TypingMind (→ feedback.typingmind.com)

Allow agents to call other agents. This would enable the ability to be able to use an orchestrating agent, instead of solely sequentially chained agents.

I would like to request a feature that allows users to easily reorder or rearrange messages within an AI agent’s conversation history. Currently, it is difficult to edit the order of messages, and users have to use copy & paste repeatedly to change the flow of the conversation. Adding a simple drag-and-drop or similar functionality to reorder messages would greatly improve the usability when refining AI agents and their dialogues. Thank you for considering this feature!

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.

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.

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

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?

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.

This will greatly help fine-tuning the agent as it will allow users to analyze and keep record of changes. Additionally, and most important, it will allow the upload of the summary file to chat leveraging AI to help fine-tune the agent.

I would like Map scrapper like https://mapsscraper.ai/

In the section of assigning a specific model to an AI agent, it is unclear which provider I select based on the name in the list. Example: when I define Claude from Anthropic or have access to Claude via OpenRouter I don't see the difference in the list.