Replies (57)
Awesome! 2026 is coming in great. 👏🏻
We've got one more big release for you in 2025.
@Maple AI can hang with ChatGPT and Claude when it comes to reasoning. And Maple already beats them for security.
What are you waiting for? Grab you some Maple!
View quoted note →Will there be more options for sharing existing content with the AI? To be able to share a folder containing the codebase for a project would make a big difference!
Use privacy-respecting tools.
View quoted note →Can we pay per prompt with bitcoin?
yall rock. thanks!! 💪
Are you guys aware of the background refresh bug on IOS?
Black screens every time I open it after using it prior. Have to force close and re open.
Maple’s newest thinking model outperforms GPT-5, Grok 4, and Claude Sonnet 4.5.
Open models are here to compete!
View quoted note →Not in the app. You can buy tokens to use with the Maple Proxy.
@PayPerQ offers paying per prompt with bitcoin.
Are you running the latest? We fixed some issues recently with that.
Just checked. Up to date, opened app and same issue.
Can I use MapleAI for the most recent information? No cut-off dates etc.?
When can I manipulate images that I upload? Thanks.
Good reminder
Really need to take a look at maple
What do you ask to maple
Maple is great! I use it all the time
What do you mean?
It has web search, so yes.
can multiple people use one subscription without their chats being visible to each other? Anthropic is disallowing that, and I'd like a solution around it.
I suggested family plans.
I think I will use the paid version in 2026. Any promo codes?
Would be great
Have you guys considered publishing to
@Zapstore for us degoogled people? 😏
You’re a child molester. Kill yourself.
The ability to hide my chat history in case I want to show someone a specific chat without them being able to see the titles for all of the chats I have
I offered my help, even though it's the easiest store by far. Now waiting!
That's cool I might just become a paid subscriber. I am testing your app.
I paid for Lumo+ and it's complete garbage
Is the paid sub faster than the free one ?
Happy New Year! Maple got a huge model upgrade while you were celebrating. 🎉
For 2026 you get AI reasoning as good as the frontier labs AND privacy.
Why give your data away to other companies anymore?
View quoted note →We let you collapse the entire history by clicking this button. Would you like something more, like blurred chat titles?
Lots of requests for a Family Plan. For now we offer the Teams plan
Probably not coming to Maple, unfortunately. Too much awful stuff can be done with it, and we already have lots of awesome, useful things we want to build in Maple aside from image gen.
You wiling to delete and reinstall to see if that fixes it? We have a handful of people reporting this but haven't locked down what's causing it. Your data won't be lost because it's all stored encrypted.
Would be great to use Zapstore, whilst Maple does have apk download (which is nice) a usable appstore is better
And zapstore publishing is as straightforward as it gets
Would be nice but they have their apk on their site for non google players
Will keep an eye out - doesn’t make sense for a commercial plan for just 2 of us.
Done - will check back in
@Marks looks to be resolved
You guys are killing it!
Like everything privacy allows you to take full advantage -- niche things I won't use with the AI spyware (gemini, GPT, etc...) Maple has really helped me with...
Zapstore I believe can sign it themselves as the apk is available
Been using it and really enjoying
@Maple AI do you have a referral program?
@Marks issue has returned.
Do you find it happens more on cell connection or wifi? And do you use a VPN on your phone?
We suspect it's an initial connection issue and are trying to diagnose.
Feel free to drop out from sharing tech details if you don't want to.
What's in it for you:
- Discovery - thousands of Nostr users who use Zapstore
- Auto-updates (typically not possible with APK)
- Security: Users that first install can cryptographically verify your release, important for a privacy-focused product
- Bonus: Get zapped and support freedom tech
All good happy to help try and diagnose.
I’ll keep note on cell/wifi. I don’t feel like either makes a difference currently.
I’m running Obscura as my VPN
Ahhhhh, this is so helpful. Love these quality of life small changes that add up over time. Thank you!
Thank
@Marks and the
@Maple AI crew for allowing a pleb like me to use the Kimi model daily. It’s very good and will come up with angles Claude and ChatGPT don’t. And obviously I can have private chat with it.
Well worth the sats.
#v4v #ai
View quoted note →@Derek Ross can we use this in Shakespeare?
yes you can.
Having issues with Maple not understanding today date.
I want to use
@Maple AI for coding, but it still has some maddening limitations that make it not a viable option yet. I don't know which are the LLM's fault and which are Maple's, but a few improvements would make a big difference:
File sharing:
- I can only upload one file at a time, and not with drag and drop - there's a file picker that starts from scratch every time instead of opening the last directory I used.
- There's no option to show it a repository online or a folder on the device so it can scan more than one file at once. Even without this, uploading a bunch of files in one message and doing it more efficiently would be enough.
Behaviour:
- No matter what I tell it, the AI responds to every prompt by jumping straight into fixing or writing code. I literally just said (using Kimi K2 Thinking), "I can only share files one at a time, so don't respond until I've shared a bunch to show you what's happening." I expected some short response back, maybe with observations about that first file, but sure enough, it generated a whole page worth of code. How do I get it up to speed with what I want when that's the response to every prompt, and it takes 10 prompts to get my point across? And all the unwanted processing takes up usage credits and context window space?
- I saw the same behaviour with Qwen3 Coder a few weeks ago - if it's a Maple thing, maybe it can be easily fixed.
With Claude Sonnet 4.5, I can tell it to wait as I get it up to speed, upload 20 or so files at a time if I like, and let it observe as I go. It does respond to each message, but it will wait if I say to until I tell it what I'd like to build next. Feels like a functional conversation with a capable employee instead of a frustrating conversation with an overconfident, pushy one.
I hope this is constructive - the tool is so close to being ready, I hope it becomes the one I use soon. It's fine for asking questions, but for working on a project like I am, it feels like a battle the whole way through.
Wondering if I'm being unreasonable, I'm running a test, taking turns trying each model within one chat, with the same prompt: "I'll upload a file - don't do anything with it until I tell you more." I'm uploading a different txt file each time.
Llama 3.3, OpenAI GPT-OSS, Gemma, and Qwen3-VL passed the test fine. Qwen 3 Coder and even Kimi K2 showed considerable restraint. DeepSeek R1 thought for 44 seconds and responded with a long answer, but didn't write code.
So I can try uploading files with the chat set to a model that obeys more easily, then switching to an overly eager one when it's time to build.
I'm sorry, I spoke a bit hastily.
I can make it work, if I'm really firm with it, and patient with the file-sharing process.
Looking forward to the improvements I'm sure will come.
Read the full announcement: 
