Lumo
311 results found
-
Personas
A fantastic feature is "Personas", which already exist in GPT-5 or CoPilot. In my opinion, personas should be permanently stored beyond a conversation. For example, with the term "Remember that Eva, my team assistant, makes suggestions to me about stakeholder management for my customer base and does the LinkedIn analysis. This would enable me to continuously expand an AI assistant and my knowledge management.
I have asked Lumo+, but Lumo+ can only remember my requests or orders within a conversation. Or is there another way to set different personas?
Keep up the good work, Lumo+ is great fun and the…5 votes -
delete button (outside of settings)
Can you please move the delete button out of the settings and into the sidebar, or somewhere? I know lots of people keep AI chats, I don't. It seems like extra steps to hide it in settings.
2 votes -
add a clear command to clear the current chat
I'd like to be able to type "clear" or "clear chat" and have Lumo wipe the current conversation.
I tried it, and the AI knows what I mean but can't do it.
2 votes -
How about ditching these stupid time limited upgrade offers?
Sick of seeing them,desperate and bloody annoying!
2 votes -
Ease Navigation through a Chat: Chat Outline
At the moment, I am finding it difficult to navigate through the information in a chat when it has several questions.
The biggest problem I have is finding a specific question again in the chat, because my questions are much shorter than Lumos's answers. So, when I want to scroll back to a particular question, it takes me a long time to read through the chat.
The same thing happens when I'm looking for a specific part of an answer. First, I have to find the answer, and then the relevant section. This is time-consuming and mentally exhausting.
Of course,…2 votes -
Apple Shortcuts
Can we please get Apple Shortcuts for Lumo :D
I’d love to migrate my current automation away from GPT
6 votes -
First reply is occasionally given with no words
I find on a fairly frequent reoccurrance that when I ask Lumo a question, it simply spits sources back at me with no words to explain the answer. I have to follow up with a "Please expand" reply in order for it to finally give me an answer. It's not the worst thing, but a little annoying
5 votes -
Geolocation for the location field
It would be so nice for the location field in the calendar to search for and populate a location (e.g. I type in the name of a store & city name, and then it gives me a few options to select, at which point it then replaces what I've typed for search with an address)
3 votes -
Allow pasting underscores
I want to paste a regex
.*_([^_]+_[^_]+)$into chat. As soon as I paste, the underscores are removed and my text is converted to italic. I am unable to create a fenced code block with triple backticks. If I create a code block with single backticks and then paste my regex inside, it breaks the code block in half and inserts non-code text.- If the chat box is going to magically remove characters, CTRL+Z should put them back
- I should be able to create a code block, and paste text inside that code block without any magic
6 votes -
File types and size / unsupported file types
The current file types to upload f.e. images don’t work well and constantly I’ll get the message of “unsupported file type” in the pop-up window and that’s a false flag. They are all files types that Lumo support. I can open those files without any problems within Proton Drive or iCloud. Same issue occurs on Windows desktop, iPhone and iPad. Drag and drop makes no difference.
The file size is also an issue, limited to 10MB and I have a subscription. An average photo is already more than that. Files stored in Proton Drive can be uploaded with a maximum…
4 votes -
STT voice transcription run on-device, not sent to Google.
STT voice transcription run on-device, not sent to Google.
4 votes -
Lumo prompt-library
Create and save prompt to reuse them with different parameters.
3 votes -
Feature Request: Exclusive Access to Larger LLMs for Lumo Plus Subscribers
I would like to propose a feature specifically for paying Lumo Plus subscribers: the ability to enable Lumo to use larger LLMs (such as GPT-5, GPT-5 Thinking, Gemini 2.5 Pro, Grok 4, Claude Sonnet 4.5, etc.) for processing queries. The core idea is for Lumo to act as a privacy barrier—protecting user data—while still taking advantage of the advanced capabilities of top-tier models for those who subscribe.
This enhanced feature should be strictly limited to users who actively pay for Lumo Plus. Free users would continue using the current models and would not have access to this option.
Lumo Plus…4 votes -
Feature Suggestion: Built-In Email Productivity Tools for Faster Daily Workflow
Many ProtonMail users handle a high volume of emails every day and often need small productivity tools to speed up their work. A built-in panel offering simple utilities like quick text formatting, a snippet creator, a link checker, and an email content helper could make daily communication much faster and easier.
I’ve created an external toolbox at https://toolinq.com
that provides similar utilities. If ProtonMail adds a simplified version of these features directly inside the inbox, it could make the overall user experience even more efficient.3 votes -
Multiple Personalities - more control & community templates
Currently, under the 'Personalization' you can create ONE personality per user. Depending on my task at hand I need more control over the expected output. As currently there is not really a good way to configure the expected outcome. (e.g. how 'creative' the model can be or how strict it needs to adhere to the input).
This feature would also really benefit from (community) templates which must be editable for better control.
4 votes -
[Lumo generated] Feature Request: Model Routing Transparency & Analytics Dashboard
Here is a structured feature request drafted for the Proton/Lumo engineering team. It incorporates your specific insights about metadata injection, routing transparency, and the potential for usage analytics.
Feature Request: Model Routing Transparency & Analytics Dashboard
Priority: Medium-High (User Trust & System Optimization) Component: Lumo Core / Routing Infrastructure Date: April 5, 2026- Executive Summary Currently, Lumo utilizes a multi-model architecture where requests are routed to specialized models (e.g., code, creative, reasoning) automatically. However, this routing is opaque to the end-user. Users cannot verify which model handled their request, nor can they provide granular feedback on model performance.
This feature…
1 vote -
starting over from the beginning is annoying
It's very annoying to have to scroll to pick up where I left off in a long chat. Please revert to the way things were before or add a setting for those who want to start the chat from the beginning.
3 votes -
proton needs to collab with greenpt
proton needs to collab with greenpt.ai to make there AI more sustainable (there AI work now better then lumo)
3 votes -
Hierarchical Multi-Task Constraint Optimization Engine
I am writing to propose a mission-critical feature to address severe hallucination and performance degradation when processing complex, multi-project prompts with nested constraints.
Problem Statement
Our system currently exhibits fundamental breakdowns when handling prompts containing multiple distinct projects with interdependent constraints and domain-specific requirements:
Critical Performance Drop: Benchmarks show accuracy falling below 10% compared to single-task prompts. When processing 32+ nested hierarchical tasks (e.g., "Project Z's Project B's Project D"), performance degrades to GPT-3 equivalence levels.
Constraint Isolation Failure: The system cannot reconcile project-specific constraints with global constraints simultaneously. Complex nesting ("Project A's Project B's Project 9") causes complete context…
2 votes -
Add custom domain for lumo
Instead of accessing lumo.proton.me , users can create a custom domain for lumo access
5 votes
- Don't see your idea?