AIRI — self‑hosted Neuro‑sama‑style digital companion (Web, desktop, mobile)
moeru-ai/airi
💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minecraft, Factorio playing. Web / macOS / Windows supported.
AIRI is an open-source, self-hosted “Grok Companion” that re-creates Neuro-sama–style digital beings: containerized AI waifu / virtual characters that can chat, use memory/RAG systems, and interact with games. The project (TypeScript) ships desktop installers (v0.10.2 binaries linked in the README), web builds, and a PWA for mobile. Key capabilities called out in the README include realtime voice chat, automated gameplay (Minecraft, Factorio), and integration with a plugin/memory ecosystem maintained under the @proj-airi organization.
Translation
Translation
Translated body generated separately from the summary.
AIRI was built from day one around modern Web technologies — WebGPU, WebAudio, Web Workers, WebAssembly, and WebSocket — while the desktop app also supports native ML acceleration (NVIDIA CUDA and Apple Metal via HuggingFace’s candle) to avoid browser performance limits. The README documents install routes (winget, Scoop, Homebrew Cask) and an active docs/blog feed with recent devlogs (e.g., DevLog 2026.03.23 on mobile performance and game engine exploration; DevLog 2026.02.16 on Dome Keeper data collection and training pipeline; DevLog 2026.01.01 on AIRI Pocket and FlowChat memory experiments).
Who it's for
VTuber creators and streamers who want an owner‑run, persistent virtual performer
AI hobbyists and modders building chat+action agents that can play games or observe environments
Researchers and engineers interested in combining Web front-ends with native ML acceleration and RAG/memory systems
Why It Matters
AIRI provides a concrete, open alternative to closed systems like Neuro-sama by giving users ownership (self‑hosted stacks, downloadable binaries) and by bridging browser-friendly UI tech with native GPU acceleration for heavier ML workloads. It’s trending now (Rank #3 daily) after a large spike in community attention — +572 stars today to 44,067 total — likely driven by recent devlogs and the project’s cross‑platform release strategy (desktop installers, web demo at airi.moeru.ai, and PWA/mobile support). The combination of game-playing bots (Factorio, Minecraft), realtime voice chat, and an extensible plugin/memory stack makes it notable for anyone wanting an always-on, multimodal digital companion.
On macOS, you can install AIRI with Homebrew Cask without adding a custom tap:
brew install --cask airi
[!WARNING]
Attention: We do not have any officially minted cryptocurrency or token associated with this project. Please check the information and proceed with caution.
[!NOTE]
We've got a whole dedicated organization @proj-airi for all the sub-projects born from Project AIRI. Check it out!
RAG, memory system, embedded database, icons, Live2D utilities, and more!
[!TIP]
We have a translation project on Crowdin. If you find any inaccurate translations, feel free to contribute improvements there.
<a href="https://crowdin.com/project/proj-airi" target="_blank" rel="nofollow"><img style="width: 140px; height: 40px;" src="https://badges.crowdin.net/badge/light/crowdin-on-dark.png" srcset="https://badges.crowdin.net/badge/light/crowdin-on-dark.png 1x, https://badges.crowdin.net/badge/light/crowdin-on-dark@2x.png 2x" alt="Crowdin | Agile localization for tech companies" width="140" height="40" /></a>
Have you dreamed about having a cyber living being (cyber waifu, digital pet) or digital companion that could play with and talk to you?
With the power of modern large language models like ChatGPT and famous Claude, asking a virtual being to roleplay and chat with us is already easy enough for everyone. Platforms like Character.ai (a.k.a. c.ai) and JanitorAI as well as local playgrounds like SillyTavern are already good-enough solutions for a chat based or visual adventure game like experience.
But, what about the abilities to play games? And see what you are coding at? Chatting while playing games, watching videos, and is capable of doing many other things.
Perhaps you know Neuro-sama already. She is currently the best virtual streamer capable of playing games, chatting, and interacting with you and the participants. Some also call this kind of being "digital human." Sadly, as it's not open sourced, you cannot interact with her after her live streams go offline.
Therefore, this project, AIRI, offers another possibility here: let you own your digital life, cyber living, easily, anywhere, anytime.
Unlike the other AI driven VTuber open source projects, アイリ was built with support of many Web technologies such as WebGPU, WebAudio, Web Workers, WebAssembly, WebSocket, etc. from the first day.
[!TIP]
Worrying about the performance drop since we are using Web related technologies?
Don't worry, while the Web browser version is meant to give an insight into how much we can push and do inside browsers and webviews, we will never fully rely on this. The desktop version of AIRI is capable of using native NVIDIA CUDA and Apple Metal by default (thanks to HuggingFace & the beloved candle project), without any complex dependency management. Considering the tradeoff, it is partially powered by Web technologies for graphics, layouts, animations, and the WIP plugin system for everyone to integrate things.
This means that アイリ is capable of running on modern browsers and devices and even on mobile devices (already done with PWA support). This brings a lot of possibilities for us (the developers) to build and extend the power of アイリ VTuber to the next level, while still leaving the flexibility for users to enable features that require TCP connections or other non-Web technologies such as connecting to a Discord voice channel or playing Minecraft and Factorio with friends.
[!NOTE]
We are still in the early stage of development where we are seeking out talented developers to join us and help us to make アイリ a reality.
It's ok if you are not familiar with Vue.js, TypeScript, and devtools required for this project, you can join us as an artist, designer, or even help us to launch our first live stream.
Even if you are a big fan of React, Svelte or even Solid, we welcome you. You can open a sub-directory to add features that you want to see in アイリ, or would like to experiment with.
Fields (and related projects) that we are looking for:
Multi-provider voice synthesis, including ElevenLabs, Microsoft/Azure Speech, OpenAI-compatible TTS, Alibaba Cloud Model Studio, and local Kokoro TTS
Body
VRM support
Control VRM model
VRM model animations
Auto blink
Auto look at
Idle eye movement
Live2D support
Control Live2D model
Live2D model animations
Auto blink
Auto look at
Idle eye movement
Development
For detailed instructions to develop this project, follow CONTRIBUTING.md
[!NOTE]
By default, pnpm dev will start the development server for the Stage Web (browser version). If you would
like to try developing the desktop version, please make sure you read CONTRIBUTING.md
to setup the environment correctly.
Reka UI: for designing the documentation site, the new landing page is based on this, as well as implementing a massive amount of UI components. (shadcn-vue is using Reka UI as the headless, do checkout!)
