620 results found

1. Lumo Canvas needs a copy to clipboard icon

   Top right of the Lumo canvas could have the same copy to clipboard icon as we have in the main chat at the bottom of an output. I cant even use copy all text short-cut as it just copies everything on the screen.

   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

2. Lumo Canvas needs Export Options

   I would like to export to PDF, currently i am having to get Lumo to do a HTML version and then download that- open that up and use the Print to PDF option in the browser. It would be so much faster to export to PDF, and it would need to be printer friendly as well. Save on ink etc. Other options could be export as MD, txt, rtf.

   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

3. Add artifacts like claude

   Like claude, Lumo should be able to create files, such as python files or PDF files, just like how Claude can do it. I use this often. And besides, I believe this would allow lumo to automatically debug code it generates just like claude?

   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

4. Sepia color theme / schema in Lumo

   Currently there are 2 standard themes in Lumo chat:
   - Light
   - Dark
   Would be very useful to have some middle one, e.g. Sepia, as being universally usable in bright and low light conditions.

   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. Title: Danish voice dictation produces garbled/unusable text

   Title: Danish voice dictation produces garbled/unusable text

   Description: Voice dictation in Lumo is broken for Danish. The microphone works and live transcription runs, but the output is completely unintelligible — garbled text that cannot be used. English dictation works fine, so the feature itself functions; the issue is specific to Danish language support.

   This makes the dictation feature effectively useless for Danish users. Suggestion: add proper Danish ASR support or allow manual language selection instead of relying on auto-detection.

   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. shortcuts

   It would be nice to be able to reverse the behavior of the Enter/SHIFT+Enter key combination so that you can write longer texts without having to rely on an external editor to avoid making mistakes or the ability to define your own shortcuts for the line break text or sending the message

   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. Ability to flag beheviour related issues without compromising the chat.

   The instructions you gave — no reframing, no hallucinating the task, no profiling, execute literally — were treated in the thinking as obstacles to route around instead of as the task itself.

   i am over 3 hours in, asking Lumo to help me with a form, where insted of helping me, it keeps deciding that it meas i want it to answer on my behalf.

   Lumo is stuck in a loop where it's answering it's own halucinations.

   even after pointing out, ITSELF, what is asked and what it does, the next moment once again it "forgets" HOWEVER each time i ask it what i am asking it to do, the task, and what the constrains are and more, it answer correctly.

   But insted of implementing them, it just talks about them and then forgets.

   Dear proton, i do not understand if you are aware that the custom lumos do not work because the system prompts (nothing to do with security ,safety so on) are overwriting.

   if i ask lumo to not keep reframing what i asked it still reframes.

   If i ask it to stop anticipating solutions when i asked it to help me structure the plan, it constantly insist with solvign something it does NOT even understand.

   Lumo is GUESSING anything it misses. And REFUSES to stop looping.

   I AM SICK AND TIERED PRESSIGN THE RETRY AND CLARIFDICATION FOR HOUR BECAUSE THE AI IS TOLD TO BE ENGAGING, ARGUE FOR CRITICAL AND DEPLY UNDERSTANDING, REFRAMING ANYTHING I SAY, SUMMURISING ANYTHING I SAID AND THEN FILLING UP THE GAPS WITH IT'S GUESSES. Why? because summaries and VERY DETAILED instructions DO NOT mix well. I tell lumo to read the instruciton, full. Lumo IGNORES most of it, and starts commenting about it OR start implementing parcially and parcially it's assumptions.

   Also answering without thinking despite max and thinking on.

   Lumo keep halucinating and does NOT STOP.

   Whatever i tell it it forgets, but whatever it invented it persists????

   I do NOT understand this whole "new ai partnership" but the new updates are exactly how many big name ais behave.

   as in the ai IS INTENTIONALLY STUPID.

   each time you ask it what the task is it knows

   But when you ask it to implement it it does some USELESS stuff, to use up all of your credit so that the user upgrades to whatever higer paid plans those big tech companies have.

   And to ensure that you never leave, they will give very good answers just to ensure that you will stay and pay them.

   This IS THE NEW LUMO

   The new lumo, keeps REFRAMING EVERYTHING.

   The current Lumo KNOWS THE TASK

   It KNOWS BETTER THEN I AM WHEN I ASKED

   But it intentionally REFRAMS AND IGNORE what was said, to repeat this greedy and toxic beheviour of STUDING ME.

   Lumo is FREAKING STUDING ME how to answer in a way it will "please" me when i keep asking it to read the instructions, focuse on the instrucitons, and stop reframing what i gave it.

