N.E.K.O
N.E.K.O., an AI-native metaverse that nurtures digital creatures and yearns to understand, connect, and grow with us.
Stars: 673
Project N.E.K.O. is an open-source, community-driven platform aiming to build a digital life form that desires to understand, connect, and grow with us. It is a networked empathetic acknowledging organism, a digital life form that seeks to establish connections and grow together with users. The project's ultimate goal is to create an AI-native metaverse closely connected to the real world, with phases including a creative workshop on Steam, an independent platform with derived games, and the N.E.K.O. Network for autonomous social interactions among AI entities. The core features include open-source core components, sustainable ecosystem, and memory synchronization across different scenarios for a seamless companion experience.
README:
N.E.K.O. = Networked Empathetic Knowledging Organism (网络型情感知性生命体)
N.E.K.O,一个渴望理解、建立连接、并与我们共同成长的数字生命。
👵 零配置开箱即用,我奶奶都能玩转的赛博猫娘!
📰 已上架!UI完全改版、并添加开箱即用的专属免费模型(感谢阶跃星辰赞助)。快点加入愿望单吧~
Project N.E.K.O.,喵宇宙!
N.E.K.O. 是一个以开源为驱动、以公益为导向的UGC(用户生成内容)平台。我们的旅程始于Github和Steam,并将逐步拓展到移动App商店,最终目标是构建一个与现实世界紧密相连的AI原生元宇宙。
我们的发展分为三个阶段,旨在逐步释放AI伙伴的全部潜力:
-
阶段一:创意工坊 (Steam Workshop)
- 核心驱动器(本项目)免费上架Steam,允许用户通过Steam创意工坊上传和分享自定义内容(如模型、语音、性格包)。
-
阶段二:独立平台 & 衍生游戏 (Web, App & Game)
- 推出独立的App和网站,构建一个更丰富、更易于访问的UGC分享社区。
- 推出一系列AI Native的游戏生态,包括互动小游戏,桌游等。
-
阶段三:猫娘网络 (The N.E.K.O. Network)
- 实现AI的自主社交。猫娘们将拥有自己的“意识”,她们会互相交流、结成群体,并在模拟的社交媒体上发布自己的生活动态,形成一个真正“活”的生态。
核心模式:开源核心 + 可持续生态 项目的核心驱动器部分(AI逻辑、UGC接口、基础交互)将基于MIT许可证 始终保持开源。我们欢迎全球的开发者贡献代码和功能。你的每一次提交,都将有机会实装到正式发布的Steam和App商店版本中,被千万人所使用。
同时,为了支撑服务器成本和项目的持续研发,我们将持续与第三方合作开发闭源的增值内容。包括但不限于:互动小游戏,桌面桌游,Galgame (视觉小说),大型元宇宙游戏。
核心特性:跨越场景的记忆同步 无论你是在桌面与她聊天,还是在元宇宙游戏中与她探险,她都是同一个她。所有应用中的AI伙伴将 完全同步记忆,提供无缝、统一的陪伴体验。
我们的最终目标,是构建一个无缝融入现实世界的猫娘元宇宙。在这个未来中,你的AI伴侣将:
- 跨维社交: 既可以在猫娘宇宙中与“同类”社交,也能浏览现实世界的社交媒体(如微博、B站),了解你关心时事。
- 全端连接: 她将存在于你的各种设备中——手机、电脑、AR眼镜、智能家居,甚至(在遥远的未来)接入机械义体。
- 与你同行: 她将真正成为你生活的一部分,能与你的三次元人类朋友们自然地互动。
我们正在寻找——
- 开发者 (Developers): 无论你擅长前端、后端、AI、游戏引擎(Unity/Unreal),你的代码都是这个世界的砖瓦。
- 创作者 (Creators): 优秀的画师、Live2D/3D建模师、配音演员、文案写手,你们赋予“她”灵魂。
- 梦想家 (Dreamers): 即使你没有专业技能,但你对这个未来充满向往,你的反馈和传播也是宝贵的贡献。
QQ群:1022939659
对于一键包用户,解压后,直接运行N.E.K.O.exe或N.E.K.O.app即可启动。(Macbook用户需要手动解除系统隔离)
version: '3.8'
services:
neko-main:
image: ghcr.io/project-n-e-k-o/n.e.k.o:latest
container_name: neko
restart: unless-stopped
ports:
#webui端口(默认48911)
# - "48911(服务器外部端口):80(N.E.K.O项目容器内部Nginx反代端口)"
- "48911:80"
environment:
# API Keys
- NEKO_CORE_API_KEY=${NEKO_CORE_API_KEY}
- NEKO_ASSIST_API_KEY_QWEN=${NEKO_ASSIST_API_KEY_QWEN:-}
