595 results found

1. I want to be able to use Lumo using the latest Firefox Extended Support Release (ESR) version

   I want to be able to use Lumo using the latest Firefox Extended Support Release (ESR) version, so that I can continue to use Lumo on my company notebook that does not support other browser brands.

   Since yesterday (1 Nov 2025) I receive a message that says "Unsupported browser". There has been no communications to inform us that the Firefox Extended Support Release (ESR) version will no longer be supported. Our browser version is fully up-to-date, at the time of writing it is 115.29.0 Firefox ESR October 14, 2025 and no newer version of Firefox ESR has been released at this point.

   Therefore we urgently request this browser to be supported, in conformity with what has also been stated in the following page, where it is explicitly mentioned that Firefox is supported and even recommended:

   https://proton.me/support/recommended-browsers

   Please act with urgency! Thank you.

   I want to be able to use Lumo using the latest Firefox Extended Support Release (ESR) version, so that I can continue to use Lumo on my company notebook that does not support other browser brands.

   Since yesterday (1 Nov 2025) I receive a message that says "Unsupported browser". There has been no communications to inform us that the Firefox Extended Support Release (ESR) version will no longer be supported. Our browser version is fully up-to-date, at the time of writing it is 115.29.0 Firefox ESR October 14, 2025 and no newer version of Firefox ESR has been released at… 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  ·  Changes to existing features  ·  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. Custom shortcut/alias/abbreviation for a frequently used queries/prompts

   It happens that your Lumo question is long and used repeatedly while minor part of the question is variable. For example:
   Translate "string here" to spanish.

   Instead of needing to always write this sentence, i would like to setup custom shortcut, for example:
   t2sp paste here the phrase i would like to translate to spanish

   There would have to be some page, where i can manage all shortcuts (search/filter, sort). And it should not require learning/remembering any complicated syntax. Intuitive, layman friendly.

   ---

   Similar feature request: https://protonmail.uservoice.com/forums/932842-lumo/suggestions/50578022-lumo-system-prompt

   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

3. Lumo system prompt

   When I ask Lumo for help, I have to always give instructions how it should respond, otherwise it may generate an undesired huge response for rather simple questions. Having an ability to predefine a system prompt to influence this behaviour is in my opinion a required feature. This feature could be also expanded to have several system prompts to choose from at the beginning of a conversation.

   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. Lumo Companion

   Lumo Companion, virtual Girlfriend or Boyfriend. I like lumo and everything it stands for, but for $9.99 a month(with annual sub) I will like the option to have a virtual companion.

   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

   118 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. Security

   Changes to all existing idieas replace with a save and more secure one

   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  ·  Changes to existing features  ·  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. Last Day of Month Events

   Recurring events on calendar - ability to choose the last day of the month. I tried choosing the 31st of the month, but on days that don't have 31 days, the event just disappeared, rather than adjusting to the last day.

   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

   3 comments  ·  Changes to existing features  ·  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. Keep Lumo's Proton documentation index synchronised with product announcements

   Problem: Lumo's documentation lookup had no record of a major Proton Pass feature (AI Access Tokens) roughly four months after launch, despite it being documented on Proton's own support site.

   Requested feature: A regular sync pipeline between product announcement/support documentation and the documentation lookup Lumo uses, so newly shipped features are answerable on day one rather than discovered only via manual web search.

   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  ·  Changes to existing features  ·  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. Automatic web-search fallback for Proton product questions

   Problem: When a question about Proton products/features finds no results via Lumo's Proton documentation lookup, Lumo currently concludes the feature doesn't exist — sometimes confidently warning users it may be a scam. In my case, Lumo denied Proton Pass AI Access Tokens (a real, shipped feature announced May 2026) and suggested I'd encountered phishing, because the docs index hadn't caught up with the announcement. Live web search quickly corrected this, but only because it happened to be used.

   Requested feature: When the Proton documentation tool returns no results for a product question, Lumo should automatically fall back to web search before answering, rather than treating "not in the index" as "doesn't exist." This matters for user trust: the assistant contradicting Proton's own documentation undermines confidence in using it for Proton questions at all.

