Lumo
223 results found
-
ghost mode (and/or web search) saved
Hi there,
after I started using Lumo for a while, I like to use the ghost mode by default. However, under current setting (both on webpage and on Android app) I have to switch Lumo to ghost mode (and turn on web search) every time. Can we make it a setting to use the ghost mode (and/or web search) by default? It will save a lot of effort.
Thanks.
By the way, I like Lumo very much. After I found it, it became my main AI assistance.
13 votes -
Copy/export AI reply the way it preserves font/formating/headers/quotations
Would it be handy if a button to copy the AI answer would be multi-functional to allow copying answer also in a
- markdown
- HTML
- BBCode ("Bulletin Board Code")
- readable text (currently pasted formated text with quotations is not so easily readable when pasted into a plaint text editor/viewer)13 votes -
Please list reference links for various parts of the answer
It would be great if the Lumo AI would include web links with all answers referencing where answers came from and/or where further direct research could be carried out. Perplexity offers this functionality and I really like it because it allows you to put a little more trust in the quality of the answers.
13 votes -
Highlight‑to‑Answer Feature
Add a capability that lets the user highlight (select) any fragment of text in the chat and then have Lumo generate a response that is explicitly focused on that highlighted portion. This makes clarifying questions, getting quick explanations, and avoiding unnecessary back‑and‑forth much easier.
13 votes -
Python interpreter
Hi there, I'm a Proton user from around 4–5 years. I consider myself an early adopter of new technologies, so I've been testing out ChatGPT, Gemini, and other variants of LLM chats. One of my main uses of them is as a researcher and engineer, so I want LLM that are robust, in the sense all a LLM can be robust and predictable. But, in the sense, I want a "translator" o a "meta-transpilator" that translate commands into actions to be performed. For example, the task "translate this from Spanish to Catalan", is in fact a direct task that involves…
12 votes -
Allow anonymous data sharing
I know that Proton doesn't create/train its own AI model, but a good european alternative would be nice to see. As unpleasant as this might be, to create a good model, lots of data is needed. A great app is worth nothing without good models. The current market leader, openAI, uses user data to train their models and have a huge advantage.
If my data is ever used for training, I want to give it to a company I trust (or think I can trust) to handle them carefully. And this is you. I would like to see the option…
11 votes -
VSCode integration
Other LLM's like ChatGPT and Claude have integration with VSCode. It would be great to see an integration for that or another opensource IDE.
The most amazing thing would be if you can replace all the things most people use day to day with apps and have full support on Linux.
11 votes -
Add models for creative writing
None of the models Lumo uses are very good at creative writing. Please add a model that can provide helpful writing critiques, ideas, etc., for creative uses such as storytelling, poetry, songwriting, and creative non-fiction.
11 votes -
Customize Response
I'd love to see a "Customize Response" button like duck.ai has. It basically lets you tweak the prompt without having to type out everything every time you start a new chat. The idea is sort of similar to https://protonmail.uservoice.com/forums/932842-lumo/suggestions/50343312-memory-or-knowledge-functionality-for-lumo, but not quite. I think this idea is a bit easier to implement.
11 votes -
Option to change avatar
I wanted to suggest adding an option to customise or hide the default cat avatar. I'm not much of a cat person, so having the ability to change or turn it off entirely would be a great improvement.
11 votes -
Disclose weekly limits
At present, Lumo has a weekly limit on the free tier. The problem is, a user has no idea what this limit is, and only find out when they hit it. They also don't know what it'd reset. Proton should be providing transparency on this, not just a "surprise, you hit quota, buy or come back after some undisclosed period of time".
10 votes -
3) Lumo Research
Lumo Research: A deep research report that lists sources, articles and an AI article that can be used.
Next post: https://protonmail.uservoice.com/forums/932842-lumo/suggestions/50637323-4-lumo-pages
10 votes -
Add support for de-googled devices
Lumo is unsupported without Google Play Services. Can't start the application, blocked during boot.
Using LineageOS. Should work without Google.10 votes -
public URL parameter that pre‑loads a specific prompt
It would be nice to have a public URL parameter that pre‑loads a specific prompt, such as https://lumo.proton.me&q=my_specific_prompt because this would make it possible to define "search"-shortcuts in Browsers or for example in krunner under Linux to open Lumo directly with a starting-prompt.
10 votes -
Font size options for Lumo app, IOS
The need for a larger font size in Lumo IOS app for those of us with visual impairments please! Or better yet font size options (small, medium, large), ASAP on this thank you!
10 votes -
Learning Feature on Lumo
I would love to see Lumo receive a learning feature similar to ChatGPT or other AI tools. The idea would be that Lumo could help users study by generating learning materials such as quizzes, flashcards, or practice exercises automatically based on input. This would make Proton not only a privacy-focused productivity suite but also a helpful tool for education and personal development. Adding such a feature would make Lumo far more versatile and improve its value for students and lifelong learners.
9 votes -
Latest highly efficient open source LLMs suggestions.
I would like to suggest some of the latest, cheap and very powerfull llms, so that you can replace current LLMs for better ones, to improve consistency and manage costs.
hf.co/Qwen/Qwen3-Next-80B-A3B-Instruct
hf.co/Qwen/Qwen3-Next-80B-A3B-Thinking
hf.co/openai/gpt-oss-120b
hf.co/zai-org/GLM-4.5Vplease consider using them in lumo instead of the current models
9 votes -
Allow external files as data sources
It's annoying that I have to download publicly available files in order to upload to a Lumo session. Since you have a web search option, I know you have access to the web. Please add functionality that allows us to point to URLs to use as data sources. For example, I have some markdown files in my public GitHub repos i would like to use as a data source
9 votes -
Some replies are unnecessarily long / Make shorter replies
Quite often Lumo is longer in its replies than I would like to. I can always ask Lumo to be short, but it is a bit annoying.
A) Can there be some switch near the prompt where i can single click to change length of the reply? (my last choice would be remembered or in a Settings would be an option where I can override this so it always resets to a mine defined default length)
B) Make the replies shorter and add a button at the end of the reply, where i can click to let Lumo return more…9 votes -
Feedback on Conversation Restrictions
I value Lumo’s privacy-first approach and commitment to respectful dialogue, but I feel that the conversation restrictions and automated content moderation make it frustrating to use for honest adult discussion. Too often, it feels less like I’m talking to a smart assistant and more like I’m conversing with a cautious PR department or a nervous nun—avoiding anything remotely challenging or controversial.
Real conversation and learning require engagement on sensitive, nuanced topics (like politics, social justice, religion and world affairs). Instead, Lumo shuts down or blocks the session whenever certain keywords or contentious issues are mentioned—even if the conversation is thoughtful,…
9 votes
- Don't see your idea?