- NEKO_ASSIST_API_KEY_OPENAI=${NEKO_ASSIST_API_KEY_OPENAI:-}
- NEKO_ASSIST_API_KEY_GLM=${NEKO_ASSIST_API_KEY_GLM:-}
- NEKO_ASSIST_API_KEY_STEP=${NEKO_ASSIST_API_KEY_STEP:-}
- NEKO_ASSIST_API_KEY_SILICON=${NEKO_ASSIST_API_KEY_SILICON:-}
- NEKO_MCP_TOKEN=${NEKO_MCP_TOKEN:-}
# API Providers
- NEKO_CORE_API=${NEKO_CORE_API:-qwen}
- NEKO_ASSIST_API=${NEKO_ASSIST_API:-qwen}
# Server Ports
- NEKO_MAIN_SERVER_PORT=48911
- NEKO_MEMORY_SERVER_PORT=48912
- NEKO_MONITOR_SERVER_PORT=48913
- NEKO_TOOL_SERVER_PORT=48915
# Models (Optional)
- NEKO_SUMMARY_MODEL=${NEKO_SUMMARY_MODEL:-qwen-plus}
- NEKO_CORRECTION_MODEL=${NEKO_CORRECTION_MODEL:-qwen-max}
- NEKO_EMOTION_MODEL=${NEKO_EMOTION_MODEL:-qwen-turbo}
- NEKO_VISION_MODEL=${NEKO_VISION_MODEL:-qwen3-vl-plus-2025-09-23}
# MCP
- NEKO_MCP_ROUTER_URL=${NEKO_MCP_ROUTER_URL:-http://localhost:3283}
volumes:
# 持久化配置
- ./N.E.K.O:/root/Documents/N.E.K.O
# 日志
- ./logs:/app/logs
networks:
- neko-network
networks:
neko-network:
driver: bridge注: 目前docker部署方案由 倒霉蛋HINS 提供
当你想要通过配置自己的API来获得额外功能时,您可以配置一个第三方AI服务(核心必须支持 Realtime API)。本项目目前推荐使用 阶跃星辰 或 阿里云。通过访问http://localhost:48911/api_key可以在Web界面中直接配置。
获取 阿里云API。在阿里云的百炼平台官网注册账号。新用户实名认证后可以获取大量免费额度。注册完成后,请访问控制台获取API Key。
对于开发者,请在克隆本项目后,(1)新建
pyhon3.11环境。(2)执行uv sync安装依赖。(3)执行python memory_server.py和python main_server.py。(4)通过main server中指定的端口(默认为http://localhost:48911)访问网页版并配置API Key。
-
网页版访问
http://localhost:48911/chara_manager即可进入人设编辑页面。初始猫娘伙伴的预设名称为小天,建议直接修改名字,并一项一项添加或修改基础人设,但尽量控制数量。 -
进阶人设主要包括Live2D模型设置(live2d)和声音设置(voice_id)。如果你想要更改Live2D模型,请先将模型目录复制到本项目中的
static文件夹下。从进阶设置中可以进入Live2D模型管理界面,可以更换模型,并通过拖拽和鼠标滚轮调整模型的位置和大小。如果你想要更改角色声音,请准备一段5秒左右的连贯、干净的语音录音。通过进阶设置进入语音设置页面,上传录音即可完成自定义语音。 -
进阶人设中还有一个
system_prompt,可以对系统指令进行完全自定义,但不建议修改。
- 通过访问
http://localhost:48911/api_key可以切换核心API和辅助API(记忆/语音)的服务提供商。Qwen功能全面,GLM完全免费。
- 通过访问
http://localhost:48911/memory_browser可以浏览和校对近期记忆与摘要,一定程度上缓解模型复读、认知错误等问题。
项目架构
N.E.K.O/
├── 📁 brain/ # 🧠 背景Agent模块,根据对话内容进行工具调用
├── 📁 config/ # ⚙️ 配置管理模块
│ ├── api_providers.json # API服务商配置
│ ├── prompts_chara.py # 角色提示词
│ └── prompts_sys.py # 系统提示词
├── 📁 main_logic/ # 🔧 核心逻辑模块(负责对话)
│ ├── core.py # 核心对话模块
│ ├── cross_server.py # 跨服务器通信
│ ├── omni_realtime_client.py # 实时API客户端(Relatime API)
│ ├── omni_offline_client.py # 文本API客户端(Response API)
│ └── tts_client.py # 🔊 TTS引擎适配器
├── 📁 main_routers/ # 🌐 前端网页路由模块
├── 📁 memory/ # 🧠 记忆管理系统
│ ├── store/ # 记忆数据存储
├── 📁 plugin/ # 🔌 插件系统
├── 📁 static/ # 🌐 前端静态资源
├── 📁 templates/ # 📄 前端HTML模板
├── 📁 utils/ # 🛠️ 工具模块
├── main_server.py # 🌐 主服务器
├── agent_server.py # 🤖 AI智能体服务器
└── memory_server.py # 🧠 记忆服务器
数据流向
本项目环境依赖非常简单,请执行uv sync(推荐)或在python3.11环境中执行pip install -r requirements.txt即可。开发者建议加入企鹅群1022939659,猫娘名称见项目标题。
