Hello, In the past I requested support for Opencode Go. This has been added and I am very thankful for taking this up so quickly. I am creating this post as you mentioned, to request support for Opencode Zen.

It would be great to have a one-click button to summarize a long conversation and automatically start a new chat with that summary as the context—without having to copy and paste manually. This would help manage token limits, streamline the workflow, and keep conversations focused. Please consider adding this feature for a smoother chat experience!

It would be helpful to have an option to assign knowledge-base documents to a folder based on tags. This way, when working within a folder, the AI would not need to sift through all documents in the KB. We also would not be restricted by an AI agent assigned to a specific knowledge base. It would also be nice to have the AI update the documents in the knowledge base.

I am hoping you could add the TypingMind proxy for this URL: 'https://apiclaude.cc/v1'. I'm currently using a third-party API relay service, but it always fails to connect when I try to use it.

I’m having a problem with the multi-model response feature in TypingMind. At the moment, it’s not possible to save multiple model responses permanently. Please change this. I suggest that, in future, all model responses should be saved permanently in the chat.

Currently, selecting a prompt from the library automatically overwrites all existing text in the chat input box. Ideally, the default behavior should be updated to simply append the selected prompt, but if that isn't feasible, please add an 'Append to current input' checkbox within the prompt editor. Great work on closing the previous ticket ('Prompt Library Browsing w/o Erasing Prompt') a year ago, which successfully fixed text being erased when simply opening the library! This new request focuses strictly on the replacement that happens when inserting the prompt, giving users a seamless way to combine custom text with saved templates.

Without this feature it is very difficult to see longs chants because in typing mind chat search options We can see the chat content but by clicking,We cannot Jump to that particular question in the chat. This feature ChatGPT has developed and this is very good feature take it seriously.

In fact, I have Claude’s new Cowork feature in mind.

Setapp now supports GPT-5.4, GPT-5.4-Pro, GPT-5.4-mini, GPT-5.5, Claude Sonnet 4.6, Gemini 3.1 Pro, and possibly others as I have seen these supported in some other Setapp AI apps. Can you add these to TypingMind? Thanks!

I suggest TypingMind add a feature to allow dynamic context to fetch/lookup data directly from the Knowledge Base, so that AI agents and chat prompts can access and use up-to-date internal documents more conveniently.

I think in the future you could add optionally some local models to make some part of the work locally, in example audio to text, and save; or even some simple reasoning tasks. :)

I’d like to suggest a feature that could make TypingMind even better for users who run local LLMs. While TypingMind already supports custom OpenAI-compatible endpoints, configuring local inference servers such as Ollama, LM Studio, LocalAI, vLLM, llama.cpp, and similar solutions still requires manual setup. It would be fantastic to have a dedicated Local Models section that makes connecting to local LLMs much easier and more user-friendly. Some ideas that could improve the experience include: Automatic detection of local inference servers running on localhost (especially Ollama and LM Studio). One-click connection to supported local backends. Built-in presets for Ollama, LM Studio, LocalAI, vLLM, llama.cpp server, and other OpenAI-compatible APIs. Automatic discovery and listing of available models instead of requiring users to manually enter model names. A connection test with clear diagnostics when a server isn’t reachable. An optional setup wizard to guide new users through the configuration process. A streamlined setup process would significantly improve the user experience while making TypingMind an even more compelling choice for anyone who wants to combine cloud models with locally hosted models. Thank you for taking the time to read this suggestion and for continuously improving such an excellent product. I hope you’ll consider adding these enhancements in a future release.

Current login solutions involve one time passcode or passkey. Both solutions require external dependencies such as access to email and access to password manager. QR login allows typing mind to be used on public computer without the risk of password being stolen. It also requires less mental effort to use compared to one time passcode.

