Feature Requests

App crash all the time, no support for newer models, memory leak, no support... As a paying customer I'm really disappointed.

from openai import OpenAI client = OpenAI() prompt = """ Write a bash script that takes a matrix represented as a string with format '[1,2],[3,4],[5,6]' and prints the transpose in the same format. """ response = client.responses.create( model="o3-mini", reasoning={"effort": "medium"}, input=[ { "role": "user", "content": prompt } ] ) print(response.output_text) https://platform.openai.com/docs/guides/reasoning?api-mode=responses

It would be great to know what to expect for support for new models from companies MindMac already supports. Claude 3.7 came out a couple of weeks ago but it's not supported yet. I get that it takes time to get things updated, but what is a reasonable expectation for customers who want access to the newest models?

I'm not affiliated with any of these, just providing options to those of you who, like me, got burned by this app. BoltAI - This is the absolute best alternative if you're Mac-only. https://boltai.com/ . tons of regular updates. Msty - Phenomenal app, multi-plat, lots of great productivity features, update frequently, lots of activity in Discord: https://msty.app/ . Free version does a ton. Jan.ai - Not nearly as powerful, since it's primarily intended for Local LLM usage but also happens to do some cloud LLM inference as well, but fully open source: https://jan.ai/ MacAI - Open source, extremely new, Mac-Native, progressing very rapidly: https://github.com/Renset/macai SupGPT - decent, not much experience: https://supgpt.app/ Good look to anyone else looking for an alternative.

I really like your software, and thank you for providing such an excellent tool. I’m currently facing a minor issue and would like to consult with you to see if it can be resolved. I’m using the OpenRouter API with the model deepseek:r1, corresponding to the model link: https://openrouter.ai/deepseek/deepseek-r1 . In OpenRouter’s official chat room, I can see the reasoning process of deepseek, but when using MindMac, I could not see the reasoning process. I would like to know whether MindMac supports displaying the reasoning process?

I'm wondering if the app development is still ongoing, as I have not received any replies to my support requests.

Incredibly slow to update for a paid product & abstraction of model updates from general app / software updates is critical. Just realized there haven't been any updates for a few months now, which is completely ridiculous. For anything ai-oriented, that's a lifetime.

Please decouple new API support from other releases. Enhancements, bugfixes, etc should not be blocking for new model support, e.g. Gemini 1.5 Flash or Sonnet 3.5. This request isn't about adding these in specific, it's about rethinking the current release process to allow for new models to launch swiftly after they become available.

It would be good if we could just paste in Google Drive links to documents and spreadsheets instead of having to download them and upload them to MSTY .