Lumo
359 results found
-
Make it possible for Lumo to interact (via an dedicated Proton AI agent) with all your apps within the Proton Suite
E.g.
I want to tell Lumo that it should add the vacation details of the last Protonmail I've received to my Proton calendar
update a specific proton Sheet with the latest information I give it (add a number to a column)
show me photos of my vacation in October last year (e.g. only selfie photos)
ask when my Proton subscription will expire.
etc
The idea is to have one Proton app to manage your entire Proton suite. Like a secretary. ofc you would need to set up everything separately.
To think this even further, make it possible to integrate Lumo…
17 votes -
Add Lumo Plus to one of your bundle deals
Currently you can only pay for Lumo Plus as a standalone product. Would be nice if it could bundled with Proton Mail or different tier of Proton Unlimited
46 votes -
Really needs image OCR
There are a lot of image processing requests here. All basically requesting the same thing with different wording. Moderators should combine them to increase the votes. Basically we need Optical Character Recognition for uploaded images, and some PDFs that contain bitmaps. On a cell phone, this is critical and the primary reason I rarely use lumo. Being able to upload a screenshot of a log file, or a code routine, or a medical lab result and have it convert to text and analyze it is really needed. Every other big name model has this ability, but I am sure you…
12 votes -
Letting programmers use Lumo in a code editor
As a developer, I added extensions to my code editor. Some companies offer extensions to use their AI models directly in a code editor, like "Claude" extension in VS Code. Being able to work with the AI within the code editor is a huge time saver.
It would make Lumo an even more useful tool for programmers and help improve their workflow.
Could you make the same with Lumo?
25 votes -
Search not just Lumo chats titles but also content
The sidebar allows searching in chat titles, but I am unable to easily find on how to search in the chats content (in my questions and Lumo replies). I am aware that i can use browser Ctrl+F to search in current chat, but not in all available chats).
Ideas:
- after you type the search query, maybe hitting enter can execute search in content.
- content search included by default, only the matches in chat titles will be displayed on the top of the search resultsclicking on a content search result, should jump to a correct place in the…
40 votes -
Reoccurring tasks
I would like to see a feature where you set up a job for Lumo, like "summarize the news" (ofcourse with a more finegraded prompt), using web search, with an option to make it reoccurring, like a calendar event, for example every day at 7am.
Lumo would then message me on its own, with the latest findings.
This could be used in many ways.15 votes -
Code editor
It would be nice if the codeblock Lumo uses would be an interactive code editor.
Right now if I ask Lumo to change part of my code it also tends to rewrite other parts of code which I didnt ask it to do. With an interactive code editor I would be able to select a part of the code and make a prompt just about that selected part. Or I could edit the code myself if I dont like something without having to copy paste the whole code again to Lumo to let it know I edited something. This wouldn't…40 votes -
Report Carbon equivalent footprint of a user requests
I think I do not have to explain that energy consumption of LLMs even doing only inférence is high.
Since Proton has always promoted transparency over source code of its tools, I believe it should also pioneer transparency on this matter.
There exist libraries to wrap function calls and estimate co2 équivalent (e.g. mlco2)37 votes -
Make Lumo Less Dumb
As a paid Lumo subscriber, there's no kind way of putting this -- Lumo feels really dumb compared to any of the other mainstream LMMs. It struggles to follow and keep up with conversations once they exceed a handful of back-and-forth exchanges, it frequently hallucinates and confabulates, it gets easily confused to the point where I'm having to help it rather than it helping me, and it just generally feels like conversing with a well-meaning but addled, confused elderly person. As such, I use it sparingly to brainstorm ideas or just have quick chats but cannot rely on it for…
16 votes -
A setting which prevents the Enter/Return key from submitting the prompt
Often now, when I am in the flow of writing a prompt and I naturally press Enter for a new line I end up submitting the partially written prompt. I am aware I can use shift for a newline but I've enjoyed the ability to change this behaviour in other apps (like Slack) to work in my favour. I would love to see this option to appear in Lumo sometime!
