617 results found

1. Add secure tool support to Lumo for file creation, previews, and integrations

   Dear Proton Community and Development Team,

   I would like to suggest expanding Lumo with secure tool support so it can become more useful for practical daily work.

   At the moment, an AI assistant is most valuable when it can not only answer questions, but also help users create, organize, preview, and export work in a controlled and privacy-respecting way.

   Suggested tool improvements:

   1. File creation and export
      Lumo should be able to create files such as text documents, tables, simple presentations, ZIP archives, or structured project files and offer them as downloads.

   2. Secure preview features
      Lumo could provide previews for generated content, such as simple web pages, layouts, documents, or structured outputs before the user downloads or applies them.

   3. Live Work inside Lumo
      Lumo should have just like any regular AI, an Canvas feature for example for live editing content or previewing work

   4. Project-style file context
      Users should be able to upload files or reference materials into a Lumo workspace so the assistant can work with them without requiring users to paste very long text manually.

   Why this matters:

   Many users need AI not only for chatting, but also for producing usable outputs. Secure file generation, previews, and optional integrations would make Lumo much more practical while still respecting Proton’s privacy-first approach.

   I understand that this requires careful security and permission handling, but I believe it is possible if implemented with clear user control, transparency, and Proton’s existing privacy standards.

   Thank you for considering this suggestion.

   Dear Proton Community and Development Team,

   I would like to suggest expanding Lumo with secure tool support so it can become more useful for practical daily work.

   At the moment, an AI assistant is most valuable when it can not only answer questions, but also help users create, organize, preview, and export work in a controlled and privacy-respecting way.

   Suggested tool improvements:

   1. File creation and export
      Lumo should be able to create files such as text documents, tables, simple presentations, ZIP archives, or structured project files and offer them as downloads.

   2. Secure preview features
      Lumo could provide previews for generated… 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

2. Improve Lumo’s UI/UX for a smoother, more responsive daily experience

   Dear Proton Community and Development Team,

   I would like to suggest improvements to Lumo’s user interface and overall user experience so that it feels smoother, more consistent, and better suited for daily use.

   Privacy and security are very important, and this is one of the main reasons why many users are interested in Proton products. However, for an AI assistant to become part of everyday work, it also needs to feel fast, polished, intuitive, and enjoyable to use.

   My request is specifically about improving the interaction design and visual consistency of Lumo.

   Suggested improvements:

   1. More responsive UI interactions
      Buttons, menus, input fields, and other interactive elements should provide clearer visual feedback when users hover, click, tap, open panels, or send messages.

   2. Smoother animations
      New messages, loading states, chat transitions, and opening or closing panels could feel more natural with subtle, polished animations.

   3. More consistent spacing, borders, and layout
      Some UI elements feel small or visually inconsistent. A more unified design system with consistent spacing, rounded corners, and clearer hierarchy would make Lumo feel more refined.

   4. More polished visual design
      A cleaner design language, possibly using soft rounded “squircle” shapes and subtle glass-like surfaces, could make the interface feel more modern while still remaining simple and professional. Dark and light modes are enough, but both should feel carefully designed and visually balanced.

   5. More personality in the Lumo brand elements
      The Lumo cat or logo could become slightly more interactive or reactive, for example during loading, idle states, or successful actions. This should remain subtle and professional, but it could make the product feel more alive and memorable.

   6. Better personalization inside Lumo
      It would be useful to allow users to upload files or reference material directly inside Lumo for personalization, similar to project-based workflows in other AI tools. This would reduce the need to paste very long texts manually.

   Why this matters:

   A secure AI assistant is valuable, but security alone is not enough for daily adoption. If the product feels too static, too small, or not responsive enough, users are less likely to use it regularly. A smoother and more consistent interface would make Lumo feel more mature, trustworthy, and pleasant to use.

   This request is not about adding unnecessary visual effects. It is about improving usability, consistency, responsiveness, and the overall feeling of quality.

   Thank you for considering this suggestion.

   Dear Proton Community and Development Team,

   I would like to suggest improvements to Lumo’s user interface and overall user experience so that it feels smoother, more consistent, and better suited for daily use.

   Privacy and security are very important, and this is one of the main reasons why many users are interested in Proton products. However, for an AI assistant to become part of everyday work, it also needs to feel fast, polished, intuitive, and enjoyable to use.

   My request is specifically about improving the interaction design and visual consistency of Lumo.

