TypingMind

I really love running two models concurrently - my favourite feature of Typing Mind - allowing instant comparisons to be made. Would it be possible to add this feature to the agents - so they automatically start with two models - as opposed to me adding the second model each time.

At the moment, you can assign a specific model to an agent, but doing so prevents you from selecting any other model. It would be useful to be able to specify a default model for an agent and still allow the user to choose another if the situation requires it. For example, I have xAi as my global default model. But when I choose my "Pro Coder" agent, I would like it to default to Claude Sonnet 4. However, there are times when using Pro Coder agent that I think GPT4.1 might be the better choice based on the type of coding question I'm asking.

Cron style actions for AI agents so they can reach out to user on daily (or any specified) basis. Use cases: Fixed checkin with users about topics, reminders, pro active bots instead of passive.

https://platform.openai.com/docs/assistants/overview

Are there any plans to add more data source features for the knowledge base soon? My code bases are larger than 200k, and I’m curious how extra knowledge base context could improve my workflow via TypingMind. I heard that more data sources are available with the business tier of TypingMind—do I need to purchase a business account to access these features?

Option to toggle or pin conversation starters for a character so they don't disappear after a chat has started, or can at least be accessed. This would offer a huge boost in productivity with pre-written prompts.

Similar to custom GPTs, it would be awesome to be able to quickly generate profile pictures for custom characters using DALL E.

1) update agent name in chat when updated in settings 2) mark agent in chat deleted, when deleted from TypingMind

For example these different methods: Text file(s) of data: Currently it becomes a long process if a user want to provide multiple example of training data since one has to copy and paste into each filed User/Response. This can be just text based on the data. Or example conversations user/response example. CSV file: The file can have examples of data for the AI character to be trained. on. Again this can be just text based on the data. Or example conversations user/response example. PDF files of data: Another method is a PDF file(s) which can have data you want to train the AI character on. URL Link(s): User can provide a link to a site which has data related to the AI character.

It would be great to be able to organize characters, create user tags for easier search. This could be bundling characters into a folder structure (eg. strategy, content, design). Or providing search tags and a filter option at the search bar so that the user can toggle a category and only those types of agents are filtered.