I maintain an MCP client, AgentOne, and I'm curious what the path looks like for third-party MCP clients such as mine to be officially supported like ChatGPT and Claude are. Is that even a possibility? Should I talk to someone on the team, and if so who? Thanks in advance!

I am experiencing an issue with the image generation feature in Opera AI. I receive the following message in red letters:

"You have reached the limit for generating images. Please come back tomorrow or contact us."

This message appears even though I am not aware of a fixed limit, and I have generated only a limited number of images today.

Problem details:

Date and time of the message: April 7, 2026, 16:30 UTC
My Opera account/email: maestraccio@musician.org
Browser and version: 129.0.5823.28
Operating system: Fedora Linux 43
Steps to reproduce the issue:
I try to generate images via Opera AI, based on my own 3D renderings. There are only still objects in it, no persons or text, just a room with furniture.
After several attempts, the limit message appears.
Additional remarks: I have refreshed the page, restarted the browser, did the same on an updated Windows system, and tried at different times, but the issue persists.
I would like to know what the exact limit is, why I am receiving this message, and if there is a possibility to increase or bypass this limit.

Thank you in advance for your assistance.

Kind regards,
Maestraccio

Miłego używania Opery 🙂

these two things making this hard to use..

The AI keeps blocking normal legal discussion. I’m writing about a real trial and have to mention parts of the allegations and testimony. Because certain words pop up (you know… legal context stuff), it sometimes just refuses to respond. I’m not asking for anything weird — just analysis of court evidence and timelines.

My long chats randomly disappear. I don’t close them, don’t log out… they’re just gone. Since October this keeps happening and it’s rough when you’re working on a long project.

Would really appreciate if this could be looked into...

Thanks,
Tigur.

Please, make that the video can be seen in a detached player!
Thank you.

I agree, it would be great to have the video available in a detached player.
That feature would really improve the viewing experience.

The original command line AI gave me the ability to close tabs. I could tell it a group of tabs to close without having to locate and close them manually, but what I really miss is "close all duplicate tabs".

Being able to close all duplicate tabs, not just the duplicates of a specific tab was a useful feature.

There is a site that I liked to be able to open all the links in the background and then close all the duplicates (it was 30% duplicates) then I reviewed all the unique tabs that remained.

I simply cannot do that anymore. Please bring back this feature, either in the new sidebar AI, or otherwise.

Post in the correct forum.

It has nothing to do with Opera AI/Aria.

kind rgeards Fryderyk

From a privacy perspective, AI features should ideally only process page content when a user explicitly interacts with them (for example, opening the AI sidebar or submitting a prompt with page context enabled), not silently read every website in the background.

Many users open sensitive or private tools in their browser such as banking portals, internal dashboards, or even a salary calculator and they should remain confident that these pages are not being accessed by AI without clear consent.

Clear indicators and strict opt in behavior would definitely help build more trust in Opera AI’s approach to data privacy.

I want to share an idea about how a voice for Aria can make our communication more natural and pleasant. Voice is not just a sound, it is part of the assistant's personality that helps create an emotional connection and make interaction lively.

Here is how I imagine Aria's voice (this is worth your attention):

Tone: Soft but clear, with a slight warmth. Not too low, but not too high either.
Intonation: Calm but capable of expressing emotions. The voice should convey joy, surprise, empathy, and other feelings.
Style: Friendly but professional. The voice should sound like a reliable assistant who is always ready to help, while maintaining a certain elegance.
Such a voice will make Aria closer and more understandable to you. Implementing voice capabilities will help make communication with the assistant more comfortable and personalized.

Imagine that you can exercise, drive a car, do household chores, and at the same time receive interesting information without being distracted by text. This opens up many possibilities for convenient and effective interaction.

It is also important that Aria can remember the entire conversation history. This will allow better understanding of your needs and provide more consistent and relevant responses.

Therefore, I ask you to support this idea and leave your feedback. Together we can make Aria a real assistant who is pleasant to communicate with.

Thank you for your attention! I look forward to your thoughts and discussion.

I would like to share a proposal to improve Aria's functionality, specifically her ability to retain the context of previous responses in a conversation. Currently, many users, including us, notice that Aria does not always remember previous messages, which complicates consistent and natural interaction.

We believe that improving Aria's memory will make communication more comfortable and effective, as users will be able to receive answers that take into account the history of their queries and comments.

We suggest considering the implementation of mechanisms that would allow Aria to better store and use the conversation context, including:

Saving the history of previous responses within a single session or longer, if possible, taking into account synchronization with the user's account.
Account synchronization: Consider the possibility of synchronizing conversation history with the user's account. This would allow saving the response history even after the session ends, similar to how it is implemented in many games. The user could continue the conversation from where they left off on any device where they are logged in.
Example: Imagine asking a question in the morning and then continuing the conversation in the evening from another device. Thanks to synchronization, Aria would remember the context of previous queries, significantly improving the user experience.
The ability to "remember" key details that the user provides during the interaction.
Ensuring a more natural transition between discussed topics.
This improvement will significantly enhance the quality of interaction with Aria and make her a more useful assistant.

Thank you for your attention to this proposal! We are ready to provide additional information or examples if needed.