   Suggested improvements:

   1. More responsive UI interactions
      Buttons, menus,… 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

   1 comment  ·  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

3. Add capability allowing Lumo to package conversation, both prompts and responses, into a Proton doc file.

   Add capability allowing Lumo to package conversation, both prompts and responses, into a Proton doc file.

   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

4. Use better open-source ai models.

   Dear Proton Team,

   I would like to propose integrating several high-quality open-source AI models into the Lumo platform. These models align with Proton’s core values of privacy, transparency, and user data sovereignty, while offering excellent performance and flexibility.

   The recommended models include GPT-OSS 120B, LLaMA 3, DeepSeek-V3, Mistral 8x22B, and BLOOM. These models stand out because they are open source, enabling complete self-hosting and customization. This means Proton can maintain full control over user data, keeping all processing within secured European data centers, aligned with Proton’s zero-access policy and strong privacy commitments.

   GPT-OSS 120B offers powerful capabilities close to proprietary large models but without API dependency and high ongoing costs. LLaMA 3 is dialog-optimized and supports long context windows, enhancing user interaction experience. DeepSeek-V3 presents a highly efficient mixture-of-experts architecture with exceptional scaling potential. Mistral 8x22B balances performance and resource demands, fitting well with Proton’s infrastructure. BLOOM provides multi-language support and responsible open-source licensing, broadening Lumo’s global reach.

   By choosing these models, Proton can deliver a privacy-first, performant AI assistant that scales from edge devices to enterprise deployments, all under Proton’s full control. This approach boosts user trust, reduces dependency on third parties, and aligns with evolving global privacy regulations.

   Thank you for considering this proposal.

   Dear Proton Team,

   I would like to propose integrating several high-quality open-source AI models into the Lumo platform. These models align with Proton’s core values of privacy, transparency, and user data sovereignty, while offering excellent performance and flexibility.

   The recommended models include GPT-OSS 120B, LLaMA 3, DeepSeek-V3, Mistral 8x22B, and BLOOM. These models stand out because they are open source, enabling complete self-hosting and customization. This means Proton can maintain full control over user data, keeping all processing within secured European data centers, aligned with Proton’s zero-access policy and strong privacy commitments.

   GPT-OSS 120B offers powerful capabilities close to proprietary… more

   24 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  ·  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

5. 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

   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

6. Project Threads Lack Clear Memory Architecture

   Title: Project Threads Lack Clear Memory Architecture—Choose Privacy OR Context, Not Neither
   Category: General Ideas / Lumo

   The Current Problem:

   Lumo's v2.0 persistent memory aggregates content from general chat threads—but excludes project threads from memory aggregation. However, project threads remain indexed and searchable by keyword within the account.

   This creates a contradictory state with no tangible benefit:

   No context continuity — When you mention a project topic in a general chat, Lumo doesn't know the project exists or have any history to reference
   No real privacy — Project content is still searchable/indexed, so it's not a true "black box"
   No security gain — A snooper with account access can find project content via search; a locked memory system wouldn't add protection
   

   Current State:

   Projects: NOT aggregated → memory = incomplete
   Projects: Still indexed → search = works
   Result: Worst of both worlds (loss of convenience, no privacy benefit)
   

   Proposed Solutions (Either/Or):

   Option A: True Private Project Mode

   Project threads are fully gated—requires PIN/code entry to access
   Content excluded from both memory and search indexing
   Opt-in only (user explicitly locks a project)
   For sensitive work that needs genuine isolation
   

   Option B: Full Memory Aggregation

   Project threads feed into Lumo's persistent memory like general chats
   Content indexed and searchable (current behavior)
   Cross-thread context works seamlessly
   For users who prioritize functionality over isolation
   

   Option C: Hybrid Approach (Recommended)

   Default: Project threads aggregate to memory AND indexed
   User can enable "PIN Lock" on specific projects
   Locked projects: Excluded from memory, excluded from search
   Requires authentication to view or discuss locked project content
   Dual-memory system: General memory + Project-only memory (accessible after PIN unlock)
   

   Why This Matters:

   Users managing multiple projects (business startup, technical documentation, etc.) need consistency. If project threads are meant to be private, make them private. If they're meant to support context continuity, let them aggregate.

   The current halfway measure provides neither benefit.

   Requested Action: Implement gatekeeping (PIN/code) for project threads with dedicated project memory upon unlock. Give users explicit control over whether their project content feeds into general memory or stays isolated.