   Problem: When a question about Proton products/features finds no results via Lumo's Proton documentation lookup, Lumo currently concludes the feature doesn't exist — sometimes confidently warning users it may be a scam. In my case, Lumo denied Proton Pass AI Access Tokens (a real, shipped feature announced May 2026) and suggested I'd encountered phishing, because the docs index hadn't caught up with the announcement. Live web search quickly corrected this, but only because it happened to be used.

   Requested feature: When the Proton documentation tool returns no results for a product question, Lumo should automatically fall back to web search… 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

9. Proposal: Include Lumo Plus for free with Proton Unlimited subscriptions or 50% discount

   Dear Proton Team,

   First of all, thank you for building such a strong privacy-first ecosystem. As a paying Proton Unlimited subscriber, I genuinely value the work you do, and my subscription feels like an investment in a company whose mission I believe in.

   With that in mind, I would like to propose a change to the Unlimited plan that I believe would strengthen loyalty among your paying customers and differentiate the bundle even further:

   Proposal: Include Lumo Plus at no extra cost for Proton Unlimited subscribers or give 50% discount for paid users. And, not for yearly payments, but also for monthly pay.

   The reasoning:

   Rewarding loyalty. Paying Unlimited members are the backbone of Proton's sustainability. Unlike free users, we directly fund the infrastructure, development, and innovation that keep Proton running. Extending Lumo Plus to us would feel like a meaningful acknowledgment of that contribution.
   Stronger bundle value. Unlimited already bundles Mail, VPN, Drive, and Pass. Adding Lumo Plus would make the bundle even more competitive against Big Tech ecosystems (Google One, Microsoft 365, Apple One) that increasingly bundle AI features at no extra charge.
   Alignment with Proton's mission. Lumo is promoted as a privacy-first AI assistant. Making it a core part of the paid privacy ecosystem would reinforce the message that privacy tools belong everywhere — including AI — not just in email and VPN.
   Likely minimal revenue impact. Many Unlimited subscribers currently use Lumo Free. The users who would benefit most from this change are existing loyal customers, not heavy AI power users who would already be paying for Lumo Plus. In practice, this mostly transfers value back to the people funding Proton.

   Kind regards,

   a 5 years Proton Unlimited user

   Dear Proton Team,

   First of all, thank you for building such a strong privacy-first ecosystem. As a paying Proton Unlimited subscriber, I genuinely value the work you do, and my subscription feels like an investment in a company whose mission I believe in.

   With that in mind, I would like to propose a change to the Unlimited plan that I believe would strengthen loyalty among your paying customers and differentiate the bundle even further:

   Proposal: Include Lumo Plus at no extra cost for Proton Unlimited subscribers or give 50% discount for paid users. And, not for yearly payments, but also… 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  ·  Changes to existing features  ·  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. Multi-user Reservation page

    Idea on Proton Calendar to be able to get completely rid of Calendly = a multi-user reservation page, offering the ability to create a link to be sent to external user to book a meeting on the shared availbilities of several users of one company using Proton.

    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

11. How Do You Approach Law Coursework?

    https://writemycoursework.co.uk/law may sometimes prove to be tough since it requires a lot of legal research, case studies, law, and referencing. I would like to know which aspects of LLB coursework help UK prove to be difficult for other law students. Is it sourcing information, applying legal principles, IRAC, or something else?

    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

12. Title: Per-conversation memory control: "New Private Chat" option + memory containers

    Hi Proton Team,

    Memory shipped with Lumo v2.0, and it's a genuinely useful feature — but right now the only control is a global on/off toggle. I'd like to suggest finer-grained control, in two parts.

    Part 1. "New Private Chat"

    A conversation with no memory loaded in, and no memory saved out. Like a browser private window: fully functional, nothing retained afterwards. Your existing memory stays intact for all your other chats — this session simply doesn't participate.

