Cotypist

This is one of my favorite apps because it not only helps me type, but also helps me think about what I could type next. It’s like having a personal assistant when I’m stuck for words. It’s been great to see its development over the last year. I’m not sure what else could be added to it, but I’m quite sure that the developers have some tricks up their sleeve.

@daniel_a_a I'm curious why Cotypist doesn't the Apple Neural Engine at least as an option. It's much more efficient than inference on CPU/GPU, which would significantly improve concerns about battery life. It would also eliminate the obnoxious "chirping birds" sounds from coil whine as I type (M5 Max).

Local and in my own voice is the exact reason I'd turn this on. Cloud autocomplete always felt off inside Mail and Slack. Does it learn a style per app or share one across everything?

I've been using @Cotypist since one of the earliest versions, and it’s been a game changer for me. Can you believe that the sentense you just read was written 100% by @Cotypist? ;) Using tabs to accept suggestions is so much faster. I'm addicted to it! Many many many thanks to @daniel_a_a and a lot of hopes that the product is going to grow and find more users and traction. More people should know about it!

One of my favorite products!!! Can't believe I've been working without it all this time. It's on the same level as having a voice dictation app — absolutely essential. Once you start using it, you'll never go back.

The system-wide angle is what actually makes this interesting - not just autocomplete in one app but everywhere you write. I keep context-switching between Slack, email, and docs all day and having suggestions that follow you across all of them without sending anything to the cloud is a real differentiator. Curious how it handles technical jargon and product-specific terms - does it adapt just from usage patterns or is there a way to seed it with your own vocabulary?

"Autocomplete shouldn't live in one editor" is such a clean framing — the copy-into-VSCode-and-paste-back habit is painfully real. The local-only choice is what makes me trust it; I build voice/chat agents and privacy is usually the first objection. Question for you Daniel: how does "in your voice" stay accurate when it can't phone home — does it learn per-app (my Slack tone vs my email tone differ a lot), or is it one global style profile?

It's become a standard part of my tool kit. It keeps surprising me by suggesting not the most generically likely completions, but ones ones that are relevant to what it's learned about my style andmy topics. It's a genuine time saver. It also ticks the boxes for privacy, starting with the fact that its AI magic happens on your Mac.

Running a local Gemma model system-wide without choking the GPU is an awesome engineering feat. The privacy angle is a no-brainer, but honestly, just being able to tab-complete in my native flow across Slack and Mail sounds like an instant workflow upgrade.Out of curiosity, how does Cotypist handle low-level conflicts with native macOS auto-correct features?

How do you keep the first suggestion after an idle pause from eating a cold-read penalty? Do you pin a hot subset or just accept the occasional slow first token? Great work, you guys are on the right path!

Cotypist has completely transformed how I work every single day. Typing is something we all do constantly without thinking, but Daniel has turned it into a seamless, high-productivity experience. For me, it means significantly less effort and a massive boost in speed—honestly, it feels like the app flows with my rhythm and sometimes even refines my thoughts as I type.The real test of a great tool is how much you miss it when it’s not there. Once you adopt Cotypist, you simply cannot go back. In fact, whenever I have to switch over to a Windows machine or an Android phone, I instantly feel a bit irritated because the experience just feels clunky without it. It has truly become a 'day-one' essential for me. Highly recommended!

the "no cloud, no API calls" part is what makes this interesting. most AI writing tools send every keystroke to a server, which means your drafts, emails, and half-formed thoughts are all sitting in someone else's logs. running inference locally sidesteps that entirely. practical question though, how large is the model and how does it handle the tradeoff between suggestion quality and system resource usage? i'd want autocomplete that's fast enough to not interrupt my typing flow, but local models can get heavy on older machines.

Local-first is the right call for this category. The apps where autocomplete helps most are also where people write sensitive or unfinished material. The Mac-wide layer is the hard UX: suggestions useful enough to accept, quiet enough not to fight the writer.

I absolutely love it. The best part is, that it's constantly improving noticeably by itself. In addition, the developer is very responsive and adds cool features on a regular basis. Absolutely recommended.

The best productivity tools disappear into the background. Cotypist seems to fit that philosophy really well. :D