BoltAI

⚡️ All AI models in one app. 🐛 Bug & Feature Requests 📱Mobile (beta) by @daniel_nguyenx

[Daniel Nguyen @daniel_nguyenx]

I think Expo is a good option for building desktop apps now. I just ported both @Bolt__AI & @pdfpals to Windows and it works very well.

It started as a proof of concept (PoC), but the end result surpassed my expectations. Not only does the app work correctly, it uses native UI components (Mica & Fluent Design System) and it's fast.

With VMPal and its agent mode, I was able to do most of the work with Claude Opus on my Mac. Without the annoying permission approval on the Mac, opus can autonomously drive all the implementations:

- It analyzes and takes screenshots of the Mac app, then generates a full plan for the port

- It then downloads the Rust toolchain to compile the native UI components for Windows. It basically built a native Markdown renderer for Windows with syntax highlighting (tree-sitter) and math expressions (RaTex).

- It even found a couple of bugs in the react-native-windows package, generated a small C#/WinUI app to verify it.

- I setup an SSH server on my Dell laptop for claude to smoke test the release build. It also ran all kinds of benchmarks there to make sure the app runs smoothly on a low-end PC.

@TablePlus half-joked that I could just one-shot the port with VMPal + Claude. It did require more effort than that and I didn't choose WPF but still, I spent most of the time on QA-ing.

This is honestly incredible.

[BoltAI @Bolt__AI]

@GeminiApp https://t.co/zEYVa7Am5L

[BoltAI @Bolt__AI]

Gemini 4 Argon is here.

Refresh your model list to use it in BoltAI ✌️

[BoltAI @Bolt__AI]

@Google https://t.co/zEYVa7Am5L

[BoltAI @Bolt__AI]

Gemini 4 Argon is here.

Refresh your model list to use it in BoltAI ✌️

[BoltAI @Bolt__AI]

@sundarpichai https://t.co/zEYVa7Am5L

[BoltAI @Bolt__AI]

Gemini 4 Argon is here.

Refresh your model list to use it in BoltAI ✌️

[BoltAI @Bolt__AI]

Gemini 4 Argon is here.

Refresh your model list to use it in BoltAI ✌️

[Sundar Pichai @sundarpichai]

Gemini 4 Argon is here.

It’s available globally today for developers and enterprises in the paid tier of the Gemini API and the Gemini platform, for Ultra subscribers in Google Antigravity, and Ultra and Pro subscribers in the Gemini app and Search.

Hope you all enjoy it!

[BoltAI @Bolt__AI]

It took a while, but BoltAI is now half-bounce fast. The app is ready in 0.48s ⚡

[BoltAI @Bolt__AI]

Claude Opus 5.5 is here!

[Claude @claudeai]

Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family.

It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.

[BoltAI @Bolt__AI]

@adamlyttleapps I shared your hacking story with my wife and she loved it. You’re a hero. Keep up the good work Adam!

[BoltAI @Bolt__AI]

@CleanShot Congrats on the launch. It looks amazing!

[BoltAI @Bolt__AI]

@marclou Great works, Marc. Happy birthday ShipFast!

[BoltAI @Bolt__AI]

Fable 5.1 is here! Refresh your model list in BoltAI to use it ⚡️

[Claude @claudeai]

We’re introducing Claude Fable 5.1 and Claude Mythos 5.1.

They're the world’s most advanced models for coding and knowledge work.

[BoltAI @Bolt__AI]

Correction: https://t.co/RIgA6TXuNC

[Daniel Nguyen @daniel_nguyenx]

Correction: the QT video was not half-bounce. I was too excited and launched the debug build.

This one is faster. It misses the peak just a little, but that was because of the screen recording software.

[BoltAI @Bolt__AI]

Half-bounce club ⚡

[Mitchell Hashimoto @mitchellh]

I love how many people are attaching to the "half-bounch" startup time metric. I used to do paid macOS dev ~20 years ago and most macOS devs I knew then used the bounce metric! Back then multiple bounces was the norm due to HDDs. One bounce really wasn't possible until SSDs. We've lost this obsession and its time to bring it back.

[BoltAI @Bolt__AI]

Congratulations! Check out https://t.co/FAluvR0skv if you need a native OpenRouter client for mac ✌️

[OpenRouter @OpenRouter]

OpenRouter is joining Stripe.

We started OpenRouter with a simple mission: intelligence should be multi-model. Today, we are the largest AI marketplace & gateway, processing 10T+ tokens daily on 400+ models.

Joining @Stripe gives us the opportunity to accelerate that mission.

[BoltAI @Bolt__AI]

Congratulations OpenRouter team! Check out https://t.co/eOjFqLTEV2 if you need a native OpenRouter client for mac ✌️

[Daniel Nguyen @daniel_nguyenx]

I'm happy to sponsor Indie App Sales again. Find BoltAI on https://t.co/v0dnfEegHj for 30% discount✌️

[BoltAI @Bolt__AI]

@claudeai https://t.co/daTKdI211f

[BoltAI @Bolt__AI]

Opus 5 is available on BoltAI. Refresh the model list to see it ✌️

[BoltAI @Bolt__AI]

Opus 5 is available on BoltAI. Refresh the model list to see it ✌️

[Claude @claudeai]

Introducing Claude Opus 5.

It's a thoughtful and proactive model that comes close to the frontier intelligence of Fable 5 at half the price.

[BoltAI @Bolt__AI]

@2Hand2Leg Wrong Bolt

[BoltAI @Bolt__AI]

I listened to your feedback and redesigned the Model Selection popover.

✅ One list for all providers & models
✅ Fast fuzzy search
✅ Add models to favorite for quick access
✅ Keyboard-friendly

Release soon.