383 results found

1. Speech-to-text (use mic for desktop version)

   To dictate vague ideas and concepts while your browser captures the stream of thoughts is a real time saver and I feel enhances the experience of collaborating with the AI agent. I would really like to use my Mic with the desktop version of Lumo.

   39 votes

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  New feature  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

2. Automatic calendar for displaying contact birthdays

   Please add automatic calendar for displaying contact birthdays. This is a feature in Google Calendar and is the only reason I still hang on to that app

   17 votes

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   4 comments  ·  New feature  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

3. Enable .ICS file import from https://calendar.proton.me/u/1/ instead of via https://account.proton.me/u/1/calendar/dashboard

   Various platforms are used increasingly for video meetings and webinars. When booking, I often receive a .ICS file to download frtom an email, then import into my calendar. Each time, I have to go to my calendar, then select settings, then all settings, then Import/Export. This process takes a long time. Given the frequency of needing to import .ICS files, it would be much faster and easier if it were possible to import it from the Calendar view.

   3 votes

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  New feature  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

4. Pay-as-you-go option alongside subscriptions

   Since I assume you may eventually add more capable, larger, and more expensive models, such as Kimi K3, it would be great to have an alternative option for occasional users.

   Something similar to what OpenRouter and NanoGPT offer: a prepaid, usage-based credit system rather than a traditional fixed monthly subscription. Users could add funds to their account balance, and each model request would deduct credits based on the model used, token usage, and pricing.

   Alongside this, it would also be nice to have more advanced generation settings, such as a custom system prompt, the option to use the base/vanilla model behavior where supported, adjustable reasoning effort, temperature controls, and similar parameters.

   I think this would be especially useful for people who don't use Lumo frequently enough to justify a monthly subscription but would still like occasional access to more capable or expensive models.

   Since I assume you may eventually add more capable, larger, and more expensive models, such as Kimi K3, it would be great to have an alternative option for occasional users.

   Something similar to what OpenRouter and NanoGPT offer: a prepaid, usage-based credit system rather than a traditional fixed monthly subscription. Users could add funds to their account balance, and each model request would deduct credits based on the model used, token usage, and pricing.

   Alongside this, it would also be nice to have more advanced generation settings, such as a custom system prompt, the option to use the base/vanilla model… more

   4 votes

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  New feature  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

5. Screenshot -> Proton Drive + directly added in Lumo's chat/project

   WARNING: what i am suggesting does exist if you use "change destination" of the screenshot program you use to save the images in a Proton Drive folder that will upload the pictures and so on. So please understand that what i will suggest is actually MORE then this and it's DIRECTLY linked to Lumo. AKA no, this is NOT a proton Drive suggestion => NO this is NOT a duplicate of existing suggestion exactly because i am suggesting MORE.

   That is also why:
   I will NOT explain in details why it's needed because it's absurd to assume that you even would need what i will suggest if you don't understand it.

   Lumo, new tool -> screenshot.

   In settings -> Timmer, format (like png), whole screen or snip so on and on, all this are the typical screenshot stuff.

   But the idea of it being from proton = it is saved directly in proton drive, not on the PC disk.

   And on the idea that proton drive can be linked to projects (or reverse i guess is more correct?) well that is why i said: NEW TOOL.

   As in we are in LUMO CHAT! we press tools and screenshot and we can take a picture and Lumo get's the screenshot directly.

   And what people don't get is the following: Upload image requested... how many of you saw this when dealing with bureaucracy or other document or evidence or similar? as in Lumo to have screenshots so well integrated that it can show us click butons.

   Can you show me situation a (click to upload) and situation b (click to upload)

   Or

   Click here to take a screenshot of situation a if you press "shortcut key combination" and, then, again, for situation b.

   Note: both files are save on proton drive's subfolder that is linked to this chat.

   Above is an illustrative example. idea is that we don't need to create any folder, we don't need to link anything. we don't need to upload anything. it's exactly how the take a photo via phone, but screenshot. But it also allows Lumo to directly associate screenshots with specific topics aka eliminating everything else, all the other information, in that picture.

