TypingMind

If Theo can do it, there's no reason it can't be applied on Typindmind. Currently, only Sonnet 3.7 Sonnet and Gemini 2.5 Flash support it in TM. I would love to see it for O3, O4 mini and Gemini 2.5 Pro here. I know OpenAI restricts some models unless you've verified your organization but even with that, I don't get the reasoning text.

Sometimes I need to refer to an old chat, but its not super easy to find it, or even remember that it exists. It would be really cool if I could chat with the AI in typingmind about the rest of my chats within typingmind. Basically RAG for my typingmind chat library.

Can we have conversations where we can choose multiple bots to talk to - similar to Silly Tavern? https://sillytavernai.com/ For example, then we could have brainstorming sessions with different bots with different skills, or learn languages in a room with multiple bots for more immersion. This will also open up the program to more people.

No plugin or easy feature available for downloading MS excel files directly. It's a key need for all people from accounts and finance. My sister who is a CFO dropped your software for that one single reason - the other being the easy of use on specialized GPTS on chatgpt Pro.

My question to the TM Help Bot: "Is it possible to fork a chat in TypingMind from the forking point onwards instead of backwards?" Its answer: "In TypingMind, when you use the Fork Chat feature, it creates a new chat that copies the conversation up to (and including) the forking point—meaning all messages from the chat’s start up to your selected message are included in the new chat. It is not currently possible to fork a chat and have the new chat contain only the messages from the forking point and onwards (“forwards-only”). The fork action always creates a copy that starts from the beginning up to your selected message, not just the branch after that message. If you need more advanced branching (like copying only the forwards/consequent messages), please consider submitting a feature request here: https://www.typingmind.com/ideas " So, here is my suggestion to add the possibility of forking "from here" in addition to the existing "until here".

Description: Currently, only AI agents can be restricted to certain knowledge base tags or sources. There is no option to filter or limit which parts of the KB are accessible within a project’s settings. It would be much more efficient and secure if we could configure, at the project level, which KB folders or tags are visible/searchable during chats started in that project. This would simplify workflows for teams managing multiple projects with different information boundaries, ensuring users don’t see or retrieve irrelevant or confidential data. Use Case: Ensure users working in a specific project only access relevant documents. Avoid needing to create dedicated AI agents for every project/Kb-combination. Improve privacy, focus, and organization for teams with several overlapping datasets. Suggestion: Add a section in project settings to select which KB tags/folders are available in that project. Chats within the project would only search/retrieve those tagged documents.

I use ---- to separate different blocks of copy but typingmind takes it as though I want to queue message. Please enable a feature that allows us to Disable message queuing Allow us to setup a different syntax for queuing Thanks

Description: Allow users to treat prompts as context blocks that can be rotated in and out by selecting multiple prompts from the Prompt Library in one go. Users should be able to efficiently insert several prompts sequentially into the input window with a single action. Reason: Managing prompts as context blocks would streamline workflows by enabling users to quickly combine and rearrange pre-stored context pieces. This feature would enhance productivity and provide a more efficient way to handle complex queries or instructions. Context Modules: Prompt Library: Store and manage reusable prompts. Context Blocks: Treat prompts as modular context blocks for easy rotation. Efficiency: Improve workflow by allowing multiple prompt selections and insertions at once. Productivity: Boost user productivity and enhance the user experience. Submit this feature on typingmind.com/ideas for tracking and support.

I sometimes create chats that shouldn't be visible to everyone. Could you perhaps create a “lock icon” for such chats? If you activate the lock in the parameters, you must enter a password to open the chat account. When you leave the chat, you have to re-enter the password to access the chat.