   Title: Project Threads Lack Clear Memory Architecture—Choose Privacy OR Context, Not Neither
   Category: General Ideas / Lumo

   The Current Problem:

   Lumo's v2.0 persistent memory aggregates content from general chat threads—but excludes project threads from memory aggregation. However, project threads remain indexed and searchable by keyword within the account.

   This creates a contradictory state with no tangible benefit:

   No context continuity — When you mention a project topic in a general chat, Lumo doesn't know the project exists or have any history to reference
   No real privacy — Project content is still searchable/indexed, so it's not a true "black box"
   No

   … 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  ·  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. Multiple windows (both emails and calendar) on Windows

   When using ProtonMail, I want to be able to:
   - Open a specific email in a new (secondary) window, So that I can read that email and type in a new email in a different window.
   - Open the calendar in a new (secondary) window, So that I can look at my calender while processing emails.
   - Open multiple emails in one window each.
   - Open multiple calendar views in one window each.

   All this is possible in the WEB version, but I need to use the full search feature of the local installed ProtonMail client.

   15 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

   7 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. Offline access to Lumo chats & local search (like Proton Drive)

   I'd like to propose a new feature for Lumo that enables access to chat histories without an internet connection – similar to the "Make available offline" function in Proton Drive.

   Use Case: Users want to read and search through specific chats or project histories while offline (e.g., on a plane, in areas with poor connectivity, or for privacy reasons). Currently, Lumo is only usable online, which limits access to your own conversation data.

   Proposed Features:

   1. Offline toggle for chats:
      Like in Proton Drive, users should be able to mark individual chats (or entire projects) with a toggle as "Available offline." These would then be stored locally on the device, fully encrypted.

   2. Two export modes:

   • Full-text mode: The complete chat history is made readable offline (including all details and discussion threads).
   • Summary mode: Users can select multiple chats to generate a compact, Lumo-created summary available offline.

   1. Local search with navigation:

   A full search within the offline-saved chats that:

   • Highlights found terms in color.
   • Allows navigating up/down between search results.
   • Works entirely without internet (indexing happens locally).

   Why this is valuable:

   • Increases the practical usability of Lumo in situations without internet.
   • Provides continuity in long-term projects and conversations, even offline.
   • Leverages proven Proton principles (encrypted local storage) and extends them to chat data.
   • Universally useful – not limited to specific use cases but beneficial for anyone who wants to work flexibly.

   Technical Feasibility: The infrastructure for encrypted local storage already exists in Proton Drive. Extending this to chat data would be a logical evolution. Local search is technically achievable since the text resides on the device after download.

   I'd like to propose a new feature for Lumo that enables access to chat histories without an internet connection – similar to the "Make available offline" function in Proton Drive.

   Use Case: Users want to read and search through specific chats or project histories while offline (e.g., on a plane, in areas with poor connectivity, or for privacy reasons). Currently, Lumo is only usable online, which limits access to your own conversation data.

   Proposed Features:

   1. Offline toggle for chats:
      Like in Proton Drive, users should be able to mark individual chats (or entire projects) with a toggle as "Available offline."… 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

9. Proton Draw

   Title: Feature Request: Lumo Draw – Privacy-First AI Illustration for Authors (Watercolor & Dark Fantasy Styles)

   Description: I am writing to strongly request the development of Lumo Draw, an AI image generation tool integrated into the Lumo ecosystem with zero-access encryption. (Note: The name "Lumo Draw" was my original concept, proposed here to maintain brand consistency with the Proton ecosystem.)

   My Background & Member History: I have been a loyal Proton member for many years. Currently, I am subscribed to the Lumo+ Family Plan, and I am also a Lifetime Supporter who donated during the annual ticket drive to secure my lifetime status. I am deeply invested in the Proton mission and the privacy-first ecosystem.

   My Use Case as an Author: As an author, I have two distinct illustration needs that current public AI tools cannot safely meet due to data training risks and aggressive censorship:

   Children's Books: I need a dedicated "Warm Watercolor" style. Soft edges, bleeding colors, and whimsical tones are essential. Current tools often force a generic digital look or struggle with consistent style locking.
   Adult Dark Fantasy Novel: This project requires a "Gritty/Dark" aesthetic. It includes atmospheric violence, complex moral themes, and mature storytelling. While it contains no illegal content (CSAM), existing consumer AI tools often over-censor artistic depictions of war, darkness, or mythological figures, making them useless for serious fiction.
   Why This Matters & Why "Lumo Draw"? The market has AI art generators, but they all suffer from the same fatal flaw for creators: They harvest user prompts and images to train future models. If I use Midjourney or DALL-E to design my book characters, I risk losing ownership of my unique IP. My specific "watercolor" or "gritty" style could be ingested into their models and sold back to others.