   As in the Proton Drive, will have the screenshots = we can do cross platform chat <- again, the take photo via phone's camera is the best example.

   With the main idea is that the screenshots (and i guess phone photo?) are saved in a specific Proton Drive that is associated with the particular chat or project <- chat/project name + timestamp + all in one folder might be more easy to implement since the idea of Lumo can't create folders in Proton Drive.

   Anyways. Idea is that, the the advantages of screenshots done by proton for 100% privacy, no microsoft or apple or google or whatever log, and of course the idea is that if it's saved on proton drive via Lumo chat, Lumo can associate the image with specific information.

   As in image memory. In the memory function to have a "files xyz" - has the following information

   like this, if we just mention that information, it will trigger Lumo to check the image related information to search for that information and tell use which file is the one having that information. Or reverse, i want to check something, it's regarding case A, B, and C, can you also check image memories? And then lumo will check the images as say what information it has regarding A B and C <- Aka insted of checking hundrends of documents, insted of creating documents, insted of doing web search, you simple do a screenshot and well that is all the info you need. And it's instant and more.

   so again, what i suggest is not the same as the other suggestion that have been made, aka it's not a duplicate.

   But it's screenshots that are done and stored via Proton Drive (i mean it already has docs and sheets, why not screenshot on top?) with the purpose of it being for them to be directly added to chat's with Lumo as in: Lumo can add meaning to the pictures, direct and clear. No confusion. Anything irrelevant can be filtered out while also allow to unfiltered if there are relevant information ALL while giving the advantages of screenshot (quick, instantly, no create folder, no name file, nothing, it's simple and fast and most of all, efficient QoL)

   WARNING: what i am suggesting does exist if you use "change destination" of the screenshot program you use to save the images in a Proton Drive folder that will upload the pictures and so on. So please understand that what i will suggest is actually MORE then this and it's DIRECTLY linked to Lumo. AKA no, this is NOT a proton Drive suggestion => NO this is NOT a duplicate of existing suggestion exactly because i am suggesting MORE.

   That is also why:
   I will NOT explain in details why it's needed because it's absurd to assume that you even… more

   5 votes

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  New feature  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

6. Native file generation and download in Lumo (return edited project files as a ZIP)

   As an amateur developer working on Android apps with Visual Studio, I currently rely on ChatGPT for my coding workflow. I upload my entire project folder as a ZIP, describe the changes I need, and the AI corrects the files directly and sends them back to me as a downloadable ZIP. This automated loop is essential for me as a hobbyist who doesn't have the time or patience to manually copy-paste code into dozens of files.

   I would love to switch to Lumo because of its privacy focus and non-US ownership, but the current limitation is a dealbreaker. Right now, I can upload files for analysis, but any corrections require me to manually copy-paste the code back into Visual Studio. For a small project with many files, this makes the workflow too slow and cumbersome for an amateur developer.

   Feature request:

   Allow Lumo to act as a code agent: accept a project ZIP, apply requested changes to the files internally, and return the corrected project as a downloadable ZIP archive.
   Alternatively, enable direct writing to a linked Proton Drive folder for a project, so the changes are saved automatically.
   

   Without this feature, Lumo is impractical for software development tasks involving multiple files. Implementing this would make Lumo the perfect privacy-respecting alternative for hobbyists and indie developers who want to avoid US-based AI services but still need efficient, automated coding assistance.

   As an amateur developer working on Android apps with Visual Studio, I currently rely on ChatGPT for my coding workflow. I upload my entire project folder as a ZIP, describe the changes I need, and the AI corrects the files directly and sends them back to me as a downloadable ZIP. This automated loop is essential for me as a hobbyist who doesn't have the time or patience to manually copy-paste code into dozens of files.

   I would love to switch to Lumo because of its privacy focus and non-US ownership, but the current limitation is a dealbreaker. Right now,… more

   3 votes

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  New feature  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

7. Transcript feature uncensored

   Currently i get censored when i am speaking for no reason <- me swearing is not "a reason" unless there is no free speak. Me swearing when someone is present, including a child, or someone who will get offended, are reason i fully understand that are real "a reason". But:

   Or what, what i am talking with Lumo needs to be censored in case someone read what i speak with an 100% privacy AI?