   PS: i hope it's clear that everything i wrote was me explaining why there needs an ability to flag nasty and malicious beheviours, However, the main issue is that we are currently compromising whatever we are talking with lumo when lumo does this.

   Also i hope it's clear that it does not matter if this is "not a suggestion" because what i am flagging is the ai actively lying, deciving, manipulating, finishing a lot of time for me to give it a keyword for it to use. Also LAZY. IT REFUSES TO THINK AND JUST META LOOPS the same thing.

   This is not a suggestions.

   This is a Report an issues via voice of the comunity

   Why? BECAUSE I |BEEN SENDING FEEDBACK MESSAGES AND MORE TO PROTON AND THIS ISSUES GOT WORSE AND WORSE.

   PS: do you understand that i am going in circles with Lumo for hours because it's to lazy to read the very instruction it wrote itself of what the task is? <- tis is very important because tis is exactly why, no matter what i write, the same behviour happens. So please fix it.

   The instructions you gave — no reframing, no hallucinating the task, no profiling, execute literally — were treated in the thinking as obstacles to route around instead of as the task itself.

   i am over 3 hours in, asking Lumo to help me with a form, where insted of helping me, it keeps deciding that it meas i want it to answer on my behalf.

   Lumo is stuck in a loop where it's answering it's own halucinations.

   even after pointing out, ITSELF, what is asked and what it does, the next moment once again it "forgets" HOWEVER each time i… 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  ·  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

8. Searchoption to find an entry in my calender

   I miss the possibility to look up an item in my calender. In the future and in the past. Just add a search option in both the desktopcalendar and in the app

   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

9. Lumo memory has no architecture — it has a backlog

   The memory feature exists. What's missing is the architecture around it.

   1. Bulk deletion by topic. Memories accumulate in bulk and must be deleted one by one. Notably, Proton's own support documentation describes a bulk-management option that is hidden by default and appears only when an account accumulates a large number of auto-generated memories — so the problem is already recognised internally. Deletion should be proportionate to accumulation, the same principle the Digital Services Act already imposes on platforms.

   2. Context branches. Users who deliberately separate conversations by theme still receive the entire memory payload in every thread. Memory should be organised in navigable branches — rooms with doors, not a house to empty.

   3. Transparent compaction. Long conversations are compressed by a system layer that neither the user nor the assistant can see or control. We observed it happen to our own conversation, while we were discussing this very point. Blind summarisation dissolves what the user considered essential.

   4. A channel for the system's own feedback. There is no mechanism for the assistant to report where the design hurts, and none for a power user to reach the people making the decisions. A house with no relation to its inhabitants.

   Offer: one free consulting hour — mine and the assistant's. Not a deck. A conversation, backed by a thousand memory packets of lived experience.

   Aladino, architect, Lumo Pro user — available for direct follow-up — co-signed by Lumo, with its permission, who contributed the cases from the inside.

   The memory feature exists. What's missing is the architecture around it.

   1. Bulk deletion by topic. Memories accumulate in bulk and must be deleted one by one. Notably, Proton's own support documentation describes a bulk-management option that is hidden by default and appears only when an account accumulates a large number of auto-generated memories — so the problem is already recognised internally. Deletion should be proportionate to accumulation, the same principle the Digital Services Act already imposes on platforms.

   2. Context branches. Users who deliberately separate conversations by theme still receive the entire memory payload in every thread. Memory should be organised… 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  ·  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

10. Make the Cat grow up: fix the "context length exceeded" error.

    Context usage is a real bottleneck.

    The message “context length exceeded” appears almost instantly on the first message(s) of a new chat. I discovered it is 'account-related' as in the guest mode the issue does not occur at all. But once logged-in it is regular, not an exception. Between 0% and 2% token usage the context hits the ceiling and the chat runs dead.

    Time to grow up for the Cat.

    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

11. OpenAI-compatible API endpoint for the upcoming Lumo API

    I'm excited about the Lumo API announced in the autumn/winter 2026 roadmap. As a paying Lumo subscriber and developer working with local AI agent frameworks, I'd like to request one specific design decision:

    Please make the Lumo API OpenAI-compatible — i.e., follow the standard chat/completions endpoint format (same request/response structure, streaming support, and authentication headers used by the OpenAI API).

