Feature Requests

Allow us to use other LLM models like ChatGPT or GROK or Gemini or etc in the chat section so we can get better answers to the queries about the data in the card(s) we have selected. API key to connect a Recall account to GPT, etc.? With that, I think you can jack your monthly price to MEM 2.0 announced pricing. Offer annual subscription or if you're ready to raise bootstrap capital then offer a lifetime deal.

I would like to be able to chat directly from a public AI like chatgpt, gemini or Claude and have access to recall from behind. For example, I would like to be able to generate images, use gpt5 voice chat, etc. with access to recall. Currently Recall remembers everything but keeps it to himself. It's like creating a library but keeping it private instead of making it public. This could use a more direct mcp server or integration. The ideal would be for the configuration to be simple/accessible and fast in public AI. Example, using a gtps in chatgpt. Todoist does that, it's great. We talk normally but with additional capacities. Regards, Adrien

I'd like to have the option to choose the AI model that I want to use and/or be able to bring my own API key for the model of my choice.

adding chat answers as notes. Sometime it is very good answer we need to save.

Possibility to define a system-prompt for each tag. For example, if I have a tag that contains financial articles, I can define standard instructions for LLM such as: “use financial jargon and don't translate technical terms.”

I’d like the chat feature to list links to pages in the document it used to generate the response

Have the option of a chat ai that, when asked a question that the card doesnt have an answer for, it can search the internet for content on the topic that does answer the question and suggests content that you can save to your Recall. If you are using Recall for research purposes, the ai could help you fill holes and get clearer information by helping you expand your saved content.

AI space is every evolving. Would love to have more insight into what LLM is currently being used. Also what emedding model is being used on the inference side as well. What's good today may not be good tomorrow. Are you all using open ai? I'd love the option of using open router even. or better yet give folks a discounted rate, but let them use their own API key.

It would be nice if I could exclude a tag when querying my Recall database. I noticed that when asked about election, 5 episodes of 'Chris' are consulted and not one of 'religion'.

When on a tag or card chat, if you ask a question that is not answered in the content, you have the option to allow the ai to find another source online that includes the info you need. It could make suggestions for content that would take your understanding of the topic to the next step, or fill a hole into the info that your saved cards dont include. So now when an issue comes up that you haven't seen before, you can still go Recall to search you for new content and help you expand on your topics. This also gets more people using your app more often. It becomes the default search engine for your heavy Recall users and changes the way they research.