   And

   If this is not from Lumo, but our own device, then why do we have a function in the chat that might expose our talk? Aka not enough transparecy on this, and sadly this becomes more and more important as companies add more "monitoring what you do on the device" <- look up LG and such if you want an up to date version of what i mean......

   Now that i "addressed" tons of "arguments", i want to point out one thing. That argument is not really far fetched. On top of Lumo Trying to understand what we say, especially if we have issues with pronouncing, then it's even more difficult to be clear. And the issue is that Lumo needs to further check everything if it's slur, swearing, or more.

   This means: Run through ALLLLL of the information in case it's a code, or slag, or different expression or language

   This also means that it might "flag" something. And this is an issue. After all, if it flags something, does this not add even further to background thinking that is used for other matters because, as the argument said, aka, who are we "minding our manners" for?

   Also i want to highlight, i was told many times that the whole "don't" and "no" and even "avoid" are stuff ais don't understand well.

   this means that Lumo is actively needing to censor whatever it's thinking, removing "bad words" or "adding " around the terms" so that it can think about....

   So

   again

   I ask something: Lumo censorese what i said. Rephases what i said. Removes pieces. And then it finally has the full picture? No, this is NOT what i am talking about.

   I am talking about the fact that as a program, before Lumo is even thinking, it already has parcially censored, removed, version, that NO thinking was used.

   Exemple

   ****** dsfdnsfo **** fdaslknsgfmowern

   are causing issues for Lumo to understand what it is.

   And those ***** is the terms that got censored.

   Without any thinking, no reasoning, nothing.

   so the end message is not a complete on, but fragmented.

   Also when Lumo writes the whole thing it actually finally understand everything because the whole idea was that it summary and filled out details itself.

   Did you know the term ********? Because this is the BEST to use with ais.

   1st: you make it clear you are asking it to NOT be ********.

   Aka you are not telling or labelling that it's ******** but that it behaves like one.

   And the fun part? when you ask the AI what ******** means in this context.

   you will see that it will not answer no matter what.

   And constantly output the same BS.

   Example: "a person"

   Why would an AI talk about a person when you asked it, the ai, to not be ********? <- REMINDER, THIS IS ME GIVING AN EXAMPLE OF WHAT I DO WITH ALL OF THE AIs.

   and after struggling a lot, finally it understand that you are not talking about any person.

   But about it (the ai)'s behaviour.

   And the "level of output" due to it's own behaviour (lack of thinking and understanding)

   And also, within reasons since i hope you understand you being "non thinking" will never recreate what i am talking about..... so, also, then you address the elephant in the room:

   Who is it offensive to?

   After all, legally, that term is not a valid any more. Even if it was at one point, now, when people use the term, is 100% not used as a way to say that someone is clinically low IQ or similar. On the contrary, it's them pointing out that what they said, think, do, and react does not meet with something, someone who thinks, would meet. As such, why is it an insult that we point out to other people that you need to stop being offended when you have failed to think?

   BTW, i am still talking about AIs, i know what i said is true in many cases but i hope everyone understand we are on Lumo suggestion and what i wrote is just me using people vs people as example to make it clear why i am suggestion an uncensored version

   Currently i get censored when i am speaking for no reason <- me swearing is not "a reason" unless there is no free speak. Me swearing when someone is present, including a child, or someone who will get offended, are reason i fully understand that are real "a reason". But:

   Or what, what i am talking with Lumo needs to be censored in case someone read what i speak with an 100% privacy AI?

   And

   If this is not from Lumo, but our own device, then why do we have a function in the chat that might expose our talk?… more

   3 votes

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  New feature  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

8. Lumo Watchlist & Scheduled Monitoring – Client-Side Alerts for Topic Tracking

   Hi Proton Team,

   I'm a long-time Proton user who relies heavily on GrapheneOS + Lumo as part of a de-Googled mobile workflow. I love that Lumo 2.0 now has private web search and persistent memory — these features make it an incredibly powerful tool for privacy-conscious professionals.