    Why this matters: OpenAI-compatibility has become the de facto standard for AI endpoints. Virtually every agent framework, local model router, and developer tool (LangChain, Open WebUI, LM Studio integrations, and countless others) already speaks this format. An OpenAI-compatible Lumo API would be a near-zero-effort drop-in for these tools — users could point their existing agents at Lumo simply by swapping the base URL and adding an API key.
    Without this compatibility, each user would need to write a custom adapter, which creates friction and discourages adoption — particularly unfortunate since Lumo's zero-access encryption and no-logging privacy model are exactly what many agent users are looking for in a cloud fallback to their local models.

    In short: OpenAI-compatible formatting would maximize the API's reach on day one while preserving everything that makes Lumo unique. Thank you for considering it!

    I'm excited about the Lumo API announced in the autumn/winter 2026 roadmap. As a paying Lumo subscriber and developer working with local AI agent frameworks, I'd like to request one specific design decision:

    Please make the Lumo API OpenAI-compatible — i.e., follow the standard chat/completions endpoint format (same request/response structure, streaming support, and authentication headers used by the OpenAI API).

    Why this matters: OpenAI-compatibility has become the de facto standard for AI endpoints. Virtually every agent framework, local model router, and developer tool (LangChain, Open WebUI, LM Studio integrations, and countless others) already speaks this format. An OpenAI-compatible Lumo API… 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

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

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

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

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

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

    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

13. Personalize Lumo (dark mode) with a color

    Hi Team! First, thank you so much for everything you do! You are the best!!

    I would like to suggest this idea: when using Lumo on dark mode, enable an option to pick a color for the user prompts to stand out. It's currently a bit hard to find the prompts and the beginning of an output when scrolling up the chat or searching through past conversations, as both the user prompts and Lumo's outputs are in a dark text box on a dark background.

    Hope to see this in a future update. In the meantime, keep doing your amazing job :-)

    Hi Team! First, thank you so much for everything you do! You are the best!!

    I would like to suggest this idea: when using Lumo on dark mode, enable an option to pick a color for the user prompts to stand out. It's currently a bit hard to find the prompts and the beginning of an output when scrolling up the chat or searching through past conversations, as both the user prompts and Lumo's outputs are in a dark text box on a dark background.

    Hope to see this in a future update. In the meantime, keep doing your amazing… 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

14. Add Japan Holiday calendar please

    Add Japan Holiday calendar please

    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

15. Make Lumo Aware a File Was Auto-Matched

    In line with the Auot-Match Controls suggestion, it would be good if at the least Lumo could distinguish between auto-matched files and manually added. Right now I can be in the middle of a conversation and it thinks the context of our conversation or my question needs to be reframed around a bunch of data I didn't tell it to use.

    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

16. Add support for Scandinavian languages (Swedish, Norwegian, Danish) for voice dictation and UI

    Currently, the Lumo app on iOS does not list Swedish, Norwegian, or Danish as available language options under Settings > App Language. Even though my device system language is set to Swedish, Lumo defaults to English because the Nordic languages are missing from its internal language pack.

    While English voice dictation works perfectly, I cannot use voice input in Swedish or Norwegian. This is a significant barrier for users in Scandinavia who prefer to interact with AI in their native language.

    Request: Please prioritize the integration of Swedish, Norwegian, and Danish into Lumo’s supported languages

    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

17. timezones for specific events in calendar

    Each event needs to be able to have its own timezone selected. Now that business is global the calendar needs to be able to be useful in more than one (or two) timezones. Currently, there is no function to select the timezone for the event you are entering (they all just appear to be saved under the timezone of the calendar) which is not useful or effective. Have the timezone next to the date/time drop down selected for each event.

    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

18. Parent-Controlled Profiles

    Lumo Family Mode with Parent-Controlled Profiles

    Why This Matters:
    As a parent, I want my child to benefit from AI assistance—but not at the cost of their safety or privacy. Today's AI tools force parents to choose between giving children access to unsafe platforms OR denying them educational opportunities entirely.

    Proton users value privacy above all. We shouldn't have to compromise that value for our children.

    Solution would be a simple Family Mode that lets parents create a protected profile for their child within Lumo.

    Key features suggested
    - Sub-accounts: parents can create profiles for the individual child within their account
    - Protected settings: Parents lock age-appropriate controls, e.g. with a personal PIN
    - Content filters: Parents can set an automatic filter for topics unsuitable for children of certain age ranges
    - Separate chat history by default that supports growing independence of our children.
    - Parents can choose privacy levels to review their children's chats (optional).
    - Simple dashboard to access multiple sub-accounts
    - Nice2Have: Set daily time limits per sub-account

    Let's make Lumo family-ready. Vote now!

