love: - How do you currently collaborate on .md files? - If you could add one feature to a Markdown editor like this, what would it be?

Limitations: - Works only for public GitHub repositories for now - Support for private repos coming soon

Comments URL: https://news.ycombinator.com/item?id=47221706

Points: 3

# Comments: 2

Some weeks ago we launched this:

https://github.com/Legit-Control/monorepo/tree/main/examples...

The idea was simple: keep AI prompts, intents, and conversations alongside your code and commits — basically treating AI interaction as first-class development artifacts. everything just plain Git

We struggled to get momentum. Things happen.

Now, less than 24 hours ago, Thomas announced Entire.io:

“Entire CLI hooks into your git workflow to capture AI agent sessions on every push. Sessions are indexed alongside commits, a searchable record of how code was written.”

That’s… very, very close to what we tried to build.

Honestly, I love the vision and think this will matter a lot in the AI age. It’s validating to see someone with that reach betting big on it.

Best of luck to Thomas and the team behind Entire.

What really stands out is that everything lives in Git. Designs sit next to the code they relate to, with versioning, history, and collaboration handled by tools developers already use. This avoids a lot of the friction Figma had for years, where design history, branching, and reviews were either missing or awkwardly bolted on later.

If Sketch -> Figma was about moving design to the browser, Pencil feels like the next step: treating design as a first-class, versioned artifact in the developer workflow.

Curious how designers and engineers here think about Git-based design workflows, and where this approach might fall short compared to Figma.

Comments URL: https://news.ycombinator.com/item?id=46732706

Points: 3

# Comments: 1

I was surprised this wasn’t already supported. Does anyone know what made this difficult, or why it took this long to ship?

On expanding beyond Claude: there’s no concrete plan right now since we built this around Claude, but we’re very open to it. If you have a preferred CLI (e.g., Codex, OpenCode, or something else), feel free to open an issue in the repo. Or just describe your use case here and I will do it :)

Regarding branches: the tool does not pollute your working branch. Each session lives on a separate “session” branch that contains all prompts and operations. Your normal working branch stays clean.

When you end a session, you’re prompted to either:

merge the code changes into your working branch, or

discard them.

If the video or README didn’t make this clear enough, I’d appreciate the feedback I’ll update the docs accordingly.

This CLI tool preserves that context in Git, making Claude code conversations transparent, continuable later, stored alongside code, and shareable with your team via a Git host.

You can test it here: https://github.com/Legit-Control/monorepo/tree/main/examples...

Curious how you handle shareability and persistence of AI conversations, or any ideas for making conversation history more useful and easily shareable.

Comments URL: https://news.ycombinator.com/item?id=46692885

Points: 4

# Comments: 2

And even though it doesn’t actually get full sudo access, giving an LLM permission to edit files without being able to track exactly what it’s doing still feels risky.

For example, for writing a blog post, if I only want to write down notes, meeting notes, etc.

My last post was about what I’m working on. We had just launched, and I was excited to hear some feedback.

Full of anticipation, I used the prefix `Launch HN` in the title and clicked Submit.

After rereading the post, I noticed the title was wrong. It said `Show HN: ... `instead of `Launch HN: ....`

I assumed I had made a mistake, so I edited the post and changed the title back to `Launch HN`.

I pressed Submit again—only for it to revert to Show HN.

After repeating this a few times, deleting the post, and submitting it again, I finally realized it wasn’t me.

It was HN.

I’m glad I learned something new about Hacker News and the etiquette today. I’ll keep going, and eventually I’ll be able to post something that someone else wants to see.

For now, I’ll just take a quick look at what’s new on HN and call it a day.

Comments URL: https://news.ycombinator.com/item?id=46548597

Points: 1

# Comments: 5

We are building Legit, an open source version control and collaboration layer for AI agents and AI native applications.

You can find the repo here https://github.com/Legit-Control/monorepo and the website here https://legitcontrol.com

Over the last years, we worked on multiple developer tools and AI driven products. As soon as we started letting agents modify real files and business critical data, one problem kept showing up. We could not reliably answer what changed, why it changed, or how to safely undo it.

Today, most AI tools either run without real guardrails or store their state in proprietary databases that are hard to inspect, audit, or migrate. Once agents start collaborating on shared data, you are often just crossing your fingers and hoping nothing goes wrong.

We noticed something interesting. Developers do not have this problem when collaborating on code, and agent like workflows took off there first. The reason is relatively simple. Git already solves coordination, history, review, and rollback.

That insight led us to build Legit. We bring Git style versioning and collaboration to AI applications and to most file formats. Every change an agent makes is tracked. Every action is inspectable, reviewable, and reversible. No hidden state. No black box history.

Legit works as a lightweight SDK that AI apps can embed anywhere the filesystem works. It handles versioning, Sync, rollback, and access control for agens. Everything lives in a repository that you can host yourself or on any Git hosting provider you already trust.

We believe the right way to scale AI collaboration is not to hide what agents do, but to let developers and users see, review, and control every change. Legit is our attempt to bring the discipline, visibility, and safety of modern developer workflows to write enabled AI applications.

Give it a spin: https://github.com/Legit-Control/monorepo and let us know your feedback, criticism, and thoughts.

Comments URL: https://news.ycombinator.com/item?id=46548475

Points: 9

# Comments: 0

As @_mig5 mentioned, having version control with history tracking would be amazing — and an agent mode could be really cool too.