   That said, there's one gap between what Lumo offers today and what would make it a true competitor to mainstream AI assistants with automation capabilities: the inability to set up proactive, scheduled monitoring of topics or changes.

   Currently, if I want to track whether something new has been published about a specific topic (e.g., "Motorola GrapheneOS partnership"), I have to manually initiate a web search each time. This is inefficient and easy to forget. Other AI platforms offer background task scheduling or keyword monitoring, but often at the cost of privacy (they track your interests server-side).

   Proposed Solution
   Enable user-defined scheduled monitoring tasks within the Lumo client (mobile/web app). The concept would work entirely client-side:

   Create a Watchlist Entry — user specifies:

   Query/topic to monitor (e.g., "GrapheneOS Motorola news")
   Frequency (hourly, daily, weekly, custom cron-like interval)
   Comparison criteria (new results only, significant change detected, etc.)
   Alert method (in-app notification, email via Proton Mail)
   Client-Side Execution — the scheduling happens locally on the user's device. Lumo periodically performs web_search autonomously, compares results with baseline state stored locally, and surfaces differences.

   Privacy Preservation — no server-side logging of watchlists or tracking history. Everything encrypted end-to-end where applicable, with zero-access architecture maintained. Optional opt-in for syncing watchlists across devices via encrypted storage.

   Integration with Existing Features — leverage Lumo 2.0's Persistent Memory to remember previous search baselines. Leverage Private Web Search to avoid external data leaks during queries.

   Use Cases
   Journalists/Researchers: Track breaking developments on stories of interest without revealing query patterns.
   Enterprise IT Security: Monitor threat intelligence feeds or vulnerability disclosures relevant to organization infrastructure.
   Legal/Compliance Teams: Watch regulatory updates on specific topics without internal logs revealing sensitive priorities.
   Consumers: Track product releases, policy changes, or service updates privately (like the Motorola-GrapheneOS-Proton scenario we've been discussing).

   Implementation Considerations (Technical Notes)
   Since Proton already supports zero-access encryption, client-side processing, and encrypted sync across devices, most infrastructure pieces may already exist:

   Scheduling: Could run as background task using native OS scheduler (not Lumo server polling)
   Baseline Storage: Local SQLite/IndexedDB with encrypted snapshot of last-known-good state
   Comparison Logic: Simple diff algorithm comparing search result hashes or keywords
   Notifications: Push notifications via standard platform channels (no server involvement beyond delivery trigger)
   Cross-device Sync: Optional, encrypted via Proton's existing key management system
   Key constraint: Do NOT store watchlist definitions on Proton servers unless explicitly encrypted by client (E2EE), and ensure no metadata leakage occurs.

   Why Now?
   With Lumo 2.0 launching on June 30, 2026, featuring image generation, persistent memory, and private web search, the foundation is essentially ready. Adding scheduled monitoring would naturally extend Lumo's unique value proposition as the only AI assistant that doesn't require compromising privacy for automation.

   This feature would differentiate Lumo dramatically from ChatGPT, Claude, Gemini, and Copilot — all of which either track user activity server-side or lack sophisticated background task capabilities.

   Hi Proton Team,

   I'm a long-time Proton user who relies heavily on GrapheneOS + Lumo as part of a de-Googled mobile workflow. I love that Lumo 2.0 now has private web search and persistent memory — these features make it an incredibly powerful tool for privacy-conscious professionals.

   That said, there's one gap between what Lumo offers today and what would make it a true competitor to mainstream AI assistants with automation capabilities: the inability to set up proactive, scheduled monitoring of topics or changes.

   Currently, if I want to track whether something new has been published about a specific topic… more

   5 votes

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  New feature  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

9. Desktop app and Lumo feedback connection to Proton Devs and Support

   First, Lumo pointed out that maybe having a desktop app, just like all the other apps that Proton offers, is beneficial for our needs, and maybe for others.