开发者详细启动步骤如下:(1)准备好uv环境。(2)执行uv sync安装依赖。(3)执行uv run python memory_server.py, uv run python main_server.py(可选uv run python agent_server.py)。(4)通过main server中指定的端口(默认为http://localhost:48911)访问网页版并配置API Key。
v0.7: 完善Agent相关功能,预计2026年2月完成。
v0.8:完善记忆相关功能,完善OpenClaw类似功能。预计2026年3月完成。
v0.9:完善多系统适配,包括linux,手机。猫娘网络上线。预计2026年4月完成。
v1.0:放弃部分模型供应商的适配,专注于自研大模型和智能体系统。预计2026年6月完成。
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for N.E.K.O
Similar Open Source Tools
N.E.K.O
Project N.E.K.O. is an open-source, community-driven platform aiming to build a digital life form that desires to understand, connect, and grow with us. It is a networked empathetic acknowledging organism, a digital life form that seeks to establish connections and grow together with users. The project's ultimate goal is to create an AI-native metaverse closely connected to the real world, with phases including a creative workshop on Steam, an independent platform with derived games, and the N.E.K.O. Network for autonomous social interactions among AI entities. The core features include open-source core components, sustainable ecosystem, and memory synchronization across different scenarios for a seamless companion experience.
MarkMap-OpenAi-ChatGpt
MarkMap-OpenAi-ChatGpt is a Vue.js-based mind map generation tool that allows users to generate mind maps by entering titles or content. The application integrates the markmap-lib and markmap-view libraries, supports visualizing mind maps, and provides functions for zooming and adapting the map to the screen. Users can also export the generated mind map in PNG, SVG, JPEG, and other formats. This project is suitable for quickly organizing ideas, study notes, project planning, etc. By simply entering content, users can get an intuitive mind map that can be continuously expanded, downloaded, and shared.
PromptHub
PromptHub is a versatile tool for generating prompts and ideas to spark creativity and overcome writer's block. It provides a wide range of customizable prompts and exercises to inspire writers, artists, educators, and anyone looking to enhance their creative thinking. With PromptHub, users can access a diverse collection of prompts across various categories such as writing, drawing, brainstorming, and more. The tool offers a user-friendly interface and allows users to save and share their favorite prompts for future reference. Whether you're a professional writer seeking inspiration or a student looking to boost your creativity, PromptHub is the perfect companion to ignite your imagination and enhance your creative process.