40 votes -
Increase Lumo context window
Hello
Currently lumo context window is too small 3k token on the fast model and 13k token on the deep think model
ChatGPT perplexity and all other AI company their big model hold up to 130k token
Im having problem with long complex conversation where lumo forget stuff too fast forcing me to repeat or to re paste tons of data leading to a frustrating experience feel like talking to a dementia person ....
25 votes -
"Voluntarily disclose" some chat with Lumo to help training
One of the disadvantages Lumo faces compared to its rivals is the shortage of training data. Why not offer Lumo users (both free and paid) the option to allow some of their chats to be used for training? For example, add a button at the beginning or end of each chat asking: "Do you want to donate this chat to help train Lumo?"
To encourage participation, Proton could offer a small reward for every chat donated—like a few minutes of premium usage or temporary access to advanced features.
Importantly, all donated chats would be stripped of any user-identifying information before…
4 votes -
Higher file upload limits
I have a Plus account which has a listed limit of 25 mb, and have run into issues where the system gives an error message saying that I cannot load more than 10 mb; please increase file size up load limits
32 votes -
Lumo integration in meet for meeting summaries & transcriptions
It would be great if the upcoming meet app would have an option to summarize and transcript meetings.
Making this possible with a trustful AI like Lumo would be amazing (and I think no one else has a meeting transcription feature with a trustful AI)17 votes -
Real‑time audio conversation
One of the features I was using—and I see people using—is audio‑based conversation with the models. The main goal is to practice languages by asking the model to simulate a dialogue, then receiving feedback and corrections. This is a feature I would love to have in Lumo, because I don’t feel comfortable sharing my voice with Big‑Tech models or companies that don’t respect privacy.
32 votes -
LUMO+ with Access to Multiple AI Models
I’d like to suggest an improvement to LUMO+. Currently, LUMO+ is great, but it would be even more powerful if it worked more like Perplexity Pro, where subscribers can access multiple AI models like GPT-5 or Gemini 2.5 Pro, including those for image and video generation.
The key idea is that LUMO would remain the secure privacy layer between the user and these external models. This way, LUMO could either answer directly or automatically choose another model when it’s better suited for the request—without exposing any private data or the user’s identity. Everything would remain protected under Proton’s privacy-first approach.
…
30 votes -
Multiple Lumo agents
Now that its possible to personalize Lumo, I also wish for the opportunity to create multiple different Lumo Agents, so I could for example have one developer agent, one recipe agent and so on.
23 votes -
Tag organization for Lumo chats
It would be useful to be able to organize chats via tags.
The user could tag chats with multiple tags such as #job, #recipes, #travel and then could see all the chats with those tags.
Lumo could even auto-tag chats too - that'd be super neat if possible!
8 votes -
Implement TEE-Based Confidential Computing for Lumo Inference
Feature Request: Implement TEE-Based Confidential Computing for Lumo Inference
SummaryLumo's current security model does not protect user prompts during inference — the window when plaintext is most exposed and most exploitable. This is not a theoretical concern; it is a documented architectural gap with a proven, production-ready solution that a direct competitor is already shipping.
The ProblemLumo's security model blog post dismisses inference-time privacy by framing the only alternative as homomorphic encryption (HE), correctly noting it is impractically slow. However, this framing is a false dichotomy.
As Proton's own documentation acknowledges:
…"prompts are asymmetrically encrypted so only the4 votes -
Emphasize that user data is never used to train AI models
From the Lumo "Getting started" webpage: "Information you enter is never used to train AI models." I think this should be emphasized more and expounded on, perhaps giving scenarios using both Lumo and other AI chatbots. (It looks like a no-brainer choice, to me, of which bot to use given that all the other ones (Maybe not DuckAssist?) exploit you and your data/thoughts.) While the privacy mantra of Proton is well-known and can be assumed, that's no reason to be subtle.
36 votes
- Don't see your idea?