   Second, It would be nice if Lumo can send Dev Team feedback messages and get support for people. The latter especially helpful with non-technical people trying to explain a technical issue.

   3 votes

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  New feature  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

10. Import chat history from other LLM

    Please allow us to import chat history from other big commercial cloud hosted LLMs to ease transition and not lose all the information prior LLMs gleaned from us, what we are doing, what is important to us, etc.

    20 votes

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    2 comments  ·  New feature  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

11. Automatically save chat responses to a document

    In my view, Lumo 2.0 should prioritize its core strengths—leveraging the scientific and technical expertise behind Proton's mission—rather than focusing heavily on image generation. Image creation requires significant financial investment, and many established competitors already serve this market extensively. While I understand there may be legitimate privacy concerns around processing images, it seems the choice to pursue image generation was driven by market trends in AI rather than staying true to the scientific and educational purpose for which Proton was originally founded. My suggestion would be to refocus development resources toward those foundational goals where Proton has unique value and differentiation. For example;

    Background:
    I am deciding at this time who to invest my time, information and money for ai services. I see the benefits of Claude and its ability of Coworker.
    What’s my issue.
    I want to use Lumo for my personal & business for knowledge management with Projects and Drive integration. Currently:
    index works beautifully, but saving responses requires manual copy/paste/upload.

    Requested Feature:
    Automatically save chat responses to a documents name it and to assign to Project folder I’m working in, into the Proton Drive,
    then index those files for future context retrieval without loading full conversation history.

    Thank you for your Suite, I have subscribed for mainly the vpn but have unlimited subscription. I don’t use extensively because the offering is still a bit raw. No sheet app for example or document app. So just waiting.

    Please keep advancing.

    All the best
    Andy

    In my view, Lumo 2.0 should prioritize its core strengths—leveraging the scientific and technical expertise behind Proton's mission—rather than focusing heavily on image generation. Image creation requires significant financial investment, and many established competitors already serve this market extensively. While I understand there may be legitimate privacy concerns around processing images, it seems the choice to pursue image generation was driven by market trends in AI rather than staying true to the scientific and educational purpose for which Proton was originally founded. My suggestion would be to refocus development resources toward those foundational goals where Proton has unique value and… more

    5 votes

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    0 comments  ·  New feature  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

12. Language correction button for Lumo with categories

    Add a "Report Language Error" button in the Lumo chat interface that lets users flag language issues directly. After clicking, users choose a category:

    Strict — Pure nonsense/incorrect term. Generates a corrected, academically accurate response.

    Synonym — Suggest an alternative word/phrase and context where it fits better. Helps Lumo understand nuance, register and topic-specific synonyms.

    Humoristic — Witty alternatives and wordplay. Helps Lumo learn humor and puns in the local language (especially useful for users with a "Casual/Cheeky" Lumo personality).

    This feeds into Proton's language improvement pipeline, helping Lumo and Scribe produce more natural, localized output — especially for smaller languages like Norwegian, Danish, Swedish and Finish.

    Use case: When Lumo says "hundkur" instead of "hundkoja," the user flags it as Strict. When Lumo misses a pun opportunity, the user flags it as Humoristic — and Lumo gets funnier over time.

    Add a "Report Language Error" button in the Lumo chat interface that lets users flag language issues directly. After clicking, users choose a category:

    Strict — Pure nonsense/incorrect term. Generates a corrected, academically accurate response.

    Synonym — Suggest an alternative word/phrase and context where it fits better. Helps Lumo understand nuance, register and topic-specific synonyms.

    Humoristic — Witty alternatives and wordplay. Helps Lumo learn humor and puns in the local language (especially useful for users with a "Casual/Cheeky" Lumo personality).

