moeru-ai / airi

查看原文 / View Original 编辑 / Edit

moeru-ai / airi

Project AIRI Re-creating Neuro-sama, a soul container of AI waifu / virtual characters to bring them into our world. Project AIRI 旨在重现 Neuro-sama，打造一个 AI 二次元老婆/虚拟角色的“灵魂容器”，将她们带入我们的现实世界。

[Join Discord Server] [Try it] [简体中文] [日本語] [Русский] [Tiếng Việt] [Français] [한국어] [加入 Discord 服务器] [立即体验] [简体中文] [日本語] [Русский] [Tiếng Việt] [Français] [한국어]

Heavily inspired by Neuro-sama. 深受 Neuro-sama 的启发。

Tip: On Windows, you can also install AIRI with winget: winget install MoeruAI.AIRI Or install AIRI with Scoop: scoop bucket add airi https://github.com/moeru-ai/airi scoop install airi/airi On macOS, you can install AIRI with Homebrew Cask without adding a custom tap: brew install --cask airi 提示：在 Windows 上，你可以通过 winget 安装 AIRI：winget install MoeruAI.AIRI，或者使用 Scoop 安装：scoop bucket add airi https://github.com/moeru-ai/airi，scoop install airi/airi。在 macOS 上，你可以直接通过 Homebrew Cask 安装 AIRI，无需添加自定义 tap：brew install --cask airi。

Warning: We do not have any officially minted cryptocurrency or token associated with this project. Please check the information and proceed with caution. 警告：我们没有任何与本项目相关的官方加密货币或代币。请核实信息并谨慎行事。

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! 注意：我们为 Project AIRI 衍生的所有子项目建立了一个专门的组织 @proj-airi。欢迎查看！包括 RAG、记忆系统、嵌入式数据库、图标、Live2D 工具等！

Tip: We have a translation project on Crowdin. If you find any inaccurate translations, feel free to contribute improvements there. 提示：我们在 Crowdin 上有一个翻译项目。如果你发现翻译不准确，欢迎前往贡献改进。

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. 你是否曾梦想拥有一个赛博生命（赛博老婆、数字宠物）或数字伙伴，能陪你玩耍并与你交谈？借助 ChatGPT 和 Claude 等现代大语言模型的力量，让虚拟角色进行角色扮演并与我们聊天对每个人来说已经足够简单。Character.ai (c.ai)、JanitorAI 以及 SillyTavern 等本地平台，已经为基于聊天的体验或视觉冒险游戏提供了足够好的解决方案。但是，如果她们还能玩游戏呢？能看到你在写什么代码呢？能在玩游戏、看视频的同时与你聊天，并能做许多其他事情呢？

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. 也许你已经知道 Neuro-sama 了。她是目前最优秀的虚拟主播，能够玩游戏、聊天并与你及观众互动。有些人称这种存在为“数字人”。遗憾的是，由于它不是开源的，当她直播下线后，你就无法与她互动了。因此，本项目 AIRI 提供了另一种可能：让你轻松地在任何时间、任何地点拥有属于自己的数字生命和赛博生活。

Recent DevLogs & Stories

近期开发日志与故事

  • DevLog @ 2026.03.23: Mobile performance and game engine exploration - March 23, 2026
  • 开发日志 @ 2026.03.23：移动端性能与游戏引擎探索 - 2026年3月23日
  • DevLog @ 2026.03.14: VRM stage lifecycle, cache, and observability - March 14, 2026
  • 开发日志 @ 2026.03.14：VRM 舞台生命周期、缓存与可观测性 - 2026年3月14日
  • DevLog @ 2026.02.16: Dome Keeper data collection and training pipeline - February 16, 2026
  • 开发日志 @ 2026.02.16：《穹顶守护者》(Dome Keeper) 数据收集与训练流水线 - 2026年2月16日
  • DevLog @ 2026.01.01: AIRI Pocket and FlowChat memory experiments - January 1, 2026
  • 开发日志 @ 2026.01.01：AIRI Pocket 与 FlowChat 记忆实验 - 2026年1月1日
  • DevLog @ 2025.10.20: Electron migration, new models, and Moeru AI updates - October 20, 2025
  • 开发日志 @ 2025.10.20：Electron 迁移、新模型与 Moeru AI 更新 - 2025年10月20日
  • DevLog @ 2025.08.26: Pure vision progress for airi-factorio - August 26, 2025
  • 开发日志 @ 2025.08.26：airi-factorio 的纯视觉进展 - 2025年8月26日
  • DevLog @ 2025.08.05: AIRI v0.7 release highlights - August 5, 2025
  • 开发日志 @ 2025.08.05：AIRI v0.7 发布亮点 - 2025年8月5日
  • DevLog @ 2025.08.01: Streaming text animation and grapheme clusters - August 1, 2025
  • 开发日志 @ 2025.08.01：流式文本动画与字素簇 - 2025年8月1日
  • DevLog @ 2025.07.18: Rethinking airi-factorio with Factorio Learning Environment - July 18, 2025
  • 开发日志 @ 2025.07.18：利用 Factorio 学习环境重构 airi-factorio - 2025年7月18日
  • DreamLog 0x1: The backstory of Project AIRI - June 16, 2025
  • 梦想日志 0x1：Project AIRI 的背景故事 - 2025年6月16日

More on the documentation site. 更多内容请访问文档网站。

What’s So Special About This Project?