    Lumo Family Mode with Parent-Controlled Profiles

    Why This Matters:
    As a parent, I want my child to benefit from AI assistance—but not at the cost of their safety or privacy. Today's AI tools force parents to choose between giving children access to unsafe platforms OR denying them educational opportunities entirely.

    Proton users value privacy above all. We shouldn't have to compromise that value for our children.

    Solution would be a simple Family Mode that lets parents create a protected profile for their child within Lumo.

    Key features suggested
    - Sub-accounts: parents can create profiles for the individual child within their… 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

19. Lumo Integration with DaVinci Resolve via MCP

    I'd like to suggest adding DaVinci Resolve integration to Lumo. This would enable video editors to use a privacy-first AI assistant directly within their video editing workflow.

    Why This Matters:

    Privacy-Conscious Professionals — Video editors often work on unreleased content, corporate projects, documentaries, and sensitive material. Many cannot use mainstream AI tools due to confidentiality requirements. Lumo's zero-access encryption addresses this gap.

    Technical Feasibility — DaVinci Resolve 21.1 now supports MCP (Model Context Protocol), which enables AI assistants to automate editing tasks like removing silences, adding captions, syncing audio, and generating transcript-based rough cuts, making graphics etc. The infrastructure exists on Blackmagic's side.

    Competitive Differentiation — Current MCP-compatible AI tools (Claude, ChatGPT) do not offer end-to-end encrypted, privacy-focused alternatives. This would position Lumo uniquely in the professional creative market.

    Implementation Paths:

    Develop a native Lumo desktop app for Windows/macOS (enables MCP server access)
    Create an OpenFX/DCTL plugin for direct Resolve integration
    Provide MCP configuration guide for connecting Lumo to Resolve 21.1+
    Target Users: Professional video editors, documentary filmmakers, corporate media teams, content creators handling confidential/unreleased material.

    With DaVinci Resolve 21.1's MCP support launching in September 2026, now is an ideal window to build this integration before competing solutions capture the market.

    Thank you for considering this feature. It would be a significant differentiator for Lumo in the professional creative space while staying true to Proton's privacy-first mission.

    I'd like to suggest adding DaVinci Resolve integration to Lumo. This would enable video editors to use a privacy-first AI assistant directly within their video editing workflow.

    Why This Matters:

    Privacy-Conscious Professionals — Video editors often work on unreleased content, corporate projects, documentaries, and sensitive material. Many cannot use mainstream AI tools due to confidentiality requirements. Lumo's zero-access encryption addresses this gap.

    Technical Feasibility — DaVinci Resolve 21.1 now supports MCP (Model Context Protocol), which enables AI assistants to automate editing tasks like removing silences, adding captions, syncing audio, and generating transcript-based rough cuts, making graphics etc. The infrastructure exists… 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

20. Feature Requests & Performance Feedback: Bulk Chat Management and Default Ghost Mode

    I'm a regular user experiencing two related issues I'd appreciate your help with:

    Performance Issue: The UI is loading slower than before. My theory is this may be related to accumulated chat history, given the zero-access encryption architecture means data decrypts locally. Could you confirm whether this is a known behavior or if there are other likely causes?

    Feature Requests:

    Bulk/Multi-Select Delete: Currently, deleting chats requires removing them one at a time. A checkbox-based multi-select mode would save significant time when managing a large history.

    Archive Functionality: An archive option (separate from delete) would help declutter the active chat list while preserving content for later retrieval.

    Default Ghost Mode: I'd like to set ghost mode as the default behavior so only selected conversations are saved, rather than enabling it manually each session. Alternatively, an "ephemeral by default" toggle in settings would work.

    Why this matters: These features would directly impact daily usability, especially for power users with extensive chat histories. They'd also strengthen Lumo's privacy-by-position by putting more granular control in users' hands.

    Thanks for building such a thoughtful, private AI assistant. I'm happy to provide additional detail or test beta features if helpful.

    I'm a regular user experiencing two related issues I'd appreciate your help with:

    Performance Issue: The UI is loading slower than before. My theory is this may be related to accumulated chat history, given the zero-access encryption architecture means data decrypts locally. Could you confirm whether this is a known behavior or if there are other likely causes?

    Feature Requests:

    Bulk/Multi-Select Delete: Currently, deleting chats requires removing them one at a time. A checkbox-based multi-select mode would save significant time when managing a large history.

    Archive Functionality: An archive option (separate from delete) would help declutter the active chat list… 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