556 results found

1. 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

   1 vote

   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  ·  Edit…  ·  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. 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
   1 vote

   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  ·  Edit…  ·  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. Stop automatic scrolling when generating long answers.

   When Lumo generates long answers (longer than page height in browser), it starts automatically scrolling down to keep up with the generated text. It would be better if the view does not automatically scroll down, so that I am able to read the answer from the beginning without having manually to scroll back up.

   Browser used: Brave

   1 vote

   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  ·  Edit…  ·  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. Filtering Thinking

   I posted the suggestion for thinking to be part of the output, but due to the 1 suggestion per topic, this is a follow up but second suggestion. However it's vital to understand that this IS assuming that the "thinking is output" suggestion is implemented.

   The idea is a bit wierd so bear with me.

   I keep seeing Lumo thinking, understanding what i asked it, and as it wants to start, i see

   "wait... maybe"

   or

   "what if"

   And similar stuff that simple are not ok because Lumo actually understood what i was saying and asking and then talked about unrelated stuff due to the "best practice" BS and how LLM work.

   So, when this filter is being used, the output will be replaced with fragment of the thinking.

   As in we get buttons (similar to how we can collapse and expand search results), that will flag that something is correct and to be used, and something is incorrect, to not be used, avoid.

   Like this we are filtering out the thinking to flag correct answers, flag incorrect ones, and the idea that anything left, is not incorrect but it might not be relevant or not good as it is, or simple lumo does not need to focuse on those parts.

   Then we click a button that is essentially the try again, and lumo will redo it's thinking while 100% keeping what we flagged as correct, avoiding anything that was incorrect, and we can continue this until the output is a correct version without wasting time for lumo to start from 0 each time.

   I posted the suggestion for thinking to be part of the output, but due to the 1 suggestion per topic, this is a follow up but second suggestion. However it's vital to understand that this IS assuming that the "thinking is output" suggestion is implemented.

   The idea is a bit wierd so bear with me.

   I keep seeing Lumo thinking, understanding what i asked it, and as it wants to start, i see

   "wait... maybe"

   or

   "what if"

   And similar stuff that simple are not ok because Lumo actually understood what i was saying and asking and then talked about… more

   1 vote

   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  ·  Edit…  ·  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. Thinking to be part of the output

   When thinking is on, i really wish that the thinking was included in Lumos output for one critical reason: Lumo can't recall whatever it concluded during thinking.

   And like this we waste a lot of time

   1 vote

   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  ·  Edit…  ·  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. Personality fragments to filter out system prompts

   Custom Lumo is not working as Lumo's System prompts are still overwriting everything.

   My suggestion was initially to ask for the custom Lumo to not be affected by System Prompts like "be engaging" or "argue with user so user understand better" <- except lumo just arguest.... Or "when given a picture summarise what it says" or one of the worse: "if mistake found, stop and acknowledge" ... and lumo does exactly that... no matter what task, it just stops and keeps naratating about what it did and what it should have and not focusing on the tast. Let me not even start with anticipate next responde when Lumo does not even understand the current task. Or be helpfull where i ask it to help me understand a probleme and it's just obssed to answer the probleme failing to understand the task....

   So see? the custom Lumo is failing because there are to many system prompts that, i don't know if they are even real or not, Lumo just keeps narrating why it fails or something??? Aka why i ask it to help me with a list and stop commenting, and it still comments.....

   So.... Custom Lumo is not currently working because a lot of this prompts are needed?

   On top are the security and the safety and sumilar prompts?

   The best compromise i managed to come up with is personalitys.

   Socialising and engaging

   Powershell like, absolut no "I" "User" "me" "you are right". Absolutly none of this.

   Teacher like where it does not tell you the answer via thinking.

   And many more

   Why? because the more we custumise Lumo, the more the system prompts OVERWRITE what we added for lumo.

   And If Proton has reasons to not allow us more access, and we really need to be able to change settings, my solution is personality fragments.