   A tool named Lumo Draw, operating under Proton's strict zero-access encryption, would ensure my character designs and unpublished story visuals remain mine and are never used to train public models.

   Proposed Features:

   Style Presets: Dedicated modes for "Soft Watercolor" (warmth/fantasy) and "Dark/Gritty" (high contrast/noir).
   Privacy First: No logs, no scanning of creative work for "policy violations" unless illegal, ensuring my artistic vision isn't sanitized by corporate filters.
   Consistency: Tools to lock character references across multiple generated pages.
   Paid Tier Willingness: As a long-time member and Lifetime supporter, I am explicitly willing to increase my payment to access a premium "Lumo Draw" service tier.
   Conclusion: Lumo Draw would be a game-changer for independent authors who value both creativity and privacy. It would allow us to visualize our worlds without compromising our intellectual property. Having suggested this name and concept after years of supporting Proton, I believe this feature aligns perfectly with the community's needs.

   Thank you for considering this feedback from a dedicated long-term member.

   Title: Feature Request: Lumo Draw – Privacy-First AI Illustration for Authors (Watercolor & Dark Fantasy Styles)

   Description: I am writing to strongly request the development of Lumo Draw, an AI image generation tool integrated into the Lumo ecosystem with zero-access encryption. (Note: The name "Lumo Draw" was my original concept, proposed here to maintain brand consistency with the Proton ecosystem.)

   My Background & Member History: I have been a loyal Proton member for many years. Currently, I am subscribed to the Lumo+ Family Plan, and I am also a Lifetime Supporter who donated during the annual ticket drive to secure… 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

   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

10. Allow Lumo to deal with Memory reduplicates

    I notice the memory list often has either exact duplicates or very similar worded info. I presume there is some kind of self-check to see if a memory has already been added. But its not quite up to standard.
    May i suggest can we give Lumo permission to comb through the memory and weed out duplicates or too similar ones. If there are edge cases it could apply a tag for a special filter called User Attention Needed (or something) and we can click on this button that is lit up when it has memories to assess and we only see the list of edge case memories and each one has a green tick button to approve or X to delete and a pencil icon to edit and once done we can tap the green tick button to allow it back into the main memories (and of course remove the special filter tag)

    Also to further enhance this idea, add search bar so we can see if what certain topics might be listed. And we could also filter our own manual memory entries with a command in the search bar: #you or /you

    I notice the memory list often has either exact duplicates or very similar worded info. I presume there is some kind of self-check to see if a memory has already been added. But its not quite up to standard.
    May i suggest can we give Lumo permission to comb through the memory and weed out duplicates or too similar ones. If there are edge cases it could apply a tag for a special filter called User Attention Needed (or something) and we can click on this button that is lit up when it has memories to assess and we only… 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

11. 4) Lumo Pages

    Lumo Pages: Collaborate on documents with Lumo (either as a product in Lumo or Proton Docs)
    Next post: https://protonmail.uservoice.com/forums/932842-lumo/suggestions/50637332-5-image-uploads

    22 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. To make Lumo more human

    Subject: Proposal: A "Dual-Loop" Architecture for Next-Gen LLMs Inspired by Neuro-Mechanical Models

    Dear Research and Engineering Team,

    I am writing to share a conceptual proposal for a new architectural approach to Large Language Models (LLMs), inspired by the neuro-mechanical theories of Lee Kent Hempfling (specifically the distinction between Short-Term and Long-Term memory loops).

    While current LLMs excel at pattern recognition and statistical prediction (effectively acting as massive Long-Term Memory systems), they lack a mechanism for inhibition, self-correction, and proactive intent. This proposal suggests a "Dual-Loop" architecture that could significantly reduce hallucinations, bias, and reactive behaviour.
    The Core Concept: Dual-Loop Architecture

    Current models rely on a single stream of attention mechanisms. I propose a system with two distinct, interacting loops:

    The Long-Term Loop (The Library):
        Function: Standard Transformer weights for retrieving facts, grammar, and historical patterns.
        Role: Fast, reactive, and high-volume data retrieval.
    The Short-Term Loop (The Operator):
        Function: A separate, high-speed module running in parallel.
        Role: Inhibition and Monitoring. Before the Long-Term loop commits to a token, the Short-Term loop evaluates:
            Is this consistent with the immediate context?
            Is this a hallucination or a bias?
            Does this align with the user's intent?
        Mechanism: If a conflict is detected, the Short-Term loop inhibits the output and triggers a re-evaluation cycle (simulating the human "brake" or "pause").
    

