Feature Requests

Google AI Studio and Vertex AI offer extensive support for developing and deploying new and experimental language models. These models, such as gemini-exp-1206, are often at the forefront of the LLM capabilities. MindMac currently lacks support for custom models available in Google AI Studio and Vertex AI. This limits the ability of users to leverage the latest advancements in language modeling within MindMac and instead force them to wait for official MindMac support.

It would be great to have access to the same occupations, prompts and chats regardless of the device used. It would require an iCloud sync though.

Similiar to local LLMs support, through Ollama, there are other txt2img APIs. Apps such as DrawThings (free local image genration) or packages like AUTOMATIC1111's stable-diffusion-webui use this API. There's an explanation in https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/API . This would allow get images locally, fully supporting local LLMs and image generation.

Support for Stability A.i. https://stability.ai Stable Diffusion

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.

I really like using https://unstuckstudy.com/ so would be good to be able to chat with the transcript like they allow on Msty.

The current application frequently deadlocks during use, causing CPU usage to spike to 100% and requiring a force quit and restart to continue working.

For users of multiple devices, it could be very convenient to have the same favorites, folders and conversations available on all devices. This would require a sync function, or saving the conversations, folder data and most of the settings in a project file. The latter option (project file) would only be an alternative idea if a sync function is too much work for the current state. Then the user himself can simply save the project file on his own cloud share/drive. Once a project file is defined, MindMac could check automatically for changes or update the project file when some are done. This is fore sure, a bigger feature, so no stress, just for road-map documentation. ;D Suggested by Sascha

It would be beneficial if we had the ability to pose the next question while the AI is still generating a response. Unfortunately, at the moment, this function is not available. Suggested by Kamil Maciejewski

Straico provides access to several LLMs via a single subscription (think of something like OpenRouter). The developers are keen on working with developers considering integrating their API into their products. People do use the Straico API for certain applications with an Ollama proxy, but direct integration would be very helpful and less cumbersome!