Lumo
630 results found
-
"Voluntarily disclose" some chat with Lumo to help training
One of the disadvantages Lumo faces compared to its rivals is the shortage of training data. Why not offer Lumo users (both free and paid) the option to allow some of their chats to be used for training? For example, add a button at the beginning or end of each chat asking: "Do you want to donate this chat to help train Lumo?"
To encourage participation, Proton could offer a small reward for every chat donated—like a few minutes of premium usage or temporary access to advanced features.
Importantly, all donated chats would be stripped of any user-identifying information before…
11 votes -
iOS 27+ Siri Integration
The IOS 27 beta is releasing tomorrow June 8th with a revamped Siri that supports the third-party chatbots Claude, OpenAi and Gemini. I have no desire, as do many of us to use any of those apps due to privacy issues. There is no good reason that a security focused AI should be excluded from that list, in fact it should be at the top of the list in this day and age. To me this is a must have. I don’t appreciate being forced down a road that is going to directly impact my reliance and trust in my…
10 votes -
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.
6 votes -
Allow Lumo to use it's general memory inside of projects (or at least an option to toggle this)
Lumo's new memory feature is great, but if we had the option to allow Lumo to use the general memory it gets from our chats inside of projects, that could be really helpful for not having to repeat the same information multiple times, and potentially cut down on time spent tuning the memory in the project to what is needed.
9 votes -
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.
…
5 votes -
Organize Previous Chat Sessions
I would like the ability to move and sort chats. For example, I find myself starting a change session, and then once getting into it realize it should be part of a project. So the ability to move existing sessions to organize them would be very helpful.
9 votes -
Ability to delete portions of chats that are not useful
It would be great to have the ability to select and delete portions of chats that are not useful or were perhaps irrelevant to the query intent so as to streamline a chat to only contain the most relevant information for future reference.
13 votes -
Shared Project Folders — Persistent Files Across All Chats
Feature Request: Shared Project Folders — Persistent Files Across All Chats
Category: Feature Request
Submitted by: fretmusicThe Problem
Lumo’s conversations operate as isolated silos. When I’m working on a long-term project across multiple chats—whether it’s home automation, coding, or research—I have to repeatedly paste my project’s “master status document” into each new conversation to keep Lumo updated. If I forget, or if the document is outdated, the new chat starts with stale information and offers advice that’s no longer relevant. Even worse, the knowledge built up in past chats is essentially locked away—neither I nor a new chat can…
4 votes -
Manual control of per-chat project knowledge
As an alternative to Lumo chats ingesting project knowledge automatically from the files available to the project, it would be great if there was a "Manual" mode.
The user could selectively add and remove which files are used, as the automatic features sometimes needs a few tries to get everything right. This is especially helpful to avoid the chat auto-ingesting metadata files from external project configurations.
6 votes -
**Feature Request: Research Integration & Source Transparency**
Feature Request: Research Integration & Source Transparency
As an engineering professional using Lumo for medical/pharmacological research, I'm requesting:
1. Research-database integration for web search: Preprint servers (medRxiv, bioRxiv), clinical trial registries (NCT database), and PubMed with full-text retrieval—not just consumer health pages. Current gaps hurt real-world workflows (e.g., GLP-1 titration research misses >1 year of data).
2. Visible source trail: Inline citations linking claims to specific retrieved passages so technical users can audit responses faster.
3. Fresher model training: April 2024 cutoff creates systematic lag in fast-moving domains like pharmacology and longevity science. Request more frequent retraining cadence.
4. Domain-aware…
4 votes -
RTL Text Direction Support Request for Lumo UI
Lumo currently doesn't support right-to-left (RTL) text direction in the UI, neither in the input nor output fields.
It would be ideal if the app automatically detects and applies the correct text direction based on the first word of each paragraph. For example, if a sentence begins with an English word, it would display left-to-right; if it starts with an Arabic word, it would switch to right-to-left.
This feature (automatic direction detection) is already implemented in Telegram, and adopting similar functionality would greatly improve the experience for multilingual users.
7 votes -
Think and respond in the user's English variant, with full regional settings for Lumo (units, currency, time zones + more)
Lumo has language selection, but no regional settings governing how it formats measurements, currency, dates and times in its responses, or how it reasons within them. For users outside the US this is constant friction. Critically, these settings should shape how Lumo thinks, not just how it writes: drafting a document in British English should mean composing it in British English from the first word, rather than generating American English and converting the spelling afterwards.
Requested options, ideally as one Region preference with independent sub-settings:
English variants with full grammar, punctuation, vocabulary and idiom rules (en-GB, en-AU, en-NZ, en-IE, en-CA,…
3 votes -
Lumo Integration to Read Encrypted Emails, Calendar, via On-Device Processing
I want an AI assistant (Lumo) that can automatically read my Proton Mail inbox and execute actions based on preset rules (e.g., sorting, summarizing, drafting replies, flagging urgent items, consolidating multiple emails into one for review). I understand this requires on-device processing to maintain zero-access encryption. Currently, I have to manually copy/paste emails. An automated, privacy-preserving workflow would be a game-changer for productivity. Lumo needs more gemini like functionality in the Proton product space.
6 votes -
Integration for Lumo to Home Assistant home automation software
Add integration to Home Assistant. This would allow Lumo to help with configuration and home automation. Also, its a very tech community with lots of support on YouTube which will help spread the Proton brand further.
5 votes -
Add files or attachments to calendar events
I see "Add Proton Drive Files as attachments in Proton Calendar events" is a present request - however, it would be great to be able to add attachments regardless of Proton Drive usage.
For example, I have a ticket to an event in my pm.me email. It would be great if I could just add the ticket to my calendar event and have all info housed in one app - one source of event truth.
Another use case: adding text documents to meeting events so the agenda is attached to the event and more readily accessed.
8 votes -
Allow multiple folders in projects
Currently (Lumo Plus, 2026-07-29), only a single folder can be associated with a project. That makes it impossible to organize the knowledge base, e.g. into personal data, role, client, project for client, and reuse this data in other projects without duplication.
7 votes -
Real‑time audio conversation
One of the features I was using—and I see people using—is audio‑based conversation with the models. The main goal is to practice languages by asking the model to simulate a dialogue, then receiving feedback and corrections. This is a feature I would love to have in Lumo, because I don’t feel comfortable sharing my voice with Big‑Tech models or companies that don’t respect privacy.
49 votes -
Edit/Remove content pasted in to project chats from project files
Right now if you paste a a large enough block of text in to a project chat it coverts it to a text file and it will be added to the over all project context that Lumo has access to. But, once this content is pasted in to one chat, even if that chat is deleted the pasted content text file from the still stays in the project knowledge and all future chats will then use that as context for the project and it cannot be edited or removed.
This request is to allow us to edit/remove these pasted text…
6 votes -
Higher file upload limits
I have a Plus account which has a listed limit of 25 mb, and have run into issues where the system gives an error message saying that I cannot load more than 10 mb; please increase file size up load limits
47 votes -
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…5 votes
- Don't see your idea?