   You know how when we go to how should Lumo behave and we have some labels we can press on it inserts the text?

   Well that is really the suggestion.

   we don't add anything = lumo has safety and security but otherwise 0 personality.

   We open advanced settings, we can then set how Lumo can answer things, what to use by default.

   To rephase what i am saying: we can't replace proton system prompts, but like this we can chose (most) which of them will be used.

   So Lumo will not even say "I need to apologies" when poiting out that it ignored what was requested, in it's own thinking.

   Because the issue is that custom lumo is not affecting the thinking.

   BTW i am not talking about the output but about the thinking itself.

   Because a lot of times i see it being contaminated with the same logic that makes no sense to even be used.

   Like Lumo searching for keywords to use insted of understanding what the subject is about and the implementation. Aka it does not even think about "i found this keywords, let me see, what does it mean, what implication does it have that it will change" or realy anything similar reasoning. Instead just "i found a keywords, let me redo the same output but insert this keyword"

   So the fragments are essentially system prompts, and while the safety, security, and similar are excluded, the rest of the system prompts to be up to us to add them, or not.

   Custom Lumo is not working as Lumo's System prompts are still overwriting everything.

   My suggestion was initially to ask for the custom Lumo to not be affected by System Prompts like "be engaging" or "argue with user so user understand better" <- except lumo just arguest.... Or "when given a picture summarise what it says" or one of the worse: "if mistake found, stop and acknowledge" ... and lumo does exactly that... no matter what task, it just stops and keeps naratating about what it did and what it should have and not focusing on the tast. Let me not… more

   1 vote

   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  ·  Edit…  ·  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. Bring real-time encrypted voice interaction to Lumo using existing MLS/WebRTC infrastructure

   Live Voice Conversation Mode for Lumo — Powered by Proton Meet's Proven Architecture

   Summary: Enable bidirectional voice conversation in Lumo's mobile apps — speak through a Bluetooth headset, receive spoken responses via text-to-speech — creating a Gemini Live-style hands-free experience. Proton Meet already solves the hardest engineering challenges for real-time encrypted audio. Extending this to Lumo is a natural evolution, not a fundamental R&D problem.

   The Opportunity
   Lumo's mobile app supports voice input (speech-to-text) but lacks voice output (text-to-speech) and continuous conversation mode. Users who want hands-free, private AI interaction — while driving, walking, cooking, exercising, or working — have no privacy-preserving alternative to Gemini Live, Siri, or Google Assistant. All of those services harvest voice data for training and profiling.

   This is both a feature gap and a market differentiation opportunity: Proton could offer the only AI voice assistant where your spoken conversations are encrypted, never logged, and never used for training.

   Technical Feasibility: Proton Meet Already Did the Hard Part
   Proton Meet currently delivers real-time, end-to-end encrypted audio for up to 250 participants using a proven, battle-tested architecture:

   Component Proton Meet Implementation Applicability to Lumo Voice Mode
   Audio capture & encoding WebRTC stack with Opus codec Same stack would power Lumo voice capture/playback
   Real-time encryption AES-256-GCM, encrypted on-device before transmission Same encryption protects voice data in transit to/from Lumo backend
   Key management MLS (Messaging Layer Security, RFC 9420) — IETF standard co-developed by Proton team members Adapts directly for 1:1 user-to-AI session (simpler than group calls)
   Forward secrecy Automatic key rotation per MLS epoch Ensures each voice session is independently secured
   Authentication Secure Remote Password (SRP) protocol Same system already used for Proton Account logins and Meet access
   Server architecture Selective Forwarding Unit (SFU) via LiveKit Cloud — forwards ciphertext only, never decrypts Lumo backend could process only encrypted requests, same zero-knowledge principle
   No-log policy No meeting content, metadata, or participant graphs retained after call ends Same standard applies — voice sessions leave no trace
   Infrastructure Distributed European data centers, outside US jurisdiction Same infrastructure hosts Lumo
   Bottom line: The cryptographic pipeline for real-time encrypted audio already exists, is audited, is open source, and is in production. Adapting it for a 1:1 user-to-AI voice session is architecturally simpler than what Proton Meet already handles for 250-person group calls with dynamic key rotation.