这个项目有什么特别之处？

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. 与其他 AI 驱动的 VTuber 开源项目不同，アイリ（AIRI）从第一天起就构建在对 WebGPU、WebAudio、Web Workers、WebAssembly、WebSocket 等多种 Web 技术支持的基础上。

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. 提示：担心使用 Web 相关技术会导致性能下降？别担心，虽然 Web 浏览器版本旨在展示我们在浏览器和 webview 中能达到的极限，但我们绝不会完全依赖它。AIRI 的桌面版本默认支持使用原生的 NVIDIA CUDA 和 Apple Metal（感谢 HuggingFace 和备受喜爱的 candle 项目），且无需复杂的依赖管理。

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. 考虑到权衡，它部分由 Web 技术驱动，用于图形、布局、动画以及供大家集成功能的插件系统（开发中）。这意味着 アイリ 能够在现代浏览器、设备甚至移动设备上运行（已通过 PWA 支持实现）。这为我们（开发者）提供了无限可能，可以将 アイリ VTuber 的能力提升到新的高度，同时保留了灵活性，让用户能够启用需要 TCP 连接或其他非 Web 技术的功能，例如连接到 Discord 语音频道或与朋友一起玩《Minecraft》和《Factorio》。

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. 注意：我们仍处于开发早期阶段，正在寻找有才华的开发者加入我们，帮助我们将 アイリ 变为现实。即使你不熟悉 Vue.js、TypeScript 和本项目所需的开发工具也没关系，你可以以艺术家、设计师的身份加入，甚至帮助我们开启第一次直播。即使你是 React、Svelte 甚至 Solid 的忠实粉丝，我们也欢迎你。你可以创建一个子目录来添加你希望在 アイリ 中看到的功能，或者进行实验。

Fields (and related projects) that we are looking for: 我们正在寻找以下领域（及相关项目）的人才：

  • Live2D modeller / VRM modeller / VRChat avatar designer
  • Live2D 建模师 / VRM 建模师 / VRChat 虚拟形象设计师
  • Computer Vision / Reinforcement Learning
  • 计算机视觉 / 强化学习
  • Speech Recognition / Speech Synthesis
  • 语音识别 / 语音合成
  • ONNX Runtime / Transformers.js / vLLM / WebGPU / Three.js / WebXR (checkout the another project we have under the @moeru-ai organization)
  • ONNX Runtime / Transformers.js / vLLM / WebGPU / Three.js / WebXR（查看我们在 @moeru-ai 组织下的另一个项目）

If you are interested, why not introduce yourself here? Would like to join part of us to build AIRI? 如果你感兴趣，何不在这里介绍一下自己？想加入我们一起构建 AIRI 吗？

Current Progress & Roadmap

当前进展与路线图

  • Brain: Play Minecraft, Play Factorio (WIP, but PoC and demo available), Play Kerbal Space Program (announcement TBD), Co-play Helldivers 2 (WIP), Chat in Telegram, Chat in Discord
  • 大脑：玩《Minecraft》、玩《Factorio》（开发中，但已有 PoC 和演示）、玩《坎巴拉太空计划》（公告待定）、联机《绝地潜兵 2》（开发中）、Telegram 聊天、Discord 聊天
  • Memory: Pure in-browser database support (DuckDB WASM | pglite), Memory Alaya (WIP), Pure in-browser local (WebGPU) inference
  • 记忆：纯浏览器内数据库支持 (DuckDB WASM | pglite)、Memory Alaya（开发中）、纯浏览器内本地 (WebGPU) 推理
  • Ears: Audio input from browser, Audio input from Discord, Client side speech recognition, Client side talking detection
  • 耳朵：浏览器音频输入、Discord 音频输入、客户端语音识别、客户端说话检测
  • Mouth: Multi-provider voice synthesis, including ElevenLabs, Microsoft/Azure Speech, OpenAI-compatible TTS, Alibaba Cloud Model Studio, and local Kokoro TTS
  • 嘴巴：多供应商语音合成，包括 ElevenLabs、Microsoft/Azure Speech、OpenAI 兼容 TTS、阿里云百炼模型服务以及本地 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)
  • 身体：VRM 支持（控制 VRM 模型、VRM 模型动画、自动眨眼、自动注视、闲置眼部运动）、Live2D 支持（控制 Live2D 模型、Live2D 模型动画）
← 返回新闻列表 / Back to news list