    Key Proposed Features

    Dynamic Inhibition Layers: Instead of just predicting the next token, the model actively suppresses low-probability or biased outputs that fail a "truth/intent" check.
    Frequency-Based Temporal Processing: Implementing a "Biological Clock" simulation where different parts of the network process information at different speeds (Fast for "Now"/Logic, Slow for Deep Memory), creating a simulated sense of time and continuity.
    Intent-Driven Generation: Shifting from "Pattern Completion" to "Goal Achievement," where the Short-Term loop sets a constraint/goal before the Long-Term loop retrieves data.
    Modality-Aware Routing: Detecting if a query requires visual simulation or logical deduction and routing processing accordingly, similar to how humans switch between visual and aural dominance.
    

    Potential Benefits

    Reduced Hallucinations: By inhibiting outputs that don't pass a consistency check.
    Lower Bias: Active suppression of training-data biases via the Short-Term "brake."
    Improved Alignment: Better adherence to user intent rather than just statistical likelihood.
    Organic Output: Moving away from rigid, "stiff" text generation toward fluid, "pro-active" responses.
    

    Next Steps

    I believe this approach moves beyond simple scaling (adding more parameters) to architectural innovation. It treats the LLM not just as a database, but as a system capable of self-regulation.

    I would be happy to provide further details, diagrams, or specific mathematical formulations for the "Inhibition Layer" if the team finds this direction promising.

    This Idea was created by Lumo with prompts from me. I thought it was good enough for others to have a better look and did'nt know who to send it to.

    Subject: Proposal: A "Dual-Loop" Architecture for Next-Gen LLMs Inspired by Neuro-Mechanical Models

    Dear Research and Engineering Team,

    I am writing to share a conceptual proposal for a new architectural approach to Large Language Models (LLMs), inspired by the neuro-mechanical theories of Lee Kent Hempfling (specifically the distinction between Short-Term and Long-Term memory loops).

    While current LLMs excel at pattern recognition and statistical prediction (effectively acting as massive Long-Term Memory systems), they lack a mechanism for inhibition, self-correction, and proactive intent. This proposal suggests a "Dual-Loop" architecture that could significantly reduce hallucinations, bias, and reactive behaviour.
    The Core Concept: Dual-Loop Architecture

    … 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

    3 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. Auto-Match Controls

    The auto-match feature adds files based on keyword matching, which can unintentionally clutter conversations with unrelated files.

    Requested: Settings to control auto-match behavior:

    • Toggle auto-match on/off entirely
    • Require explicit @mention for file inclusion
    • Limit matches to exact filenames only (no substring matching)
    • Show preview before auto-added files enter context
    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

14. 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

    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. AI-powered billing verification for construction (delivery notes + measurement = invoice)

    I'm a construction site manager in landscaping (GaLaBau). Our industry software (greenGALA 8, BAUSU) is purely static – it generates output but performs no automated checks or reconciliations. Every verification is done manually: data entry, Excel cross-checks, triple manual control, handwritten delivery note sorting, and final invoice plausibility checks.

    The core billing equation in construction is: Delivery notes + Measurement = Invoice. There is currently no tool that automates this reconciliation across the entire chain.

    Three areas where AI support would create massive value:

    1. Delivery note processing – Delivery notes are often barely legible: handwritten, dirty, incomplete, filled out on-site. Manual sorting and data entry takes unreasonable amounts of time. OCR-based extraction, even from poor-quality scans or photos, would save hours per project.

    2. Measurement plan understanding – Measurements often exist as drawn plans or sketches, not digitally. If AI could read measurement plans and extract dimensions and quantities, that would eliminate another fully manual step.

    3. Final invoice plausibility check – The most error-prone and time-consuming step. Reconciling delivery note quantities and measurements against billed positions. Finding deviations that can't be logically explained.

    Concrete bug I already encountered: I uploaded a final invoice PDF + measurement list PDF to Lumo 2.0 Max (Thinking mode, web search enabled) and asked it to reconcile them. The processing log showed completion, but both times the output was: "Something went wrong." Reproducible twice with identical files and prompt.

    Financial reality: I pay for Lumo out of my own pocket, not through a company license. Tax deductibility covers only a fraction. If Lumo can't handle the core use case – reliable PDF billing verification – it's financially uninteresting for me.