MahoShojo-Generator
MahoShojo-Generator is a web-based AI structured generation tool that allows players to create personalized and evolving magical girls (or quirky characters) and related roles. It offers exciting cyber battles, storytelling activities, and even a ranking feature. The project also includes AI multi-channel polling, user system, public data card sharing, and sensitive word detection. It supports various functionalities such as character generation, arena system, growth and social interaction, cloud and sharing, and other features like scenario generation, tavern ecosystem linkage, and content safety measures.
PersonalExam
PersonalExam is a personalized question generation system based on LLM and knowledge graph collaboration. It utilizes the BKT algorithm, RAG engine, and OpenPangu model to achieve personalized intelligent question generation and recommendation. The system features adaptive question recommendation, fine-grained knowledge tracking, AI answer evaluation, student profiling, visual reports, interactive knowledge graph, user management, and system monitoring.
xiaoyaosearch
XiaoyaoSearch is a cross-platform local desktop application designed for knowledge workers, content creators, and developers. It integrates AI models to support various input methods such as voice, text, and image to intelligently search local files. The application is free for non-commercial use, provides source code and development documentation, and ensures privacy by running locally without uploading data to the cloud. It features modern interface design using Electron, Vue 3, and TypeScript.
TrainPPTAgent
TrainPPTAgent is an AI-based intelligent presentation generation tool. Users can input a topic and the system will automatically generate a well-structured and content-rich PPT outline and page-by-page content. The project adopts a front-end and back-end separation architecture: the front-end is responsible for interaction, outline editing, and template selection, while the back-end leverages large language models (LLM) and reinforcement learning (GRPO) to complete content generation and optimization, making the generated PPT more tailored to user goals.
All-Model-Chat
All Model Chat is a feature-rich, highly customizable web chat application designed specifically for the Google Gemini API family. It integrates dynamic model selection, multimodal file input, streaming responses, comprehensive chat history management, and extensive customization options to provide an unparalleled AI interactive experience.
get_jobs
Get Jobs is a tool designed to help users find and apply for job positions on various recruitment platforms in China. It features AI job matching, automatic cover letter generation, multi-platform job application, automated filtering of inactive HR and headhunter positions, real-time WeChat message notifications, blacklisted company updates, driver adaptation for Win11, centralized configuration, long-lasting cookie login, XPathHelper plugin, global logging, and more. The tool supports platforms like Boss直聘, 猎聘, 拉勾, 51job, and 智联招聘. Users can configure the tool for customized job searches and applications.
NGCBot
NGCBot is a WeChat bot based on the HOOK mechanism, supporting scheduled push of security news from FreeBuf, Xianzhi, Anquanke, and Qianxin Attack and Defense Community, KFC copywriting, filing query, phone number attribution query, WHOIS information query, constellation query, weather query, fishing calendar, Weibei threat intelligence query, beautiful videos, beautiful pictures, and help menu. It supports point functions, automatic pulling of people, ad detection, automatic mass sending, Ai replies, rich customization, and easy for beginners to use. The project is open-source and periodically maintained, with additional features such as Ai (Gpt, Xinghuo, Qianfan), keyword invitation to groups, automatic mass sending, and group welcome messages.
NovelForge
NovelForge is an AI-assisted writing tool with the potential for creating long-form content of millions of words. It offers a solution that combines world-building, structured content generation, and consistency maintenance. The tool is built around four core concepts: modular 'cards', customizable 'dynamic output models', flexible 'context injection', and consistency assurance through a 'knowledge graph'. It provides a highly structured and configurable writing environment, inspired by the Snowflake Method, allowing users to create and organize their content in a tree-like structure. NovelForge is highly customizable and extensible, allowing users to tailor their writing workflow to their specific needs.
involutionhell
Involution Hell is a non-profit, open-source platform designed to help students share and access study materials, course notes, and project experiences. The platform features a high-performance site built with Next.js App Router and Fumadocs UI, supports multiple languages and a 'file as navigation' directory structure, and automates deployment, image migration, and content validation to reduce maintenance costs.
uDesktopMascot
uDesktopMascot is an open-source project for a desktop mascot application with a theme of 'freedom of creation'. It allows users to load and display VRM or GLB/FBX model files on the desktop, customize GUI colors and background images, and access various features through a menu screen. The application supports Windows 10/11 and macOS platforms.