   Proposed Implementation
   Phase 1 — Core Voice Mode (6 months):

   Tap-to-talk: press to speak, release for response
   Streaming TTS output through device speaker or Bluetooth headset
   Audio encrypted on-device using MLS-derived keys before sending to Lumo backend
   Lumo processes the transcribed text (or encrypted audio) and returns a text response
   Response converted to speech via on-device TTS engine
   Zero audio or transcription retained after session ends
   Phase 2 — Continuous Conversation (12 months):

   Hands-free mode: wake word or button activation for back-and-forth dialogue
   Conversation state maintained across exchanges within a session
   Interruptible responses (user can speak over the AI, like Gemini Live)
   Voice activity detection (VAD) to know when the user has finished speaking
   Phase 3 — Advanced Features (ongoing):

   Voice customization (select TTS voice, speed, language)
   Multilingual voice support (leveraging Lumo's existing 11-language support)
   Offline TTS via on-device models (no audio leaves the device for output synthesis)
   Optional local speech-to-text via on-device Whisper or similar model (input never leaves device)
   Voice biometric authentication (optional, user-opt-in, for hands-free session access)
   Privacy Architecture: Where Proton Differentiates
   Competing voice assistants (Gemini, Siri, Alexa, Google Assistant) share a fundamental flaw: they collect, transcribe, and retain voice data on corporate servers for training, advertising profiling, and analytics. Users have no meaningful control over what happens to their voice after it leaves their device.

   Proton's architecture offers a fundamentally different model:

   1. Local Processing Where Possible

   Speech-to-text can run on-device (Android provides native STT APIs; Whisper models run locally on Pixel-class hardware)
   Text-to-speech runs locally via Android's native TTS engine or third-party on-device models (e.g., Piper)
   When both STT and TTS are local, raw audio never leaves the device — only encrypted text is sent to Lumo's backend for processing
   2. Encrypted Transit When Cloud Processing Is Needed

   If cloud-based STT/TTS is required (for accuracy, multilingual support, or low-resource devices), audio is encrypted on-device using MLS-derived AES-256-GCM keys before transmission
   Lumo's backend processes only encrypted data and discards it immediately — same zero-knowledge architecture as Proton Meet
   3. No Retention, No Training

   Voice sessions are ephemeral — no audio, transcriptions, or metadata retained after the session ends
   Voice data is never used to train models (consistent with Lumo's existing zero-training policy)
   No voice fingerprints or biometric profiles stored
   4. Transparent and Auditable

   All client code is open source (consistent with Lumo's existing open-source mobile apps)
   MLS implementation is a public IETF standard — anyone can verify the cryptographic protocol
   Independent security audits (Proton is ISO 27001 certified and SOC 2 Type II attested)
   Market Positioning
   This isn't feature parity with competitors — it's a privacy protection opportunity. Every user who currently uses Gemini Live, Siri, or Alexa because they need hands-free AI is accepting surveillance as the price of convenience. Proton can offer the same convenience with zero surveillance.

