Lumo
- or
No existing idea results
- ~ No ideas found ~
227 results found
-
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.
9 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 -
Live Translation Capabilities For Lumo
Lumo, as a private AI, is primed to be an excellent assistant for users to have in their daily lives. This includes the ability to accurately translate pages and other media for the user, without compromising their media data, metadata, and contributing to the data collection of other larger and gluttonous chatbots that have this capability, like Google Gemini and OpenAI's ChatGPT.
3 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 large models but without API dependency and high ongoing costs. LLaMA 3 is dialog-optimized and supports long context windows, enhancing user interaction experience. DeepSeek-V3 presents a highly efficient mixture-of-experts architecture with exceptional scaling potential. Mistral 8x22B balances performance and resource demands, fitting well with Proton’s infrastructure. BLOOM provides multi-language support and responsible open-source licensing, broadening Lumo’s global reach.
By choosing these models, Proton can deliver a privacy-first, performant AI assistant that scales from edge devices to enterprise deployments, all under Proton’s full control. This approach boosts user trust, reduces dependency on third parties, and aligns with evolving global privacy regulations.
Thank you for considering this proposal.
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…
5 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?
4 votes -
Provide a way to keep accounts completely disconnected from AI
No AI, nor company that integrates it, truly cares about user privacy and security. Frankly it makes me reconsider my choice to move to Proton. It's certainly prevented me from moving to any paid tiers
3 votes -
Using better open-source/weight AI Models
Hi everyone,
I am writing this because I think Lumo has so much more potential. Imagine them using a 1 trillion parameter Chinese open-source/weight AI model like it would give them so much more flexibility in new features and accuracy of up-to-date data. They could even train an own AI model that they can then use like OpenAI uses ChatGPT as an multimodal AI model without having to rely on others creating open-source/weight AI models for them to use plus they could customize it perfectly for privacy, speed and accuracy. This own AI model could be based of some other open-source/weight AI model or could be designed specifically for Protons privacy focused servers. They could even integrate an own search engine into this customized model, enabling it to use auto websearch so you don’t have to actively turn it on in every new conversation and could be trained for not only text but also image generation and upload, video generation and upload, text to speech, speech to text and even a Live mode like Gemini, ChatGPT and Perplexity.
Hi everyone,
I am writing this because I think Lumo has so much more potential. Imagine them using a 1 trillion parameter Chinese open-source/weight AI model like it would give them so much more flexibility in new features and accuracy of up-to-date data. They could even train an own AI model that they can then use like OpenAI uses ChatGPT as an multimodal AI model without having to rely on others creating open-source/weight AI models for them to use plus they could customize it perfectly for privacy, speed and accuracy. This own AI model could be based of some other…
4 votes -
Unlimited chat with the free version
It would be very nice if there’s not restrictions on how many messages you can send with the free version (like every other major chat bot app)
5 votes -
short key for new line / marker blok to enter code
When I am using lumo to help with coding, I need an option to make a clean new line, to activate the marker box or to enter code the right way. The enter key leads to submitting my chat, and shift + enter or alt + shift + enter won't work, as the chat interface does not interpret them as 'new lines'. This makes it impossible to enter code. The only work around that works is entering the whole marker box (including markers) in notepad, copy, paste.
4 votes -
Easy button to submit selected conversation as correction
When I get a known incorrect answer from Lumo, I give it web access and lead it to find and report to me the correct information. There should be an easy button for me to submit just that discrete conversation to proton to correct the underlying knowledge base. All within the Lumo platform. I dont have time to go to another feedback or supprt forum, login again, go back and screenshot the incorrect information, paste that into the feedback platform, go back again and screenshot the correct information, switch to the feedback forum and paste in the corrected info, go back yet again and compile the source citations and finally paste that in to the feedback,feature request, or bug report.
It would be far easier to be able to even start a new conversation, walk lumo through it again, have lumo cite its sources, then submit just that single discrete conversation as a correction request.
I dont want Lumo learning from me all the time and sucking up my info. But I also dont want to have to teach it the same thing every time i use it.
A local memory could do it, but I'd rather be able package up a discrete conversation and proactively improve the underlying dataset for everybody.
Thanks for considering!
When I get a known incorrect answer from Lumo, I give it web access and lead it to find and report to me the correct information. There should be an easy button for me to submit just that discrete conversation to proton to correct the underlying knowledge base. All within the Lumo platform. I dont have time to go to another feedback or supprt forum, login again, go back and screenshot the incorrect information, paste that into the feedback platform, go back again and screenshot the correct information, switch to the feedback forum and paste in the corrected info, go…
6 votes -
Floating widget
Add the option to enable a floating Lumo widget that can help me writing better, answer chats, or summarize long texts.
8 votes -
Import chat history from other LLM
Please allow us to import chat history from other big commercial cloud hosted LLMs to ease transition and not lose all the information prior LLMs gleaned from us, what we are doing, what is important to us, etc.
4 votes -
Multiple Lumo agents
Now that its possible to personalize Lumo, I also wish for the opportunity to create multiple different Lumo Agents, so I could for example have one developer agent, one recipe agent and so on.
5 votes -
Repair the sound
Repair app sound
3 votes -
lumo.ai for quick access > lumo.proton.me
Also: https://lumo.ai/search?q=%s site search support
5 votes -
Ability to choose which LLM (AI model) will answer for all answers
Add a button that let's you choose which LLM you want all the answers from.
5 votes -
Chat knowledge - Proton Docs not working
I now have to download Proton Docs to my computer as a txt file and then upload it to Chat knowledge.
7 votes -
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 best that Data Souverenity can offer. Best DanielA 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 -
Add Kimi K2 thinking
huggingface.co moonshotai/Kimi-K2-Thinking
Hi! would make sense to have it as a main OSS model as it is the SoA (the most "intelligent" one that is also open source!)
4 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
- Don't see your idea?