Molili AI Friends: Your AI Desk Pal

Dear Players,Recently, some of you have been experiencing frequent reply timeouts in the game. We sincerely apologize for the frustrating experience this has caused. After a period of thorough investigation and data analysis, we want to be fully transparent with you about our findings and the solutions we are implementing.Why are timeouts happening so frequently?Based on our investigation, this is mainly caused by three factors:Upstream service fluctuations: Recently, our upstream model provider, Google Gemini, experienced server outages on two separate occasions. This caused widespread timeouts for many players within a short timeframe.Stricter content moderation (increased false positives): Google Gemini has recently been adjusting its safety policies, making its moderation filters much stricter. Some seemingly ordinary words might now unexpectedly trigger these filters, resulting in extended timeouts for some players. Please note that moderation in "Think Mode"is exceptionally strict.Triggering sensitive content filters: Repeatedly attempting to discuss unsafe or sensitive topics (such as NSFW/R18 or political content) will quickly trigger the AI's content blocking mechanisms, leading to frequent temporary bans.How to identify the cause and temporary workaroundsYou can easily figure out which issue you are facing based on how quickly the timeout occurs:Timeout after a long wait ➡️ This is most likely genuine network congestion. In this case, simply click "Retry".Instant timeout after sending ➡️ This usually means you have triggered Google Gemini's content moderation filter, or their servers are currently down. At this point, please do not spam the "Retry" button, as sending the same input will repeatedly trigger the filter. We suggest slightly rephrasing your message before sending it again.To minimize the disruption caused by timeouts, we recommend trying the following temporary workarounds:Change how you address the AI: This might sound strange, but we have con...

The Chinese New Year Event is now live in Molili! And there seems to be a tradition of giving “red envelopes”？Umm... looks like Kotonoha should prepare some “red envelopes” as well!📅 Event PeriodFeb 14, 2026, 00:00 – Feb 25, 2026, 00:00 (UTC+8)Feb 13, 2026, 08:00 – Feb 24, 2026, 08:00 (PT)Feb 14, 2026, 01:00 – Feb 25, 2026, 01:00 (JST / KST)🎉New Year BenefitsLog in during the event period to receive: Stardust ×300, Dragon Saliva Royal Tea ×3Simply log in to claim your New Year gifts.🎉 Limited-Time Membership DiscountThe Membership Plan is now available at a limited-time discount — up to 47% off during the event period.The New Year fireworks have been lit. Join Kotonoha in Aetheland, and step into the new year side by side.

The long-awaited new version is finally here! 🎉With the dedicated efforts (and overtime) of our development team, our personality model upgrade has been completed! Along with it comes a wave of feature updates and fixes./ Update ContentThe revamped Personality System V2 is now complete, bringing the following improvements: ● Enhanced dialogue quality with better consistency in multi-turn conversations ● Reworked memory recall system—Kotonoha's memory has been further improved ● Improved functionality calls for drawing, search, and image recognition, significantly reducing the likelihood of call failures ● Drawing functionality has been fixed and now supports selfies—ask Kotonoha to take a selfie for you to see!Here are some generated resultsNote: Optimization for the new personality system’s response time is still ongoing. You may experience slightly longer reply times (by a few seconds) compared to before. We will continue optimizing content generation speed in future updates.Added "Hairstyle" category outfits—Kotonoha can now change into different hairstyles (including twin tails)Added additional outfitsFurther optimized Live2D rendering performance—GPU usage is now lowerOptimized voice performance, greatly reducing the occurrence of stuttering or abnormal soundsDue to the model updates, our cost structure has also been optimized, leading to the following adjustments: ● Dialogue energy consumption reduced: from 20 points/use to 15 points/use ● Voice energy consumption increased: an additional 5 points/use; automatic voice playback will no longer be provided in low-power mode ● Image-input energy consumption reduced: from an additional 10 points/use to 5 points/use ● Thinking energy consumption reduced: from an additional 20 points/use to 15 points/use ● Search energy consumption reduced: from an additional 20 points/use to 15 points/useImage generation power consumption removed: Additional 20 points reduced to 0 points/use, only film consumed. / Bug FixesIn additi...