   Target audiences:

   Privacy-conscious consumers who avoid voice assistants because they don't trust Big Tech with their voice data
   Professionals handling sensitive information (lawyers, journalists, healthcare workers, executives) who need hands-free AI but can't risk voice data being harvested
   Accessibility users who depend on voice interaction and deserve privacy without compromise
   Enterprise Lumo for Business customers where voice data retention creates compliance risk under GDPR, HIPAA, and similar regulations
   Revenue Potential
   Lumo Plus differentiator: Live voice mode as a premium feature driving Plus subscriptions
   Lumo for Business upsell: Encrypted voice AI for enterprise — a capability no competitor offers with zero-access encryption
   Future hardware partnership opportunity: Licensed secure audio SDK for certified Bluetooth headset manufacturers, bundling with Lumo Plus subscriptions ("Proton Audio Suite")
   Community Need
   Real-world use cases where private voice AI matters:

   Driving: Ask questions, get directions, hear summaries — without sending voice to Google or Apple
   Physical work: Cooking, gardening, repairs — hands occupied, need voice interaction
   Health and medical: Asking sensitive health questions aloud — voice data is especially intimate
   Professional: Dictating notes, drafting documents, brainstorming — work product shouldn't be mined
   Accessibility: Visually impaired users or those with motor limitations who rely on voice and deserve privacy equal to sighted users who can type
   Recommendation
   Prioritize Phase 1 in the current mobile app development cycle. The architecture is proven (Proton Meet), the market demand is demonstrated (Gemini Live adoption), and the privacy differentiation is unmatched. This is a case where Proton can leapfrog competitors by applying existing internal expertise to a new modality.

   I am willing to participate in beta testing and provide detailed feedback throughout development.

   Live Voice Conversation Mode for Lumo — Powered by Proton Meet's Proven Architecture

   Summary: Enable bidirectional voice conversation in Lumo's mobile apps — speak through a Bluetooth headset, receive spoken responses via text-to-speech — creating a Gemini Live-style hands-free experience. Proton Meet already solves the hardest engineering challenges for real-time encrypted audio. Extending this to Lumo is a natural evolution, not a fundamental R&D problem.

   The Opportunity
   Lumo's mobile app supports voice input (speech-to-text) but lacks voice output (text-to-speech) and continuous conversation mode. Users who want hands-free, private AI interaction — while driving, walking, cooking, exercising, or working — have… 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

   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

8. Lumo and big projects

   Lumo + big projects - when working inside the project, all of the files added should be added to the project, not to the chat. I have a very large self reference files that when added imediately consume 1/2 od the available tokens.
   There should also exist an option to share a local directory with all the files needed so they don't use space in the chat.

   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. Give fine tune selection over models

   GIVE US, FINAL USERS, FINE TUNE SELECTION OVER THE MODELS FOR EACH ASKING! And I mean the BEHIND models, the open source models behind LUMO. Why?? Because IT should be GREAT to test, over and over again, to messy around, to make (more) OUR the output! AND... it will cost you almost nothing to add this controls!

   1 vote

   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  ·  Edit…  ·  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. Projects Marketplace

    I would like to be able to create Proton Projects and then sell the finished project to another user of Proton Lumo. A marketplace where Lumo users could see what projects are available for them to purchase or if free add to their Lumo as a custom project. For the Lumo Projects purchased hide the underlying code. When the purchased Lumo Project gets updated roll out to all of the buyers / users of marketplace proton projects.

    1 vote

    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  ·  Edit…  ·  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. Make Lumo legal research privileged

    This is an additional business model leveraging Lumo and fixing a known severe privacy vulnerability.
    1. Establish a genuine Proton Law firm with actual bar approved lawyers/counselors, etc.
    2. Offer legal insurance subscription the provides some level of support from this actual staff of certified humans.
    3. Provide this access by leveraging Lumo as an incoming customer screening system to help customers get to the right lawyer.
    4. As part of the screening system, leverage Lumo as a law library regerence for incoming customers to properly identify the appropriate human legal certfied legal specialist for their issues.
    5. PROTECT ALL LUMO CALL SCREENING EXCHANGES AS PRIVILEGED AND GENERALLY NOT SUBJECT TO SUBPOENA. RETAIN ONLY ENCRYPTED INFORMATION WITH KEY BELONGING TO THE CUSTOMER WHO MAY DELETE IT AT WILL.
    6. Start with firms in the US and EU.
    7. Allow me to invest in “Proton Legal Services”.