    Visual indicators:

    In the sidebar: a small icon (lock, or similar) next to the conversation title — left side for LTR languages, right side for RTL
    In the active chat: a small badge on the existing header bar — no new persistent bar, so no screen space lost
    Icon paired with text, so it doesn't rely on colour alone (accessibility)

    Part 2. Memory "containers"

    Separate compartments (work, personal, etc.) that don't bleed into each other:

    Each container holds its own memory context
    A conversation only draws from its assigned container
    "Private chat" is effectively a container with no memory at all — nothing in, nothing out
    This serves two groups currently pulling in different directions:

    Users who want memory get organised, compartmentalised context instead of one blended pool
    Users who are wary of quiet accumulation get a deliberate, reviewable way to use memory — or none at all
    It would turn the current all-or-nothing toggle into genuine user control: stateless by default for those who prefer that, compartmentalised memory for those who don't.

    The browser-container concept is familiar, so it needs almost no explanation — and it aligns with Proton's privacy-first values: the user decides what's on the record and what isn't.

    Thanks for reading!

    Hi Proton Team,

    Memory shipped with Lumo v2.0, and it's a genuinely useful feature — but right now the only control is a global on/off toggle. I'd like to suggest finer-grained control, in two parts.

    Part 1. "New Private Chat"

    A conversation with no memory loaded in, and no memory saved out. Like a browser private window: fully functional, nothing retained afterwards. Your existing memory stays intact for all your other chats — this session simply doesn't participate.

    Visual indicators:

    In the sidebar: a small icon (lock, or similar) next to the conversation title — left side for LTR languages,… 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

13. Drag calendar event and reschedule by 15-minute increments instead of 30min

    Drag calendar events and reschedule by 15-minute increments instead of 30min

    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  ·  Changes to existing features  ·  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. Preview Images in Project Knowledge Before Deleting – Show Thumbnails or Click-to-Open

    Currently, when viewing files in the "Project Knowledge" section, images are displayed only as generic icons with filenames (e.g., IMG_9630.png). There is no way to preview the actual image content before deciding to delete it. This creates a significant risk of accidentally deleting the wrong image, especially when managing multiple uploads with similar or non-descriptive filenames.

    I request a preview feature for images in the Project Knowledge panel with the following specifics:

    • Thumbnails: Display small thumbnail previews of the images instead of just generic icons so users can instantly identify the content.
    • Click-to-Open: Allow users to tap or click an image to open a larger preview window before confirming any action.
    • Confirmation Dialog: When clicking the delete (X) button on an image, show a confirmation popup where the image preview is clearly visible, asking "Are you sure you want to delete this specific image?"

    Why this matters: For users who upload many reference images (photos, diagrams, screenshots) to guide Lumo's responses, being able to visually verify content before deletion is critical. It prevents accidental data loss and improves confidence when managing project context. This is a basic usability standard seen in most file management systems (like Photos or Drive) and should apply here too.

    Currently, when viewing files in the "Project Knowledge" section, images are displayed only as generic icons with filenames (e.g., IMG_9630.png). There is no way to preview the actual image content before deciding to delete it. This creates a significant risk of accidentally deleting the wrong image, especially when managing multiple uploads with similar or non-descriptive filenames.

    I request a preview feature for images in the Project Knowledge panel with the following specifics:

    • Thumbnails: Display small thumbnail previews of the images instead of just generic icons so users can instantly identify the content.
    • Click-to-Open: Allow users to tap or click an… 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  ·  Changes to existing features  ·  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. Anthropic Claude and Google Gemini Import

    Visionary user here switching from Anthropic Claude and Google Gemini to Proton Lumo Max I'd like to have an option as a user to import my data and memory as easy as possible. Today a manual import usually exceeds the context of the chat and even with multiple chat's it's not possible to get all data into Lumo. So please Proton give us an option to import our data.

    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

16. Hide events from shared calendar

    When looking at a calendar that is shared with you, you may want to hide some events and event chains.

    We share calendars across our family, some like to put "work" or "commute" in there, I would like to hide those event chains without hiding their entire calendar.