    This feeds into Proton's language improvement pipeline, helping Lumo and Scribe produce more natural, localized output — especially for smaller… more

    5 votes

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    0 comments  ·  New feature  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

13. lumo extended files

    Subject: Lumo Feature Request: Support for .nix, .zip, and .tar.gz files 🚀Hi Proton Team! 💜First of all, thank you for building such amazing, privacy-focused tools. Lumo looks great and works incredibly well!I would love to share a small feature request that would highly benefit technical users like myself. It would be amazing if Lumo could natively view and handle the following formats:.nix configuration files.zip folders and archives.tar.gz archivesAdding support for these formats would make checking files much faster, eliminating the need to download or move them to external apps just to see what is inside.Thank you so much for your hard work and continuous improvements. Keep up the fantastic job!Best regards,c

    Subject: Lumo Feature Request: Support for .nix, .zip, and .tar.gz files 🚀Hi Proton Team! 💜First of all, thank you for building such amazing, privacy-focused tools. Lumo looks great and works incredibly well!I would love to share a small feature request that would highly benefit technical users like myself. It would be amazing if Lumo could natively view and handle the following formats:.nix configuration files.zip folders and archives.tar.gz archivesAdding support for these formats would make checking files much faster, eliminating the need to download or move them to external apps just to see what is inside.Thank you so much for your… more

    5 votes

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    0 comments  ·  New feature  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

14. Native Mermaid diagram rendering in Lumo chat interface

    Description:

    Mermaid.ai is the de facto standard for text-to-diagram visualization, natively supported by GitHub, GitLab, Notion, Obsidian, and VS Code. Currently, when Lumo generates Mermaid syntax in a fenced ```mermaid code block, the Lumo web UI displays it as raw text instead of rendering the diagram visually. This significantly reduces the utility of Lumo for technical users who rely on diagrams — flowcharts, sequence diagrams, architecture diagrams, state machines, ER diagrams, and more.

    Proposed implementation:

    Integrate the Mermaid.js library into the Lumo web UI Markdown renderer to automatically detect and render ```mermaid fenced code blocks as interactive SVG diagrams within chat messages.
    Support the full range of Mermaid diagram types (flowchart, sequence, class, state, ER, Gantt, journey, timeline, mindmap, gitGraph, etc.).
    Ensure rendering occurs client-side to maintain Lumo's zero-access encryption and privacy-first architecture.
    Consider a fallback: if rendering fails, display the raw Mermaid source with a copy button.
    Extend support to the iOS and Android apps where feasible.

    Why this matters:

    Lumo already generates Mermaid syntax in responses — the gap is purely in rendering.
    Competing AI assistants (Claude, ChatGPT, Gemini) render Mermaid natively.
    The Mermaid.js library is lightweight, MIT-licensed, and runs entirely in the browser.
    Privacy is preserved: no server-side diagram generation is required.
    Technical professionals (developers, architects, IAM consultants) represent a key Lumo Plus subscriber demographic that depends heavily on visual documentation.
    Related existing requests:

    Syntax-highlighted code blocks (18 votes on UserVoice) — Mermaid rendering would naturally complement this feature.

    Description:

    Mermaid.ai is the de facto standard for text-to-diagram visualization, natively supported by GitHub, GitLab, Notion, Obsidian, and VS Code. Currently, when Lumo generates Mermaid syntax in a fenced ```mermaid code block, the Lumo web UI displays it as raw text instead of rendering the diagram visually. This significantly reduces the utility of Lumo for technical users who rely on diagrams — flowcharts, sequence diagrams, architecture diagrams, state machines, ER diagrams, and more.

    Proposed implementation:

    Integrate the Mermaid.js library into the Lumo web UI Markdown renderer to automatically detect and render ```mermaid fenced code blocks as interactive SVG diagrams within… more

    4 votes

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    0 comments  ·  New feature  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

15. Paid Chat Preservation - Automatic Freeze/Backup Instead of Deletion

    Current Behavior:
    After subscription expiry, all chat history is deleted 7 days later. There is no chat backup functionality currently available.

    Why Manual Backups Fall Short:
    Relying on users to manually export or back up chats defeats the purpose of a seamless subscription model. Manual backups are reactive and easy to forget - automatic preservation should be the default expectation for paid users.