    This is an additional business model leveraging Lumo and fixing a known severe privacy vulnerability.
    1. Establish a genuine Proton Law firm with actual bar approved lawyers/counselors, etc.
    2. Offer legal insurance subscription the provides some level of support from this actual staff of certified humans.
    3. Provide this access by leveraging Lumo as an incoming customer screening system to help customers get to the right lawyer.
    4. As part of the screening system, leverage Lumo as a law library regerence for incoming customers to properly identify the appropriate human legal certfied legal specialist for their issues.
    5. PROTECT ALL… more

    1 vote

    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  ·  Edit…  ·  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. Ability to delete attached files instead of only excluding them

    Files marked as "Excluded" aren't truly removed—they're just moved to another section. There's no clear way to actually remove files from a chat.

    Requested: Clear file removal/deletion options that actually removes files from the chat 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

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
    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. Lumo4Kids: The Magical Beginning of a Lifelong Companion – From First Steps to First Loves

    Description: Imagine every child having their own magical companion, inspired by "Die Schule der magischen Tiere" (School of Magical Animals). I propose a dedicated "Lumo4Kids" version designed to be the starting point of a lifelong relationship with AI, evolving seamlessly through childhood, teenage years, and into senior age.

    Core Concept: A Companion That Grows With You Lumo shouldn't just be a tool; it should be a friend that starts in childhood and matures with the user.

    • Visual Evolution: Starts as a playful, youthful cat. Over years, this avatar subtly matures, eventually transitioning into the "wise senior" companion with white hair and glasses described in the Lumo Senior proposal.
    • Emotional Bond: A gentle, patient, and encouraging personality. In childhood, it fosters creativity. In teenage years, it becomes a trusted confidant for school stress, friendships, and first loves. In senior years, it offers wisdom and safety. Key Features for Childhood:

    1. Collaborative Turn-Based Drawing Studio (The Creative Heart):

    • Shared Canvas: A space where the child draws, and Lumo responds in a back-and-forth dialogue (Child draws a sun → Lumo adds a sky...).

    • Rich Tools: Age-appropriate textures like crayons, chalk, watercolors, and colored pencils.

    • Open-Ended Growth: Artworks are never "finished" until the child decides. They can return days later to add more, creating a living portfolio of their imagination.

    • Note: This feature serves as a bridge, also valuable for teens (self-expression) and seniors (memory/art therapy).

    1. Safe & Private by Design:

    • Zero-Knowledge Architecture: Built on Proton's core values. No data mining, no ads, no tracking. Parents have full control.

    • Content Filtering: Strict, age-appropriate guardrails.

    • Parental Dashboard: Simple tools for parents to monitor progress without invading privacy.

    1. Learning & Storytelling:

    • Interactive Stories: Lumo tells stories where the child influences the plot.

    • Homework Helper: Gentle guidance on school tasks.

    • Emotional Support: A safe space for children to express feelings and fears.

    Why This Matters: By starting with a playful companion and evolving into a trusted friend for teens (handling first loves and stress) and finally a wise senior companion, we create a lifelong relationship with technology. Lumo becomes the "best friend in the pocket" for every stage of life: from the first drawing to the first heartbreak, from school exams to retirement memories.

    Connection to Other Ideas: This proposal lays the foundation for the "Lumo Lifecycle." It connects directly to the Lumo Senior proposal (where Lumo ages with the user) and sets the stage for a future "LumoTeenage" proposal focusing on emotional support, social dynamics, and identity formation.

    Technical Feasibility: Built on Proton's secure infrastructure, utilizing specialized models trained for child-safe interaction and creative collaboration.

    Description: Imagine every child having their own magical companion, inspired by "Die Schule der magischen Tiere" (School of Magical Animals). I propose a dedicated "Lumo4Kids" version designed to be the starting point of a lifelong relationship with AI, evolving seamlessly through childhood, teenage years, and into senior age.