    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

17. Integrated Notebook with Offline/Online Toggle & Nested Folder Structure

    Description: While existing requests cover "Offline Chat Access" and "Project Folders," I need a dedicated Integrated Notebook feature to permanently capture, organize, and secure specific insights extracted from our conversations. Currently, valuable information gets lost in endless scrolling or requires exporting to external tools.

    I request a native Notebook within Lumo with the following capabilities:

    1. Seamless Capture from Chat

    • Highlight any message or paragraph in a chat and instantly "Save to Notebook."

    • Saved notes become standalone, editable entries but retain a link back to the original conversation for context.

    1. User-Controlled Privacy (Offline vs. Online Toggle)

    • Crucial Feature: Users must be able to choose per note whether it is stored Offline-only (local device storage, zero-cloud access) or Online (synced across devices via Proton's secure infrastructure).

    • This allows for maximum privacy for sensitive data (health logs, personal journals) while keeping collaborative notes synced. Existing "Offline Chat" proposals do not offer this granular control per item.

    1. Robust Organization (Nested Folders)

    • Folder Structure: Create nested folders and subfolders (e.g., "Health > Silver", "Writing > Drafts", "Politics > Analysis").

    • Unlike simple project folders for chats, this allows for a hierarchical knowledge base where users can organize thoughts logically, not just chronologically.

    • Tags & Search: Add custom tags to notes and search across all notebooks instantly.

    Why this matters: This transforms Lumo from a transient chat tool into a permanent, structured, and private "second brain." The ability to toggle between offline and online storage ensures that users can keep their most sensitive data completely isolated on their device while still benefiting from cloud sync for less critical information. Combined with nested folder structures, this provides the organization power needed for complex, long-term projects without leaving the Proton ecosystem.

    Technical Feasibility: Leverages existing Proton local storage capabilities (similar to Proton Drive's offline mode) and integrates them directly into the chat UI, using the same encryption standards.

    Description: While existing requests cover "Offline Chat Access" and "Project Folders," I need a dedicated Integrated Notebook feature to permanently capture, organize, and secure specific insights extracted from our conversations. Currently, valuable information gets lost in endless scrolling or requires exporting to external tools.

    I request a native Notebook within Lumo with the following capabilities:

    1. Seamless Capture from Chat

    • Highlight any message or paragraph in a chat and instantly "Save to Notebook."

    • Saved notes become standalone, editable entries but retain a link back to the original conversation for context.

    1. User-Controlled Privacy (Offline vs. Online Toggle)

    • Crucial Feature: Users must be… 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

    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

18. Lumo AI-Powered Card Organization for Proton Drive & Brain

    Enable Lumo AI to automatically organize, tag, and summarize saved cards in Proton Brain/Drive—zero-knowledge semantic search and connection discovery.

    BACKGROUND:
    This complements the "Proton Brain" feature request (UI focus). This one focuses on the intelligence layer that makes the system actually useful.

    CURRENT STATE:
    Users manually tag, categorize, and link notes. This is tedious and rarely done consistently. MyMind solves this with AI but sacrifices privacy.

    REQUESTED CAPABILITIES:
    1. Automatic Card Enrichment (Opt-In):
    - On save: Lumo generates summary (TL;DR, max 3 sentences)
    - Auto-tags extraction (3-7 relevant tags per card)
    - Entity recognition (people, places, topics mentioned)
    - Language detection + multilingual support

    1. Semantic Search:

       • Natural language queries across all cards
       • Example: "What did I save about GDPR compliance last year?"
       • Finds cards even if exact keywords aren't present
       • Results ranked by relevance, not just keyword match

    2. Connection Discovery:

       • Lumo suggests related cards ("You also saved X about this topic")
       • Suggests bidirectional links between notes
       • Identifies recurring themes over time
       • "Weekly Insights" digest of connected topics

    3. Smart Spaces (Auto-Organization):

       • Lumo proposes Spaces based on content clusters
       • Example: "I noticed 12 cards about 'Privacy Legislation'—create Space?"
       • Manual override allowed; never forced
       • Nested Spaces supported (Projects → Subprojects)

