Lumo
264 results found
-
Latest highly efficient open source LLMs suggestions.
I would like to suggest some of the latest, cheap and very powerfull llms, so that you can replace current LLMs for better ones, to improve consistency and manage costs.
hf.co/Qwen/Qwen3-Next-80B-A3B-Instruct
hf.co/Qwen/Qwen3-Next-80B-A3B-Thinking
hf.co/openai/gpt-oss-120b
hf.co/zai-org/GLM-4.5Vplease consider using them in lumo instead of the current models
10 votes -
Add support for de-googled devices
Lumo is unsupported without Google Play Services. Can't start the application, blocked during boot.
Using LineageOS. Should work without Google.10 votes -
public URL parameter that pre‑loads a specific prompt
It would be nice to have a public URL parameter that pre‑loads a specific prompt, such as https://lumo.proton.me&q=my_specific_prompt because this would make it possible to define "search"-shortcuts in Browsers or for example in krunner under Linux to open Lumo directly with a starting-prompt.
10 votes -
Create tentative/optional events in Calendar
I need to track events where my attendance is optional, and I may be the creator of that event.
If I get an invitation to which I have not replied, the event is marked tentative, but if I create it that is not an option. It should be.
10 votes -
Android Intent Support or API for a Reading App Integration
Dear Lumo Team,
I'm the developer of @Voice Aloud Reader, a popular Android ebook/document reader app. I'm interested in integrating AI-powered book summarization features that respect user privacy - which makes Lumo an ideal solution.Current Approach & Results: I've tested Lumo with book chapters (up to 100KB text) by manually copying/pasting content. The summarization quality and literary analysis are excellent - exactly what my users need for "remind me what happened" scenarios when returning to books after breaks, having questions to answer, discuss the book etc., but copy/paste workflow is far from perfect.
Feature Requests:
1.Intent.ACTION_SENDSupport: Allow…10 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 ....
9 votes -
4) Lumo Pages
Lumo Pages: Collaborate on documents with Lumo (either as a product in Lumo or Proton Docs)
Next post: https://protonmail.uservoice.com/forums/932842-lumo/suggestions/50637332-5-image-uploads9 votes -
Do not format user inputs
Currently, in Lumo my user input is formatted in e.g. markdown when the app "recognizes" that it is markdown. However, it is not. I am working with files that have comments at the top starting with # and it is falsy detected as markdown. Please keep the user input as raw text.
9 votes -
Allow external files as data sources
It's annoying that I have to download publicly available files in order to upload to a Lumo session. Since you have a web search option, I know you have access to the web. Please add functionality that allows us to point to URLs to use as data sources. For example, I have some markdown files in my public GitHub repos i would like to use as a data source
9 votes -
Automatic calendar for displaying contact birthdays
Please add automatic calendar for displaying contact birthdays. This is a feature in Google Calendar and is the only reason I still hang on to that app
8 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?
8 votes -
Multiple personalization settings
Would it be possible to add different personalization settings and switch between them depending on how lumo is being used?
8 votes -
Better Mathematical Expression Display
Currently, the mathematical expressions produced by Lumo in responses, are not legible. They are generally in raw latex syntax, which is absolutely unsuited for display purposes. They should be rendered either as legible plain text (probably bold-faced for distinctiveness) or as document-typeset graphic math expressions.
8 votes -
Feature Request: “Auto‑Websearch” / “Always Enable Websearch” in the Personalization Tab
Hey Proton team,
thanks for the awesome Lumo 1.2 update! The new personalization options are super handy. To make Lumo’s answers truly real‑time, could you add a toggle under Personalization called “auto‑websearch” (or “always enable websearch”)?
When turned on, Lumo would automatically pull in up‑to‑date info for any query that needs fresh data—no extra steps required. This would be a game‑changer for users who rely on accurate, real‑time responses.
Appreciate the consideration!
8 votes -
Read Answers Out Loud
Add a button where I can hear the answer being read out loud. Make it be able to play in the background. Like in Perplexity.
8 votes -
Use better open-source ai models.
Dear Proton Team,
I would like to propose integrating several high-quality open-source AI models into the Lumo platform. These models align with Proton’s core values of privacy, transparency, and user data sovereignty, while offering excellent performance and flexibility.
The recommended models include GPT-OSS 120B, LLaMA 3, DeepSeek-V3, Mistral 8x22B, and BLOOM. These models stand out because they are open source, enabling complete self-hosting and customization. This means Proton can maintain full control over user data, keeping all processing within secured European data centers, aligned with Proton’s zero-access policy and strong privacy commitments.
GPT-OSS 120B offers powerful capabilities close to proprietary…
8 votes -
Enable Lumo to Integrate with iOS MCP Mode for Voice Assistant Capabilities
In the recently released developer beta of iOS 26.1, references were discovered in the system files indicating that Apple is preparing support for MCP (Model Context Protocol). While Apple has not officially announced this feature yet, these findings strongly suggest that MCP integration is coming soon.
This presents an exciting opportunity for Proton to make Lumo more powerful and accessible by enabling it to function as a third-party AI voice assistant within iOS. Users could directly invoke Lumo at the system level, similar to Siri, but with Proton’s strong emphasis on privacy and security.
Why this matters:
- Privacy-first alternative:…8 votes -
Allow switching models to better models for plus subscribers
Add a model switcher for plus subscribers that lets you choose between powerful models like gpt-oss 120b, deepseek v3.1, Mistral small and medium, kimi K2, Qwen, etc.
8 votes -
Pull to refresh chats and history
I use Lumo across many devices.
Currently I have to force quit iOS and Android apps for them to update with the latest history.
I would love to see pull to refresh in the history section.
I would also expect the chat to pull all updates when selected from the history, but this is not currently the case - it does not show activity from another device.8 votes -
Make the principal ideas, strategies, and values transparent, that drive your safety controls for lumos answers.
Maybe it exists somewhere already. But I would like an easy to find page, where the ideas and strategies behind the safety controls e.g. denying certain answers from lumo are described. I don't need details, just the major Idea about what values, or dangers you're trying to protect/avoid. Just a general Idea what I can expect not to get an answer from lumo for. I think safety controls are ok, and maybe in general necessary, but I'd like to have some tranparency about it.
8 votes
- Don't see your idea?