Store and Auto-fill OpenRouter API Key for Future Imports

When importing models from OpenRouter, I need to re-enter my OpenRouter API key every time I want to add a new model. However, OpenRouter only shows the API key once when it is generated, and if I haven't saved it somewhere, I can't recover it to use in the future. This makes the process difficult if I forget to store the key, since TypingMind does not remember it. I would like TypingMind to securely save my OpenRouter API key after I enter it for the first time, and automatically use (or pre-fill) the same key whenever I import more models from OpenRouter. This would prevent me from losing access to my models if I lose the OpenRouter key, and make the import process much smoother. Thanks for considering this improvement!

Allow two API keys for Gemini

So you can use your free rate key with paid key as backup when your limit hits.

Iphone app line break

Please change the return key in iphone to line-break. At the moment it sends the text to the chat and leaves to way available to go to the next line.

Allow to select model for selection quick quesiton

I only use Gemini 2.5 Pro which is very slow so this feature won’t ever get used by me. Allow me to change the model for the feature just like you can for title generations.

Reference another chat for context

The ability to reference another chat for context to the current one would be very useful. ChatGPT provides this feature, so this is a common need. Forking can provide a way to do this, but then the previous chat is still cluttering up the new one. So forking is useful in some cases, but not having to scroll past a long chat to get to the new part would be useful too.

Batch model change across multiple chats

Every time there is a new model released, I need to manually change the model of each conversation that I am using. I do change the default model but that only applies to the new conversations. It would be nice to have the option to chnge the model of many conversations at once.

Add chats to knowledge base.

The ability to easily chats to the knowledge base (or else an AI summary of them) would be very useful. ChatGPT does this automatically - tailoring responses based on previous chats.

Add a Agent Skills to Typingmind - https://agentskills.io/

Agent skills are MCPs on steriods, can you please add support for skills?

Support Anthropic Claude "Agent Skills" Integration via Custom Model Parameters

Description: Please add support for Anthropic's new Agent Skills (Skills API) in TypingMind’s custom model configuration. This would allow users to specify the container parameter, custom Skill IDs, and required beta headers (such as code-execution-2025-08-25 and skills-2025-10-02) when configuring Claude models—enabling full usage of Anthropic's "Skills" within the TypingMind chat interface. Key Features Needed: Ability to set container (with skills) parameter in custom model advanced settings Support for the required beta headers for code execution and Skills Option to select and manage custom skills (skill IDs) for use in Claude-powered chats UI support for Skill versioning and multi-Skill workflows (Optional) Files API integration for downloading/uploading generated files Benefits: Unlocks Advanced Automation: Use pre-built and custom Anthropic Skills for Excel, PowerPoint, PDF, scripting, and more, directly from the TypingMind interface. Empowers Agents & Workflow Building: Enable automations, code execution, custom document generation, and business process integration with Claude’s secure code sandbox. No Need for External Scripting: Use Anthropic’s Python client features from within TypingMind—no extra coding or external scripts required. Keeps TypingMind Competitive: Stay at the leading edge of LLM platform capabilities as Anthropic deploys more enterprise co-pilot and tool automation use cases. Scalable Across Teams: Organizations can administratively manage and evolve custom Skill libraries for all Claude-powered agents organization-wide. Thanks for considering this high-impact upgrade!

AI agent as an MCP connector

I want to create an agent inside TypingMind. Now I want to be able to connect it to Telegram and Slack via either the API or the MCP server so I can chat with the agent on the go via instant messaging. Similar request here: https://feedback.typingmind.com/p/ai-agents-as-plugins

Auto-Scroll to the last message

Thanks for the app. One thing worth fixing: getting back to a chat when the iOS app (PWA) after it was minimized takes you back to like 10 posts away from the last response in the current chat.

Multi-Agent Response (Parallel Execution)

Multiple Agents can run the same prompt simultaneously. The outputs can be compared without switching conversations, and the insights can be merged.

Please Help add instructions on how to add brave api

Please help Add instructions on how to add brave api

Grok image model fails to show image

I tried grok-imagine-image-pro and had to set the model to ‘OpenAI Responses API (New)’ to pass the Test and set ‘Advanced - Custom Body Params’ to ‘string:prompt:banana’. This didn’t display the image in my Chat prompt which would go to Fetch/XHR-generations-Payload-Messages[1][‘Content’] instead of Fetch/XHR-generations-Payload-prompt. I could get the image URL (of a banana) via Fetch/XHR-generations-Payload-Response. You can delete/edit the form after passing the Test and before saving the model, but you must pass the test to enable the ‘Add Model’/’Update Model’ button. I did find a Grok image plugin that didn’t work for me, although I think it was using FLUX. Maybe all I need is documentation, as Gemini 3 didn’t help.

Rearrange pluggins!

Is there a way we can rearrange pluggins in the chat and the plugins page similarly like models? This would be a really cool and important feature for organizing. Especially when we have alot of pluggins overtime it can be confusing if we don't have the option to rearrange them as we want. Thanks!

Feature requests

I use a lot of chats paired with custom agents. I do that so I can retain context. I have probably 10 chats I jump back and forth between (just like having a staff of 10 people targeted at different skill sets and tasks). In TM, the chat left sidebar currently has one display mode (AFAIK): the name of the chat on top with a bit of the last response below. What I would like: 1) A second display mode that only shows the chat name, in a single line of text. 2) Hotkeys to allow me to select chats (Alt+Ctrl+Numpad 1-9 as defaults?). 3) a shortcut to jump to the user prompt edit control. and unrelated… 4) a Setings switch to have TM scroll to the bottom of the response. (I use the Play button, and it gets tedious scrolling down so I can click it…) Thanks for your consideration.

Automatic Hiding/Deletion of Example Folder

Description: Every time I log in to TypingMind, the standard example folder and chats are recreated and I have to manually delete them. I would prefer to have an option to permanently hide or automatically delete the example folder/chats after each login, so that my workspace stays clean and only contains my own folders and chats. Benefit: This would improve the user experience for those who prefer a clutter-free workspace and don’t need to see onboarding/example content after initial use. Thank you!

More fluid category/tag editing of Agents

We have a lot of agents. Categories change. Right now, do change the category of agent, one has to edit the agent (page refresh) change the category, save. It'd be nice if in the list of agents one could changing tags/categories fluidly without having to open the agent editor.

Add Claude Opus 4.6 and Include the Version with 1M Context

I appreciate your promptness in integrating Opus 4.6 following its release. I would also like to formally request that you include the version of Opus 4.6 supporting 1M context tokens, similar to the approach taken with Sonnet 4.5 (1M).

Drawer not accessible in iPad split mode.

The UI makes it impossible to access the drawer for all the elements when I’m in split side mode because the stop light elements from Apple are in the same place. It’s really crucial for me to use the web app in split mode to have multiple apps open to copy and paste between them.