    What I need: Reliable processing of two linked PDFs, structured table extraction, and automated discrepancy detection across delivery notes, measurements, and invoices – bundled in encrypted Lumo Projects. This applies to the entire construction industry, not just landscaping: civil engineering, road building, structural work, all trades.

    Happy to provide sample documents or beta-test features.

    I'm a construction site manager in landscaping (GaLaBau). Our industry software (greenGALA 8, BAUSU) is purely static – it generates output but performs no automated checks or reconciliations. Every verification is done manually: data entry, Excel cross-checks, triple manual control, handwritten delivery note sorting, and final invoice plausibility checks.

    The core billing equation in construction is: Delivery notes + Measurement = Invoice. There is currently no tool that automates this reconciliation across the entire chain.

    Three areas where AI support would create massive value:

    1. Delivery note processing – Delivery notes are often barely legible: handwritten, dirty, incomplete, filled out on-site.… 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

    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

16. Support for audio and creative file formats (.wav, .als, etc.)

    When working on music production projects (Ableton Live), I can't upload the files I actually use:

    .wav files are rejected — drag and drop returns "Unsupported file type"
    .als files are greyed out in the file picker
    I chose Lumo Plus because privacy matters for my creative work, but I can't even load the files I work with. Could support for common audio/creative formats be added?

    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

17. Lumo "lite" tier for Unlimited, Duo and Family subscribers

    While I get the cost of hosting an LLM and a separate plan for unlimited usage is totally fair, I do think paying customers, especially subscribers to the so-called unlimited plans, should get a little special treatment with a tier of Lumo exclusive to these plans.

    Perhaps instead of the 10/day and 200/month prompt limit, 1 project limit and 7 day history that Lumo Free provides, this new Lumo Lite could give us 50/day, 500/month, 2 projects and unlimited history (we already have 500 GB of storage so Lumo message storage should be negligible).

    All the other features like unlimited prompts, projects and advanced AI models could be reserved for the Plus plan for those who need it, but having it easier to integrate in an existing 2 year plan, with appropriate discounts would be nice. Currently, upgrading to Lumo Plus while having Proton Unlimited, downgrades me to a 1 year plan for both, forcing me to pay more for Proton Unlimited as well.

    While I get the cost of hosting an LLM and a separate plan for unlimited usage is totally fair, I do think paying customers, especially subscribers to the so-called unlimited plans, should get a little special treatment with a tier of Lumo exclusive to these plans.

    Perhaps instead of the 10/day and 200/month prompt limit, 1 project limit and 7 day history that Lumo Free provides, this new Lumo Lite could give us 50/day, 500/month, 2 projects and unlimited history (we already have 500 GB of storage so Lumo message storage should be negligible).

    All the other features like unlimited… more

    6 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  ·  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

18. Please have a text to voice function at the end of each message.

    Please have a text to voice function at the end of each message. Every other AI incorporates this and it reads the text back to you. It helps people with disabilities or if you are driving and trying to pay attention to the road. This way you can voice to text to Lumo and get text to voice back. Thanks!

    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

19. Custom event time zones in Proton Calendar

    I have been traveling more, and I would like to book work and personal events in their respective time zones. I have my current primary time zone as Central U.S. (Chicago), but a secondary time zone doesn't really make sense for short trips to other time zones. An example is I booked a museum tour at a specified time in London, UK next year. I would like to add it with the 12:00 at London 0 GMT. And then let's say I book a dinner reservation in Washington, DC for my trip this week. I could make it 6:00 pm Eastern U.S. and not have to think about making it 5:00 pm Central U.S. My ideal suggestion would be a quick search field that has pre-populated with cities and countries and their time zones pulled from Wikipedia, then also the GMT system for when a backup is necessary.

    I have been traveling more, and I would like to book work and personal events in their respective time zones. I have my current primary time zone as Central U.S. (Chicago), but a secondary time zone doesn't really make sense for short trips to other time zones. An example is I booked a museum tour at a specified time in London, UK next year. I would like to add it with the 12:00 at London 0 GMT. And then let's say I book a dinner reservation in Washington, DC for my trip this week. I could make it 6:00 pm… 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. Subthread creation from highlighted response, pinning, pruning, editing, model changing.

    A fractal of subthreads started from a response.

    Tree navigation, Pruning, and editing.

    Subthread PinningG

    I understand this is complex,
    I'de rather have it slow and capable, instead of not at all.

    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