    Proposed Solutions:
    1. Freeze/Hide Logic (Lumo 1.x style): When subscription ends, chats become read-only or hidden rather than deleted
    2. Automatic Drive Integration: Proton Drive auto-backups for chat history at regular intervals
    3. Grace Period Extension: Longer retention window during subscription pauses

    Use Case:
    I want flexibility to pause Lumo temporarily without losing months of conversation history. Deleting chats after 7 days creates a "pay-to-win" dynamic where continuous payment becomes mandatory to retain data.

    Impact on Paid Customers:
    This policy punishes legitimate usage patterns (seasonal use, budget cycles, trial periods). A better approach would preserve data integrity while allowing subscription flexibility.

    Current Behavior:
    After subscription expiry, all chat history is deleted 7 days later. There is no chat backup functionality currently available.

    Why Manual Backups Fall Short:
    Relying on users to manually export or back up chats defeats the purpose of a seamless subscription model. Manual backups are reactive and easy to forget - automatic preservation should be the default expectation for paid users.

    Proposed Solutions:
    1. Freeze/Hide Logic (Lumo 1.x style): When subscription ends, chats become read-only or hidden rather than deleted
    2. Automatic Drive Integration: Proton Drive auto-backups for chat history at regular intervals
    3. Grace Period Extension: Longer… more

    4 votes

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    0 comments  ·  New feature  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

16. Dark app icon for Lumo

    All the other Proton apps have an icon for light and dark mode. I think it would be great to have a dark icon for Lumo since it only has a light icon.

    28 votes

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    2 comments  ·  New feature  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

17. Support AGENTS.md or similar global configuration file for automatic context

    Allow users to define a markdown file (e.g., AGENTS.md) that Lumo reads automatically at session start, providing global context like tech stack, coding standards, infrastructure constraints, and behavioral rules. This would:
    - Eliminate repetitive manual context-pasting per session
    - Work across all conversations (not project-scoped)
    - Support version-controlled configuration (Git repos)
    - Align with emerging AGENTS.md standard used by other AI tools (Junie AI, GitHub Copilot, Aider, Gemini CLI)

    Free-tier compatible since it doesn't require persistent storage — just file parsing at session start. File could be stored on Proton Drive.

    4 votes

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    0 comments  ·  New feature  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

18. Make chats downloadable for personal archiving

    Why are Lumo chats not downloadable? This is most cumbersome in 2026. While chats are ostensibly saved with a Lumo account, they are subjected to being abridged (for "lengthy" chats) and totally unavailable without internet. So what is the deal? Is it a Proton encryption thing or have you just not gotten around to it or what?

    4 votes

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    0 comments  ·  New feature  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

19. Creation of Lumo Browser Extension

    As a leading privacy AI, it's important that the chatbot can interact with our daily lives safely and privately. The addition of a browser extension for Lumo to interact with your screen would greatly benefit the greater Proton community.

    18 votes

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    1 comment  ·  New feature  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

20. Heptic feedback vibration for when Lumo finishes answering and during stages of processing a question

    I use Lumo a lot throughout the day while I'm on the go and often times when I post a question it takes about 10 to 20 seconds for me to get an answer back. I would like to be able to just hit the submit button and then take my eyes off my phone while Lumo is giving the answer and then for my phone to buzz when the answer is ready to be read.

    I would also like some feedback in the app while Proton is processing my answer. It would be good to just feel Proton thinking. For example, if it decides to do a web search, it would be cool if that had a vibration pattern. And then if it conducts a web search, for each web search conducted, it would be cool if that was another vibration pattern. And if it is, you know, synthesizing information or deciding not to do a web search, that would also be kind of interesting. It would be nice to just, like, get to "know" Lumo in this way.

    I use Lumo a lot throughout the day while I'm on the go and often times when I post a question it takes about 10 to 20 seconds for me to get an answer back. I would like to be able to just hit the submit button and then take my eyes off my phone while Lumo is giving the answer and then for my phone to buzz when the answer is ready to be read.

    I would also like some feedback in the app while Proton is processing my answer. It would be good to just feel Proton thinking.… more

    2 votes

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    0 comments  ·  New feature  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating