I'm curious how the Clink desktop app connects to the web app. Is it sending some kind of oauth token so you can use call Claude Code, etc, on behalf of the user?

FWIW, I created an open-source project in this space https://github.com/dyad-sh/dyad/ and it's great to see people trying different approaches :)

What you're describing as the fail-open behavior is from the Supabase platform (and not specific to any app builders): https://supabase.com/docs/guides/database/postgres/row-level...

I left Google earlier this year and created Dyad, a local, open-source AI app builder made with Electron.

The motivation: I tried one of the popular cloud-based AI app builders, but when I pulled down the app to run locally and debug in Cursor, it just didn’t work. So I created Dyad, an app builder that runs fully on your computer, making it easy to switch between Dyad and coding tools like Cursor or Claude Code.

Source code: https://github.com/dyad-sh/dyad/

Download (free, no sign-up): https://www.dyad.sh/

I've gotten questions about how it works under the hood so I wrote an architecture doc explaining how it does tool calling using XML tags, etc: https://github.com/dyad-sh/dyad/blob/main/docs/architecture....

Let me know what you think and happy to answer questions about building an Electron app, etc!

Comments URL: https://news.ycombinator.com/item?id=45296227

Points: 28

# Comments: 19

Just wanted to share a local vibe coding tool that I created. You can download it here (free, no sign-up): https://dyad.sh/

It's open-source and on GitHub: https://github.com/dyad-sh/dyad

If you've used one of the popular vibe coding tools like lovable, v0 and bolt, but want something more flexible and without the lock-in, I think you'll like dyad.

Here's a few things that makes it different:

- Runs locally, making it fast and frictionless. Because your code lives locally, you can easily switch back and forth between Dyad and your IDE like Cursor, etc.

- Run local models using the Ollama and LM Studio integration (https://www.dyad.sh/docs/guides/ai-models/local-models), which lets you build with your favorite local LLMs.

- Free and bring-your-own API key. This means you can use your free Gemini API key and get 500 free messages/day with Gemini Flash 2.5!

Note: Dyad isn't an IDE (and not another VS code fork :) and instead is focused on people, esp. non-engineers, who want an all-in-one tool to build+preview web apps in a simple desktop UI.

If you're interested in my experience building an Electron app (e.g. the pain of code signing, cross-platform issues, weird Node.js quirks), please let me know, I'm thinking about writing a technical blog post.

I’d love any feedback about the project. Thanks!

Comments URL: https://news.ycombinator.com/item?id=44138905

Points: 4

# Comments: 0

The only downside from my point of view is the large installer size for Electron apps, but it hasn't been a big issue for our users (because they will need to download quite a bit of other stuff like npm packages to actually build apps with dyad)

Your message wasn't delivered to support@relace.ai because the address couldn't be found, or is unable to receive mail.

btw, I'm interested in trying out relace for my AI app generator tool: http://dyad.sh/

I'm excited to share a free, local, open-source AI app builder that I created. You can see what it looks like and download it here: https://dyad.sh/

It's open-source and on GitHub: https://github.com/dyad-sh/dyad

If you've used one of the popular AI app builders like lovable, v0 and bolt, but want something more flexible and without the lock-in, I think you'll like dyad.

Here's a few things that makes it different:

- Runs locally - Dyad runs entirely on your computer, making it fast and frictionless. Because your code lives locally, you can easily switch back and forth between Dyad and your IDE like Cursor, etc.

- Run local models - I've just added Ollama integration (https://www.dyad.sh/docs/guides/ai-models/local-models), which lets you build with your favorite local LLMs.

- Free - Dyad is free and bring-your-own API key. This means you can use your free Gemini API key and get 25 free messages/day with Gemini Pro 2.5!

Note: dyad isn't an IDE (and not another VS code fork :) and instead is focused on people, esp. non-coders, who want an all-in-one tool to build+preview web apps in a simple intuitive desktop UI.

I’d love any feedback. Thanks!

Comments URL: https://news.ycombinator.com/item?id=43920222

Points: 2

# Comments: 0

I definitely want to support users who want to use cloud inference or local inference because you do need a pretty beefy machine to run the top open source models.

Right now Dyad supports React (vite), but i'm working on supporting more frameworks in the future! (other languages is probably further off)

I think practically, the nice part with Dyad is that all the code is on your computer, so if you want to switch back and forth with Cursor/VS Code, it's seamless.

I'm excited to share a free, local, open-source AI app builder that I created. You can see what it looks like and download it here: https://dyad.sh/

It's open-source and on GitHub: https://github.com/dyad-sh/dyad

If you've used one of the popular AI app builders like v0, lovable and bolt, but want something more flexible and without the lock-in, I think you'll like dyad.

note: dyad isn't an IDE (and not another VS code fork :) and instead is focused on people, esp. non-coders, who want an all-in-one tool to build+preview web apps in a simple intuitive desktop UI.

Here's a few things that makes it different:

- Runs locally - Dyad runs entirely on your computer, making it fast and frictionless. Because your code lives locally, you can easily switch back and forth between Dyad and your IDE like Cursor, etc.

- Run local models - I've just added Ollama integration (https://www.dyad.sh/docs/guides/ai-models/local-models), which lets you build with your favorite local LLMs.

- Free - Dyad is free and bring-your-own API key. This means you can use your free Gemini API key and get 25 free messages/day with Gemini Pro 2.5!

I’d love any feedback. Thanks!

Comments URL: https://news.ycombinator.com/item?id=43848489

Points: 6

# Comments: 5

Basically it's running a chat UI locally on a Git repo and you can reference files like "#foo.py" and then if you want to edit a file, you hit "Apply code" for a markdown code block and then it shows you a code diff so you can review the changes before actually updating the files. I've found this makes it much easier to curb stray edits and keep the LLM edits focused on what you actually care about.