    4. Card Actions via Lumo:

       • "Summarize this collection of 20 cards"
       • "Find all cards mentioning [person/topic]"
       • "Generate outline from these research notes"
       • "Convert these meeting notes into action items"

    5. Privacy Architecture (Critical):

       • All indexing/search happens client-side OR in trusted execution environment
       • Server never sees decrypted content
       • Opt-in only (disabled by default for new users)
       • No model training on user data (explicit policy)
       • Delete any card → instant removal from index

    TECHNICAL IMPLEMENTATION PATH:
    Phase 1 (6 months): Server-side inference with encrypted payloads (MVP)
    Phase 2 (12 months): Hybrid model with client-side lightweight inference
    Phase 3 (18 months): Full zero-knowledge semantic search with TEE

    COMPETITIVE DIFFERENTIATORS:
    - Notion: AI but zero privacy guarantees
    - MyMind: AI but opaque encryption practices
    - Obsidian: Privacy but no native AI
    - Proton Brain: BOTH privacy AND intelligence

    VALUE PROPOSITION:
    Power users get AI-powered organization without becoming AI companies' training data. Journalists, lawyers, researchers, and activists finally have a PKM tool they can trust with sensitive information.

    PRICING RECOMMENDATION:
    - Lumo Plus required for AI features (justifies premium tier)
    - Free tier: Manual tags only, 10 AI summaries/month
    - Visionary: Unlimited AI processing included

    LINK TO RELATED:
    See also: https://protonmail.uservoice.com/forums/932839-proton-drive/suggestions/51632422-proton-brain-zero-knowledge-second-brain-with-car

    Enable Lumo AI to automatically organize, tag, and summarize saved cards in Proton Brain/Drive—zero-knowledge semantic search and connection discovery.

    BACKGROUND:
    This complements the "Proton Brain" feature request (UI focus). This one focuses on the intelligence layer that makes the system actually useful.

    CURRENT STATE:
    Users manually tag, categorize, and link notes. This is tedious and rarely done consistently. MyMind solves this with AI but sacrifices privacy.

    REQUESTED CAPABILITIES:
    1. Automatic Card Enrichment (Opt-In):
    - On save: Lumo generates summary (TL;DR, max 3 sentences)
    - Auto-tags extraction (3-7 relevant tags per card)
    - Entity recognition (people, places, topics mentioned)
    - Language… 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  ·  Changes to existing features  ·  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. Idea: What if Lumo used on-device processing for heavy lifting?

    Here's a thought: what if Lumo tapped into Apple's on-device intelligence (Neural Engine on iPhones/MacBooks) to pre-process large files before sending them to the cloud?

    Right now, if you upload a big reference book — say, 12 MB — Lumo simply truncates it to 128K tokens. You lose most of the content before analysis even begins. That's frustrating.

    A hybrid approach could fix this: the device handles the first pass (chunking, summarizing, extracting key sections), then ships the compressed result to Lumo's servers for the deep work. Less server load, faster responses, and no more throwing away half your document.

    Yes, it'd need bigger token limits on the server side and some clever work to keep everything encrypted end-to-end — but the payoff is real. This kind of edge-cloud split is already gaining traction in the industry, and it feels like a natural.

    Something to think about.

    Here's a thought: what if Lumo tapped into Apple's on-device intelligence (Neural Engine on iPhones/MacBooks) to pre-process large files before sending them to the cloud?

    Right now, if you upload a big reference book — say, 12 MB — Lumo simply truncates it to 128K tokens. You lose most of the content before analysis even begins. That's frustrating.

    A hybrid approach could fix this: the device handles the first pass (chunking, summarizing, extracting key sections), then ships the compressed result to Lumo's servers for the deep work. Less server load, faster responses, and no more throwing away half your document.

    … 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

20. Cloud-Assisted Verification ("Draft Local, Verify Cloud")

    Here is my proposal which I think good to implement. (Note: I'm using LUMO itself to help me to produce a proposal based on my ideas)

    Problem: Small on-device models (7B–20B) are prone to hallucination on complex tasks — inventing facts, generating incorrect syntax, or producing logically inconsistent output. Pure local inference is risky for high-stakes work (configuration changes, security analysis, medical/legal information).