Hello TypingMind Team, I would like to submit a feature request to add support for the OneProvider API endpoint in TypingMind Proxy. Current Issue When attempting to use OneProvider (https://api.oneprovider.dev/v1/messages ) as a custom model endpoint, TypingMind Proxy displays the following error: "Sorry, TypingMind Proxy does not support the endpoint 'https://api.oneprovider.dev/v1/messages' yet. Please contact support if you think we should add it." This prevents users from accessing Claude models through OneProvider, which is a viable alternative to the official Anthropic API. About OneProvider OneProvider is an Anthropic-compatible API gateway that provides access to Claude models with the following characteristics: •Website: https://oneprovider.dev •API Endpoint: https://api.oneprovider.dev/v1/messages •Supported Models: Claude Opus 4.8, Claude Sonnet 4.6, Claude Haiku 4.5 •API Compatibility: Fully compatible with Anthropic Messages API •Authentication: API key via HTTP header (x-api-key ) •Payment Method: Cryptocurrency-based (no credit card required) •Key Features: •No account signup required (key-based authentication) •Pay-as-you-go pricing •No prompt logging or training on user data •EU-based infrastructure (Frankfurt) Why This Matters Adding OneProvider support would provide TypingMind users with: 1.Alternative Payment Options: Users who prefer or can only use cryptocurrency payments now have a viable option 2.No Account Requirement: Users who don't want to create an Anthropic account can still access Claude models 3.Increased Flexibility: More provider options give users greater control over their AI infrastructure 4.Competitive Advantage: TypingMind would be one of the few frontends supporting multiple Claude API providers Technical Details OneProvider's endpoint is fully compatible with the Anthropic Messages API specification. The required headers are: Plain Text x-api-key: anthropic-version: 2023-06-01 content-type: application/json The request/response format is identical to the official Anthropic API, making integration straightforward. Reference Documentation •OneProvider Official Docs: https://oneprovider.dev/docs •OneProvider Status Page: https://oneprovider.dev/status •OneProvider API Overview: https://oneprovider.dev/docs#overview •Anthropic API Documentation: https://docs.anthropic.com/ Additional Context I currently use OpenRouter with TypingMind without issues, which shows that TypingMind's infrastructure can support multiple third-party API providers. Adding OneProvider would be a natural extension of this capability. Suggested Implementation Since OneProvider uses the Anthropic Messages API format, the implementation could potentially be as simple as adding the endpo

I'd like to see a table view on the provider model name screen that shows model details (release date, pricing, etc) with the ability to sort by any column. To see this information today, I have to select each model individually. To accommodate that view, I'd redo this block. It takes up way too much space currently: I'd suggest you move this cntent block into a 'Model Details' tab and put it next to the models | api keys | global settings navigation above the model list, and use this space for a sortable table. Or just shift it further over to the right. it's using up a lot of space currently. It's useful, but uses more space then necessary. writingmate.ai does a really good job at this; see screenshot below. This is what I’d like to see when I select a model provider; a table-based layout of all the models therein along w/ relevant information on each LLM the provider offers: I can sort by model, author, date dated, context, input and output, and i can enable/disable models directly from this screen. Since so many models are added each week, giving me the flexibility to sort > enable/disbable based on needs makes it faster, quicker and easier to choose a model based on credit usage. Sometimes I want the cheapest model, sometimes middle of the pack, sometimes high-tiered ones. but right now, I have to choose the provider, select the model, look in that right pane to see token cost, etc. Maybe this table view is where the 'more model details' shows up? add a 'view details' link next to the model name? If i select that, a modal slides in from the right with the model overview/parameters shown? This would streamline things greatly!

Hi Tony, Thank you for the update on expanded model provider support and response API endpoint support. I am very happy to see my long-standing request has been fulfilled. Please have option to display Credit balance under api key management, many provider have endpoint to get credit balance details Like for vercel: Base URL: https://ai-gateway.vercel.sh/v1 Endpoint: GET /credits Json Key: balance. for openrouter: curl https://openrouter.ai/api/v1/credits -H "Authorization: Bearer " { "data": { "total_credits": 100.5, "total_usage": 25.75 } } Thank you for the continued improvements to TypingMind.

Is it possible to share chats across users so that multiple users can speak into a conversation?

We have built agents for our team members, and having admin control over these showing up granularly would simplify the experience for our team. Since we are using agents, a starting model is not relevant (our system runs only on agents). Additionally having it optional from our end for our users to be able to append or not would be useful. All of the features in this section are great — they just need to be separated out so we can control our system better.