More than a cute pet, this is your versatile AI desktop agent. Supports BYOK (OpenAI-compatible) with long-term memory, voice, and multimodal vision. It searches the web, safely executes Python code, and manages files. Features continuous agent logic, music management,and custom Live2D/voice support

Sign in to add this item to your wishlist, follow it, or mark it as ignored

This game is not yet available on Steam

Coming soon

Interested?
Add to your wishlist and get notified when it becomes available.
Add to your wishlist
 

About This Game

【What is this?】
This is not an ordinary virtual pet, but an AI Launcher with infinite possibilities. We provide the "body," and you choose the "brain." By connecting your preferred AI model (such as GPT-4, Claude, or any OpenAI-compatible service), she becomes the most capable assistant on your desktop.

Key Features:

🧠 No Subscriptions, No "Server Shutdowns" (BYOK Mode)
We do not sell expensive AI subscription plans. You have full control by configuring your own API Key (OpenAI-compatible).

  • Built-in Recommendations: We include recommended service providers for easy setup, but you are free to switch to any provider you trust.

  • Freedom of Choice: Want the smartest model? Or the most cost-effective one? You decide.

  • Privacy First: Your keys and data are stored locally. You choose the LLM provider you trust.

🐱 Standalone Companion
Even without any AI configuration, she is a fully interactive Live2D desktop pet. You can interact with her via mouse clicks and use the built-in music manager to play your local tracks.

🛠️ Multimodal Intelligence
She doesn't just chat; she works. Thanks to the built-in sandbox environment, the AI has "hands":

  • Code Execution: Tell her your needs, and she can write and run Python scripts in a secure sandbox (real-time execution upon your confirmation).

  • File Management: Organize folders, rename files, or generate data reports.

  • Web Browsing: With built-in crawler tools, she can search the web and summarize the latest news for you. (Requires appropriate network configuration).

  • Agent Architecture: She keeps a private diary to record things she doesn't want to forget. When executing complex tasks, she creates a To-Do list that you can check in real-time to see her progress.

🗣️ Full Sensory Interaction

  • Voice Chat: Supports TTS (Text-to-Speech) and STT (Speech-to-Text). Talk to her like J.A.R.V.I.S.

  • Long-term Memory: Powered by a vector database (Embeddings), she remembers what you said days ago and learns your preferences. We use multiple memory strategies to ensure core information is never lost.

  • Vision Capabilities: She can "see" your desktop and understands what you are looking at.

  • Live2D Interaction: Switch between multiple built-in models or import your own. Her emotions and expressions sync perfectly with the conversation!

🛡️ Safety First
We understand the risks of AI executing code, so we built multiple defense lines:

  • Command Blacklist: Automatically blocks dangerous system commands.

  • Sandboxed Workspace: File operations are strictly confined to a specific directory.

  • Human-in-the-Loop: A warning pops up before any script runs. It only executes when you click "Agree."

💡 Why Choose Us?

  • One-time Purchase: No in-app purchases, no risk of the developer running away with your subscription fee.

  • Customizable: Supports custom System Prompts. Define her personality—from a strict assistant to a tsundere companion.

  • Open Ecosystem: Import your own audio for custom voices and choose any trusted LLM provider for the backend.

    Licenses & Credits

    Live2D Models Used:

    • Model Name: Momose Hiyori (桃瀬ひより)

      • Copyright: ©Live2D Inc.

      • Used under Live2D Free Material License.

    • Model Name: Shirokuma no Akachan (しろくまのあかちゃん)

      • Author: piso

      • Used under specific license agreement.

AI Generated Content Disclosure

The developers describe how their game uses AI Generated Content like this:

This game is an AI-powered desktop companion that uses Large Language Models (LLM) to generate real-time dialogue and voice interactions. The AI assistant can engage in natural conversations, answer questions, perform tasks, and provide voice feedback through Text-to-Speech (TTS) technology. All AI-generated content is produced in real-time via external API services, with content filtering and safety measures implemented to ensure compliance with community standards.

System Requirements

    Minimum:
    • OS: Windows 10
    • Processor: i5
    • Memory: 400 MB RAM
    • Graphics: Intel HD Graphics 4400
    • Network: Broadband Internet connection
    • Storage: 1 GB available space
There are no reviews for this product

You can write your own review for this product to share your experience with the community. Use the area above the purchase buttons on this page to write your review.