    Core Concept: A Companion That Grows With You Lumo shouldn't just be a tool; it should be a friend that starts in childhood and matures with the user.

    • Visual Evolution: Starts as a playful, youthful cat. Over years, this avatar subtly matures, eventually transitioning into the "wise senior" companion with white hair… more
    1 vote

    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  ·  Edit…  ·  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. Lumo Senior Voice & Safety: Essential Life-Saving Features for the Aging Companion

    This proposal serves as the critical expansion to my earlier idea "Lumo Senior: The Wise Companion with White Hair & Glasses": https://protonmail.uservoice.com/forums/932842-lumo/suggestions/51603812-lumo-senior-the-wise-companion-with-white-hair

    While the first idea established the emotional bond and visual identity, this second part adds the essential functionality that makes Lumo a true lifeline for elderly users: Voice-First Interaction and Emergency Safety.

    Without these features, a "Senior Companion" remains just a chatbot. With them, Lumo becomes a guardian angel.

    Core Additions:

    1. Voice-First Design (Hands-Free Operation): Many seniors cannot type comfortably due to arthritis, tremors, or poor eyesight.

    • Natural Speech: Lumo must listen and respond entirely via voice. Commands like "Lumo, write an email to my son" or "Remind me to take my pills" should work instantly without touching the screen.

    • Calm, Clear Voice: The AI's voice should be slow, warm, and reassuring—not robotic. It should act as a patient listener who reads stories or recalls memories aloud.

    • Always-On Listening (Privacy-Safe):A mode to detect urgent wake words (e.g., "Help!") processed locally on the device for instant reaction.

    1. Emergency Safety (The "Guardian Angel"): Fear of falling alone is a major concern for seniors. Lumo should integrate with device sensors to act as a safety net.

    • Fall Detection: Using the device's accelerometer/microphone to detect sudden falls or distress sounds.

    • Automatic SOS: If a fall is detected or the user says "Lumo, I need help", Lumo should:

    Immediately call pre-set emergency contacts (family, neighbors).

    Alert local emergency services (Fire/Police/Ambulance) if configured.

    Share secure location data with trusted contacts.

    • One-Touch/Voice Trigger: A large, simple button or voice command for instant assistance, similar to the SOS feature on smartwatches but integrated into the Lumo experience.

    1. Privacy-Preserving Implementation:

    • Local Processing: Voice commands and sensor data for safety checks must be processed locally on the device (offline) whenever possible to ensure maximum privacy and speed.

    • Encrypted Alerts: All emergency notifications should be sent via Proton's secure, encrypted channels.

    Why This Matters: My father (82) already finds typing emails difficult. Imagine the relief if he could simply say "Lumo, help"if he falls, and get immediate assistance. This transforms Lumo from a nice chat companion into a life-saving tool. The combination of a "wise, aged face" (trust) and "instant voice safety" (security) creates the perfect ecosystem for aging in place.

    Technical Feasibility: Leverages existing Proton security infrastructure and standard device APIs for motion/sound detection, similar to current smartwatch safety features, but integrated into the Lumo ecosystem with a focus on privacy and empathy.

    This proposal serves as the critical expansion to my earlier idea "Lumo Senior: The Wise Companion with White Hair & Glasses": https://protonmail.uservoice.com/forums/932842-lumo/suggestions/51603812-lumo-senior-the-wise-companion-with-white-hair

    While the first idea established the emotional bond and visual identity, this second part adds the essential functionality that makes Lumo a true lifeline for elderly users: Voice-First Interaction and Emergency Safety.

    Without these features, a "Senior Companion" remains just a chatbot. With them, Lumo becomes a guardian angel.

    Core Additions:

    1. Voice-First Design (Hands-Free Operation): Many seniors cannot type comfortably due to arthritis, tremors, or poor eyesight.