    Proposed Solution: A three-layer pipeline where local generation is verified by a cloud model — without exposing raw user data.

    Architecture — "Local Generation + Cloud Verification":

    Layer 1: Local Generation (Instant & Private)

    Input (prompt + files) stays on device
    Small, fast model generates a draft response in milliseconds
    Zero data leaves the device at this stage
    

    Layer 2: Web Search Augmentation (Optional, Lightweight)

    If current information is needed, anonymized web search fetches relevant text
    Results are fed into the local model to incorporate into the draft
    

    Layer 3: Cloud Verification (Selective)

    The generated output text only (not the raw input, not the user's files, not the conversation context) is sent to a large cloud model
    The cloud model acts as a "judge" — it checks:
        Fact-checking: Are claims accurate?
        Logic consistency: Did the model contradict itself?
        Hallucination detection: Is this command syntax real or fabricated?
    Returns a confidence score or a corrected version
    Only triggered for complex/high-stakes queries; skipped for simple tasks
    

    Final Delivery:

    Confidence > Threshold: Show local draft immediately with ✅ "Verified" badge
    Confidence < Threshold: Replace with cloud-corrected version or flag as ⚠️ "Unverified — Review Recommended"
    

    Trust Indicators (Transparent to User):

    🟢 Fully Verified — Generated locally + web-augmented + cloud-verified
    🟡 Web-Verified — Generated locally + web search (no cloud verification)
    🔵 Local Only — On-device only, offline mode, best-effort accuracy
    

    Real-World Example:

    User asks: "Generate a Cisco IOS config to block SSH from subnet 192.168.10.0/24"
    Local model generates: access-list 100 deny tcp 192.168.10.0 0.0.0.255 any eq 22
    Cloud verifier checks: ACL syntax is correct, but missing permit ip any any at the end (implicit deny-all would break connectivity)
    Final output: Corrected config with verification badge
    

    Data Privacy Guarantee:

    Raw files (configs, logs, documents): ❌ Never leave device
    Conversation context/history: ❌ Never leaves device
    Generated output text: ✅ Sent to cloud for verification (output is less sensitive than input)
    User can disable cloud verification entirely ("Fast & Private" mode)
    

    Review — Strengths:

    Solves the hallucination problem without surrendering privacy or driving up costs
    Cloud verification is exponentially cheaper than cloud generation (checking 500 words vs. generating 500 words)
    Proton pays for cloud compute only on the ~20% of queries that genuinely need it
    Enables a lower subscription tier (majority of work happens on user hardware)
    Separates sensitive inputs (stay local) from generated outputs (can be verified)
    Trust indicators give users transparency about response confidence — critical for professional use
    

    Review — Risks:

    Latency: Waiting for cloud verification could delay response display
        Solution: Display local draft immediately with "Verifying..." indicator; update asynchronously if corrections are found
    Bandwidth: Sending every response for verification adds network overhead
        Solution: Selective verification — only verify complex queries; skip simple tasks (greetings, formatting, simple summaries)
    Privacy of output: Even generated output could contain sensitive information
        Solution: User toggle to disable cloud verification entirely; clear trust indicators so users know when verification is active
    

    Feasibility: MEDIUM — The concept of using a large model to verify a smaller model's output is well-established in AI research. Implementation requires Proton to build the verification API endpoint and client-side routing logic.

    Here is my proposal which I think good to implement. (Note: I'm using LUMO itself to help me to produce a proposal based on my ideas)

    Problem: Small on-device models (7B–20B) are prone to hallucination on complex tasks — inventing facts, generating incorrect syntax, or producing logically inconsistent output. Pure local inference is risky for high-stakes work (configuration changes, security analysis, medical/legal information).

    Proposed Solution: A three-layer pipeline where local generation is verified by a cloud model — without exposing raw user data.

    Architecture — "Local Generation + Cloud Verification":

    Layer 1: Local Generation (Instant & Private)

    Input (prompt +

    … 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