BoltAI

BoltAI now supports Codex 5.3 model via the Codex CLI integration. You can use the native Web Search tool, customize your System Prompt and use your own Agent settings. Update when you have a chance ✌️

Big thanks to @Bolt__AI for supporting this week newsletter! 🙏 One native app, 100+ AI models on Mac, iOS, and Android. Fast, keyboard-driven, no Electron. 25% off for a limited time with code `FATBOBMAN25`. l.fatbobman.com/sb-boltai

I've had BoltAI on my Mac since the v1 days, but upgrading to v2 last week reminded me why I made the switch. Before Bolt, I was stuck with the ChatGPT desktop app (buggy, missing web features), the Claude app (locked to one provider), and alternatives like MindMac that crashed constantly. There are GitHub threads of people saying it crashes every few messages. What sold me originally was the global shortcut. I hit one key combination and BoltAI appears over whatever I'm working on. No context switching, no tab hunting. But v2 brings even more to the table. The instant workflows are genuinely useful. I set up custom shortcuts for specific tasks, and the inline editing means I can rewrite text or fix code right where I'm typing. Everything is customisable too, from my prompt library to plugins that extend what the AI can do. I can switch between models instantly depending on what I need, using proprietary models or any open source model with the provider of my choice. When I'm working with sensitive client data, I flip to a local model via Ollama and keep everything on my machine. That privacy-first approach matters in some cases. The app isn't perfect. I'd love more detailed cost tracking for API usage (they've added basic usage metrics recently, but more granularity would help). These are nits though. The developer ships regular updates, v2 is noticeably snappier with modern Apple APIs, and it respects your privacy by default. One-time purchase, no subscription. For Mac power users who need AI properly integrated into their workflow, BoltAI v2 is the best option I've found.

@sundarpichai BoltAI now supports Gemini 3.1 Pro ⚡

Gemini 3.1 Pro is here. Hitting 77.1% on ARC-AGI-2, it’s a step forward in core reasoning (more than 2x 3 Pro). With a more capable baseline, it’s great for super complex tasks like visualizing difficult concepts, synthesizing data into a single view, or bringing creative projects to life. We’re shipping 3.1 Pro across our consumer and developer products to bring this underlying leap in intelligence to your everyday applications right away. Rolling out now to: - Developers in preview via the Gemini API in @GoogleAIStudio - Enterprises in Vertex AI and Gemini Enterprise - Everyone through the @Geminiapp and @NotebookLM

@Google BoltAI now supports Gemini 3.1 Pro ⚡

Today, we’re releasing Gemini 3.1 Pro. It’s the same core intelligence that powers Gemini 3 Deep Think, now scaled for your practical applications. It’s a smarter model for your most complex tasks. See 3.1 Pro in action 🧵↓

@openrouter @openclaw @kilocode Very cool 🙌

You can now add your app or agent to openrouter.ai/works-with-ope… See @openclaw, @kilocode, and dozens of other apps that let you use your OpenRouter credits with 350+ models

@openclaw Gotta use my old android phone to run clawdbot 🦞

PSA: You do NOT need to buy a Mac Mini to run Clawdbot 🦞 That dusty laptop in your closet? Works. Your gaming PC you feel guilty about? Works. A $5/mo VPS? Works. A Raspberry Pi held together with hope? Probably works. The M4 Mac Mini is gorgeous but Clawdbot runs on basically anything with Node. Stop giving Apple your money (unless you want to, I'm not your mom). 👉 #do-i-have-to-buy-a-mac-mini-to-install-this" target="_blank" rel="nofollow noopener">docs.clawd.bot/help/faq#do-i-…

@tkwoncpa @daniel_nguyen @thsottiaux Submit where?

@daniel_nguyen @thsottiaux @Bolt__AI Submit a pr?

Pi! It's elegant and delightful for tinkerers. And it has just joined the list of open agents that supports logging in with your ChatGPT account and use the same usage you get within Codex. Who's next? 👀 buildwithpi.ai

@openrouter Submitted 🫶

@Bolt__AI PRs are open!

Apps that work with OpenRouter, now on GitHub: github.com/OpenRouterTeam…

PSA: We haven’t launched any crypto projects. If you see claims saying otherwise, they’re not from us. Please be careful.

⚡️⚡️⚡️

@GoogleAI Thanks for mentioning us ⚡️

⚡️⚡️⚡️

@Google Thanks for mentioning us ⚡️

⚡⚡⚡

@JoannaStern Shameless plug: give boltai.com a try!

Anyone else having big issues with ChatGPT Mac app lately? Things don't copy, it's slow to load, sometimes it just jumps to another chat. Just me?

@taglia Ah I see. Will fix soon!

@Bolt__AI I tried with this file, but it was ignored.

@Bolt__AI Hi, are you planning to support StreamableHTTP MCP servers? I haven't seen it mentioned in the roadmap.

Big thanks to @Bolt__AI for supporting my newsletter! 🙏 BoltAI brings Claude, GPT, Gemini and Local LLMs directly into your workflow. ⚡️ Analyze screenshots, fix bugs, and refactor code instantly. 100% Native. 🎁 Exclusive 51% OFF(Ends Soon): BFCM25👇 l.fatbobman.com/sb-boltai

@onsteps I will do. Sorry it was a rush launch as I tried to make it before Black Friday. More guide and help docs coming soon.

@Bolt__AI It would be great to have some video tutorials as well. There are so many settings, it's a bit unclear how to replicate things like Inline Workflow, for example. 1.0 was somehow simpler. In any case, thanks for the release and for cyber monday deal 🤗

BoltAI v2 is finally here ✨ I've spent the last 6 months rebuilding it from scratch: new codebase, new design, new everything. It’s faster & much better than v1. A few details, then demos of the key features 👇

@tatarin @daniel_nguyenx Sometimes it loses the Accessibility permissions. You may need to enable it again. I’ll write a guide soon. Can you file a bug report at feedback.boltai.com Thank you

@daniel_nguyenx @daniel_nguyenx @Bolt__AI Also here is another problem(((

I made $0 from BoltAI v2 so far 😁 A few months ago, I decided to rebuild the product. It was at the stage where it’s hard to make any meaningful change. It would be impossible to fulfill my product vision with the old codebase. New users were churning because of performance issues. I figured it might actually be faster to build a new app with a stronger foundation, and then port features from v1 to v2. I initially didn’t want to rewrite. That’s usually not a good decision for a product that is already working. (Read “Things You Should Never Do, Part I” by Joel Spolsky) I attempted to refactor smaller parts but it didn’t work. It just made the codebase more complex, and even harder to maintain. (skill issue, yeah) I made a bet that a rewrite would not take a lot of time, and once it’s ready I could win back those customers. It ended up taking 3+ months. Fast forward to today, the new app is ready. It probably has 95% feature parity with v1 now. It’s faster, smarter and looks better. Both existing customers and new users love it. But none of that matters if it doesn’t improve growth. I didn’t enable monetization until now. November is going to be the moment of truth. It’s either a genius decision or the dumbest one. #buildinpublic folks, follow along 😁