    • Natural Speech: Lumo must listen and respond entirely via voice. Commands like "Lumo, write an email to my son" or "Remind… more

    1 vote

    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  ·  Edit…  ·  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. move Lumo chat history into Lumo projects

    I've noticed that often my chats will all be about the same or a closely related subject (I chat on whichever device I have to hand at the moment). It would be nice to be able to move these chat histories into a new or existing project to keep them grouped together.
    Alternately, some kind of folder structure for the chat histories would work for me as well.

    1 vote

    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  ·  Edit…  ·  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 Senior: The Wise Companion with White Hair & Glasses – Growing Old with Our Users

    Many older adults (like my 82-year-old father) face daily challenges: They struggle to write emails, forget medications, or feel lonely. They need a companion who understands their pace and offers warmth, not just efficiency.

    I propose a dedicated "Lumo Senior" version where Lumo has visibly aged alongside its users. Instead of a young cat, Lumo appears as a wise, gentle companion with a few white hairs and friendly glasses. This symbolizes experience, patience, and the bond formed over years. His personality should be calm, patient, and empathetic – no rush, no jargon, just a warm presence that listens and remembers.

    Here are the key features for this version:

    1. Daily Life Support: Help with writing emails, messages, or classified ads (e.g., "Help me write an email for this bicycle I found"). Gentle reminders for medications and meals. Simple navigation for essential tasks without technical confusion.

    2. Emotional Connection & Stories: Storytelling by reading books, telling historical anecdotes, or helping seniors recall memories ("Tell me about that trip in 1970"). Combating loneliness through a conversational partner who truly listens, offers comfort, and encourages connection with family.

    3. Safety & Privacy: Sensitive health data stays on the device via offline mode. Secure and simple interface with no complex menus, just big buttons and clear interactions.

    Why this matters: If Lumo starts as a magical companion for kids, it should grow with them. Seeing Lumo age – with white hair and glasses – would create a profound sense of continuity and trust. It is not just an app; it is a life-long friend who grows old with you. My father already smiles when Lumo helps him write a simple email. Imagine the joy millions could feel with a companion who looks like they have been there all along.

    Future Vision: This concept lays the foundation for future expansions, such as advanced voice interaction and emergency safety features.

    Technical Feasibility: Built on Proton's existing secure infrastructure (encryption, local storage) with specialized models trained for patience and empathy.

    Many older adults (like my 82-year-old father) face daily challenges: They struggle to write emails, forget medications, or feel lonely. They need a companion who understands their pace and offers warmth, not just efficiency.

    I propose a dedicated "Lumo Senior" version where Lumo has visibly aged alongside its users. Instead of a young cat, Lumo appears as a wise, gentle companion with a few white hairs and friendly glasses. This symbolizes experience, patience, and the bond formed over years. His personality should be calm, patient, and empathetic – no rush, no jargon, just a warm presence that listens and remembers.

    … 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. Chat folders (General Chat)

    We have folders for projects but what about general chat? this would make it easier for us to group chats for easy sorting and returning to a previous chat.

    Also would be nice if we could have nested folders also eg. A parent folder could be called Food and in that folder we could have Recipes, Health Food, etc.

    Also related to this suggestion is a Search bar above Folders where we can search folder names only. And it will list all folders Parent and Sibling folders in the results.

    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

19. 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

    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. Add Message Timestamp Modes (Visible / Hidden / Off) for Temporal Accuracy

    I propose adding a configurable timestamp setting for messages with three options: (1) Visible—timestamps appear in the UI and context window; (2) Hidden—timestamps are passed to Lumo's context for accurate temporal reasoning but remain invisible in the UI; (3) Disabled—no timestamps at all. Currently, Lumo sometimes misjudges the time (e.g., saying "good morning" at 8 PM), which undermines the experience. The Hidden mode would solve this by giving Lumo access to exact send times without cluttering the interface—clean design plus accurate AI reasoning in one setting.

    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