TypingMind

https://x.com/OfficialLoganK/status/1915934863527420398/photo/1 Unlike the Gemini API, the OpenAI API offers three levels of thinking control: "low", "medium", and "high", which behind the scenes we map to 1K, 8K, and 24K thinking token budgets. If you want to disable thinking, you can set the reasoning effort to "none". https://ai.google.dev/gemini-api/docs/openai

I used to be able to send a message while waiting for the response to another message and it would be queued up and sent once the response was complete. This recently went away and I am no longer able to do it. Please restore this functionality.

https://developers.googleblog.com/en/gemini-2-5-pro-io-improved-coding-performance/

https://platform.openai.com/docs/models/gpt-image-1

Will it be possible for the user to designate a local folder on the computer for backing up all chats? Then the user has the ability to backup this folder as per their convenience. Bad for the business model, absolutely superb for the user!!

thought for "1 second" (not "1 seconds")

Since vision has been around, my sync storage frequently fills up. I’d like to be able to sync and store data myself rather than clear it constantly or subscribe to an additional storage plan.

Implement the MCP protocol that Anthropic has just open sourced, so that we can add any of the MCP servers that have been and will be developed to increase the capabilities of TM. Would be extra cool if it were done in such a way that we could use them with any LLM we have configured in TM, similar to what you did with your answer to Anthropics artifacts.

One element that I think needs improving is the number of clicks required to get the audio output out: https://www.loom.com/share/da959db09e36464ab94494a957d69f09 Basically after generating text I right click on the 3 dots, click on the play button, wait for the button to appear, click on it on the left side, wait for the audio to load, press play again, wait for the audio to play, press the pause there... you can see it in the video. Ideally: have an option to autoplay audio (or at least an option to display the play button that will play the generated text)

The repo is lagging behind by a week–would really like access to the new models and MCP in my self hosted instance https://github.com/TypingMind/typingmind