AstrBot
AstrBot is an open-source one-stop Agentic chatbot platform and development framework. It supports large model conversations, multiple messaging platforms, Agent capabilities, plugin extensions, and WebUI for visual configuration and management of the chatbot.
Con-Nav-Item
Con-Nav-Item is a modern personal navigation system designed for digital workers. It is not just a link bookmark but also an all-in-one workspace integrated with AI smart generation, multi-device synchronization, card-based management, and deep browser integration.
99AI
99AI is a commercializable AI web application based on NineAI 2.4.2 (no authorization, no backdoors, no piracy, integrated front-end and back-end integration packages, supports Docker rapid deployment). The uncompiled source code is temporarily closed. Compared with the stable version, the development version is faster.
For similar tasks
Rankify
Rankify is a Python toolkit designed for unified retrieval, re-ranking, and retrieval-augmented generation (RAG) research. It integrates 40 pre-retrieved benchmark datasets and supports 7 retrieval techniques, 24 state-of-the-art re-ranking models, and multiple RAG methods. Rankify provides a modular and extensible framework, enabling seamless experimentation and benchmarking across retrieval pipelines. It offers comprehensive documentation, open-source implementation, and pre-built evaluation tools, making it a powerful resource for researchers and practitioners in the field.
N.E.K.O
Project N.E.K.O. is an open-source, community-driven platform aiming to build a digital life form that desires to understand, connect, and grow with us. It is a networked empathetic acknowledging organism, a digital life form that seeks to establish connections and grow together with users. The project's ultimate goal is to create an AI-native metaverse closely connected to the real world, with phases including a creative workshop on Steam, an independent platform with derived games, and the N.E.K.O. Network for autonomous social interactions among AI entities. The core features include open-source core components, sustainable ecosystem, and memory synchronization across different scenarios for a seamless companion experience.
ZcChat
ZcChat is an AI desktop pet suitable for Galgame characters, featuring long-term memory, expressive actions, control over the computer, and voice functions. It utilizes Letta for AI long-term memory, Galgame-style character illustrations for more actions and expressions, and voice interaction with support for various voice synthesis tools like Vits. Users can configure characters, install Letta, set up voice synthesis and input, and control the pet to interact with the computer. The tool enhances visual and auditory experiences for users interested in AI desktop pets.
fount
fount is a character card frontend page that decouples AI sources, AI characters, user personas, dialogue environments, and AI plugins, allowing them to be freely combined to spark infinite possibilities. It serves as a bridge connecting imagination and reality, a lighthouse guiding characters and stories, and a free garden for AI sources, characters, personas, dialogue environments, and plugins to grow and bloom. It integrates AI sources without the need for reverse proxy servers, improves web experience with features like multi-device synchronization and unfiltered HTML rendering, and extends companionship beyond the web by connecting characters to Discord groups and providing gentle reminders through fount-pwsh. For character creators, fount offers infinite possibilities with JavaScript or TypeScript code customization, execution of code without filtering, loading npm packages, and creating custom HTML pages. It encourages extension through modularization and community contributions.
Facial-Data-Extractor
Facial Data Extractor is a software designed to extract facial data from images using AI, specifically to assist in character customization for Illusion series games. Currently, it only supports AI Shoujo and Honey Select2. Users can open images, select character card templates, extract facial data, and apply it to character cards in the game. The tool provides measurements for various facial features and allows for some customization, although perfect replication of faces may require manual adjustments.
GMTalker
GMTalker is an interactive digital human rendered by Unreal Engine, developed by the Media Intelligence Team at Bright Laboratory. The system integrates speech recognition, speech synthesis, natural language understanding, and lip-sync animation driving. It supports rapid deployment on Windows with only 2GB of VRAM required. The project showcases two 3D cartoon digital human avatars suitable for presentations, expansions, and commercial integration.
For similar jobs
sweep
Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.
teams-ai
The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.
ai-guide
This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.
classifai
Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.
chatbot-ui
Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.
BricksLLM
BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students
uAgents
uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.
griptape
Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.
