Cotypist - Local AI Autocomplete in your voice, anywhere on your Mac
by•
Cotypist is smart autocomplete for the Mac apps you already write in: Mail, Slack, Notes, docs, even AI prompts. Press Tab when a suggestion fits, or keep typing and watch it update in real time. Runs locally on your Mac. No cloud, no API calls.
Replies
Changed the way I type. Forever.
Cotypist
❤️
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!
Cotypist
@mraza696 Thank you for sharing your experience! That is exactly the kind of experience I have been aiming for. Glad to hear it’s landing!
Since it operates globally across all text inputs, how does Cotypist handle low-level conflicts with native macOS auto-correct features or spelling engines in apps like Obsidian or Mail? Do you actively filter out system suggestions to prevent visual overlapping, or does the tab-completion mechanism override them? Congrats on shipping a very much needed product!
Cotypist
@konstant_gk Good question! Cotypist automatically offers to disable macOS' built-in inline text completions when you install it. I similarly recommend disabling built-in autocompletion features in e.g. Gmail and Google Docs; Cotypist's own suggestions should generally be more useful, anyway.
Swipe Files
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.
@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).
Cotypist
@coreyward Up until recently, the Neural Engine was not available for high-complexity tasks such as running LLMs, let alone quantized versions of them. It remains to be seen how much that has changed with projects like anellm and Apple’s new Core AI frameworks. However, I am still doubtful that the Neural Engine would provide a low enough latency to be useful for generating autocomplete suggestions in real time. In addition, the Neural Engine would also draw power in a modulated fashion, which could leave it susceptible to coil whine as well.
@daniel_a_a I think you're underestimating the Neural Engine on even M3 Max chips. From experience, it's shocking how capable it is. I've never experience coil whine when using it on my machine, even when stress testing it (I was curious how much wattage it caps at), but it's possible other machines are different.
Edit to link this: https://huggingface.co/google/gemma-4-E2B-it/discussions/14
You won't believe it, but recently I was looking for such a tool. I couldn't find something that would really work - just an autocomplete, without any other unnecessary functionality. And also that it would work quickly, and wouldn't eat up half of the computer's memory. It seems that this is what is needed. I will definitely try it and give my feedback.
I also have questions about this:
- What is the weight of the model that handles the autocomplete?
- Will this work in any input or text field? Or only in specific applications?
- What is the context for autocomplete? Is it the text that is previously entered into the text field, or does the application scan the entire page?
- After the trial period ends, if I like everything, can I buy the app permanently with a single payment? Is there or is there any plan to do so?
Cotypist
@oleg_tsizdyn Hi Oleg, thank you for the comment! This is the person I built Cotypist for: someone who wants autocomplete that just works, stays out of the way, and does this as efficiently as possible. Looking forward to your feedback. To your questions:
What model handles the autocomplete, and how heavy is it?
The default is Google's Gemma 4 E2B, running entirely on your Mac. The model file is a few gigabytes on disk, but only about 1 GB of it needs to be in active memory while it's generating. Even though it's a multi-billion-parameter model, Cotypist doesn't keep all of its weights resident at once: part of them are streamed in from disk only as they're needed, so they never have to sit in GPU memory. That's a big reason it punches above its weight, you get close to the quality of a much larger model for the footprint of a small one. On stronger Macs you get the larger E4B model (around 2.5 GB in memory) for even better suggestions.
Does it work in any field, or only specific apps?
It's system-wide. It works in most native macOS text fields and many web and Electron ones too: Mail, Slack, Notes, the major browsers, document editors, even AI prompt boxes. It isn't tied to a fixed list of apps. A handful of apps don't expose the information Cotypist needs to place a suggestion correctly, and those are listed on the compatibility page, but the large majority of where you write is covered. One notable exception is Ghostty; I submitted PRs to improve their support for Cotypist, but there hasn't been much progress on that front.
What context does it use?
Mainly what's visible on your screen as well as some information, plus some additional information. You can also provide custom instructions to tailor the suggestions to your writing style. All of that is processed on your Mac, and nothing you type is ever uploaded anywhere.
After the trial, can I buy it permanently with one payment?
Cotypist is subscription-based, and I don't offer a one-time purchase. The short reason is that the subscription is what keeps it in active development and support, faster completions, bug fixes, more app coverage, rather than a single payment that has to fund years of future work. That said, you're not forced to subscribe: after the 30-day Pro trial there's a capable free tier, so if it fits how you write, you can keep using it without paying anything.
Thanks again for giving it a try, and please do send your feedback once you've lived with it for a bit.
Running locally with no cloud dependency is a huge selling point. Privacy-first AI feels refreshing these days. Congrats Daniel.
Cotypist
@himani_sah1 Indeed! The privacy aspect is definitely important. Plus, with Cotypist running locally on your Mac, your voice isn't following the writing style that the big AI labs are pushing.
GrowMeOrganic
Love the origin story. Copying text into VS Code for autocomplete is exactly the kind of workflow hack builders create.
Cotypist
@iamanantgupta Indeed! I also love the macOS platform for its expandability and "hackability"; tools like Cotypist would simply not be possible in this form on,say, iOS.
The fact that Neuralink users adopted this is wild. Congrats on building something genuinely useful 😊
Cotypist
@divya_kothari1 I know, right!? I'm really happy how Cotypist not only makes able-bodied users more productive, but also can be a life-changing tool for people with disabilities, leveling the playing field. Besides the two Neuralink users, I have also heard from a quadriplegic journalist who can now do his work on a more equal footing.
Smart autocomplete everywhere feels more natural than opening a separate AI tool for every writing task. Well done, Daniel!!
Cotypist
@zerotox Exactly! I want Cotypist to eliminate friction everywhere, rather than adding it by introducing additional steps into your workflow.