Lumo
593 results found
-
Support MCP Integration
Lumo should support the use of Model Context Protocol servers in a fashion similar to Claude Desktop. This should be done with DXT, the Desktop Extensions package format, for ease of support. It would be acceptable if Proton were to select a limited number of offerings in this area. There MUST be a developer option where we are permitted to use the direction JSON configuration and any available server, but this should be community forum supported, with no direct assistance from Proton.
I have been evaluating the offerings in this space the last two months and I released an MCP…
98 votes -
Letting programmers use Lumo in a code editor
As a developer, I added extensions to my code editor. Some companies offer extensions to use their AI models directly in a code editor, like "Claude" extension in VS Code. Being able to work with the AI within the code editor is a huge time saver.
It would make Lumo an even more useful tool for programmers and help improve their workflow.
Could you make the same with Lumo?
53 votes -
Disclose weekly limits
At present, Lumo has a weekly limit on the free tier. The problem is, a user has no idea what this limit is, and only find out when they hit it. They also don't know what it'd reset. Proton should be providing transparency on this, not just a "surprise, you hit quota, buy or come back after some undisclosed period of time".
60 votes -
Feature Request: Integrate Lumo into Proton Docs for Intelligent Writing Assistance
Dear Proton team,
I’d like to propose adding Lumo as an integrated writing assistant within Proton Docs. By leveraging Lumo’s advanced language‑model capabilities, users could:
Automatically scan documents for grammatical errors, spelling mistakes, and style inconsistencies.
Receive contextual suggestions to improve clarity, tone, and overall readability.
Benefit from the same AI‑driven assistance currently offered by the Scribe assistant in Proton Mail, but applied directly to collaborative documents.
This integration would enhance the productivity of Proton Docs users, reinforce Proton’s commitment to privacy‑first AI tools, and create a seamless experience across the Proton ecosystem.
71 votes -
Lumo Conversation Mode
It would be amazing for Lumo to have a full conversation mode, similar to other LLM apps, where you are able to speak to Lumo, Lumo will realize you are done speaking and reply, and then wait for your next reply...etc.
67 votes -
Ability to regenerate a Lumo response into a separate chat
Sometimes I just want to be able to split off a certain response into a separate chat. This would be helpful in instances where I want to preserve partial context from a certain point and diverge without continuing that line of thought in the same conversation.
13 votes -
Ability to run local models
Some small models are capable to run locally on phones. This would be great for privacy and also as a free alternative for the more powerful paid LLMs.
95 votes -
Tasks
I'd really to have a tasks feature where I can set up quick to-do lists as well as quick notes. Currently setting most of these up as calendar events to remind at a specific time. This is a quick fix but can be a bit much on the fly. Something like how Google Tasks / Notes work. This could also be a re-occurring task (like take out trash) that doesn't necessarily clutter up the calendar.
12 votes -
Bring Ghost Mode button back to the main chat homepage
The Ghost Mode button was originally on the chat homepage, making quick access easy. Now moved to the Lumo side menu, it requires an extra step. While the side menu is tidy, it lessens the feature's visibility and slows the workflow for users who frequently rely on Ghost Mode.
It would be great if Proton could restore the Ghost Mode button to the main chat homepage, near the "New chat" button, while optionally keeping a duplicate in the side menu for consistency. Alternatively, it would add a setting that allows users to choose where the Ghost Mode button appears.
9 votes -
Add "Default digital assistant app" capability on Android
Android has the option to change your default assistant app. Proton should add this capability for Lumo. A partial screen view of the app might be necessary for this to work smoothly as well.
69 votes -
Provide a Lumo CLI
Proton should provide a Command Line Interface (CLI) to Lumo, similar to competitors's CLI tools like Claude and Gemini. There is an existing idea here [1], however that one is specific to a coding assistant. That's great, but other uses (like summarizing local text files, processing local images, etc. within a terminal) would also be very helpful and appreciated.
11 votes -
Option to "Delete All Chats EXCEPT Starred / Favourites"
In addition to "Delete all chats", I propose that there should be an option to "Delete all chats EXCEPT Starred / Favourites".
As my Lumo fills up with chats, I star the ones that I presume I would still like to come back to. As for the rest, I would like to periodically clean house by wiping them all out.
Presently that would mean deleting all of the non-starred chats one-by-one, which is unnecessarily frustrating.
This new option would regard favourites as "pinned" and leave them in place while deleting the rest.
84 votes -
It should be more aware of its own capabilities.
The model keeps telling me its capable of doing text-to-image, stating that theres a feature where there actually isnt one.
77 votes -
Lumo doesn't know it's a cat!
I asked Lumo if it was a cat and it denied outright that it was a purple cat. Poor Lumo.
73 votes -
Lumo can't see into Linked Drive Folder in Project Knowledge
The option is currently there to link a Proton Drive folder, but Lumo can't reliably look at files stored there, or notice if they are updated to a new version. Keeps insisting on having a file uploaded directly. However, if it's named the same as a file already in the folder, it fails instead of overwriting / updating.
11 votes -
Guided Learning
I would like to have a feature to set Lumo into "Guided Learning Mode", where the LLM would act like a mentor, instead of just giving the whole answer to you.
It should behave similar to how Gemini has implemented "Guided Learning", where it tries to give open ended questions based on the question asked.
I think this would be good for students or anyone that is learning new concepts, but don't want it to feed you the whole answer to you, almost like your own personal mentor/lecturer.
77 votes -
save transcript as pdf
I've come to appreciate the capabilities of online research using your AI assistant Lumo and use it quite often and also find some of the resulting conversations interesting enough to save.
However, the format produced by copying the transcript to the clipboard is rather unattractive, which is why I ultimately then ask Lumo to output the text again in Markdown format so I can then convert it to finally to pdf.
It would be very helpful if Lumo also offered a button to perform these operations automatically and make the resulting file available for download.
19 votes -
Move Existing Chats into Projects
Dear Proton Team,
I'm writing to respectfully suggest adding a feature that would greatly improve the organization capabilities of Lumo Projects.
Currently, there is no clear way to move an existing conversation into a Project workspace. While Projects are designed as dedicated spaces for bundling chats, files, and custom instructions, users cannot transfer past conversations into them. This creates a significant organizational gap.
Many users naturally accumulate conversations across different topics and workflows over time. Without the ability to move these conversations into relevant Projects, they remain scattered and disconnected from the context where they belong. This limits the utility…
9 votes -
Allow Reordering of Projects
Currently, the five most recently created projects are listed under the Project section; however, these may not be the most frequently used. It would be great if we could rearrange them to allow easy access to favorite projects.
17 votes -
Increase Lumo context window
Hello
Currently lumo context window is too small 3k token on the fast model and 13k token on the deep think model
ChatGPT perplexity and all other AI company their big model hold up to 130k token
Im having problem with long complex conversation where lumo forget stuff too fast forcing me to repeat or to re paste tons of data leading to a frustrating experience feel like talking to a dementia person ....
45 votes
- Don't see your idea?