Resonance, An Agent on your computer. Accessible to your files, wisely control and do things via LLMs ReAct. 100% data safe, highly customize include appoint own LLMs api providers. 🎇一个本地AI智能体,让智能体以ReAct的方式操控你的电脑。全程本地运行,100%数据隐私安全。需自备模型API。可接入ollama、GPT、claude、gemini等支持OpenAI接口调用的LLM作为内核。
# 💠 Resonance Windows Agent **Echoing Intelligence Locally.** 一个专为 Windows 打造的高级本地智能体 (AI Agent) 主机。它不仅仅是聊天机器人,更是连接大模型(本地/云端)与系统底层的桥梁。 **支持 Gemini Agent Skills,您可以导入任何您所想要的 SKills 立刻体验!只需把链接发给Resonance,或在配置中添加即可。**      --- ## 🌟 核心特性 * **🧠 混合大脑架构**:无缝切换本地模型 (Ollama) 与云端 API (Gemini, GPT-4)。 * **🛠️ 智能技能 (Skills)**:通过 Python/PowerShell 扩展 Agent 能力,支持文件管理、浏览器自动化、系统状态读取。 * **🛡️ 哨兵系统 (Sentinels)**:自主监控时间触发器、文件变更和全局快捷键,变被动对话为主动通知。 * **💾 向量长时记忆**:基于 ChromaDB 的 RAG 引擎,自动萃取对话中的关键事实,随时间自我进化。 * **🖥️ 现代交互界面**:基于 Tailwind CSS v4 的极简科技感 Web 控制台。 --- 本地存储记忆库 隐私安全不外露 此处为示例  --- ## 🚀 快速开始 (Startup) 由于本项目采用前后端分离架构,开发环境下需分别启动。 ### 1. 环境准备 确保已安装: * **Python 3.11+** * **Node.js 20+** * **Conda** (推荐) ### 2. 后端配置 (Backend) ```bash # 进入后端目录 cd backend # 创建并激活环境 conda create -n resonance python=3.11 -y conda activate resonance # 安装依赖 pip install -r requirements.txt # 初始化配置 (从模板复制) copy config\config.yaml.template config\config.yaml copy config\profiles.yaml.template config\profiles.yaml # 启动服务器 (默认端口 8000) python server.py ``` ### 3. 前端配置 (Frontend) > **注意**:本项目使用 Tailwind CSS v4,需配合 Vite 插件运行。 ```bash # 进入前端目录 cd frontend # 安装依赖 npm install # 启动开发服务器 (默认端口 5173) npm run dev ``` 访问 `http://localhost:5173` 即可进入控制台。 --- ## ⚙️ 配置说明 * **`backend/config/config.yaml`**: 全局系统设置、已注册的自动化脚本(Skills)。 * **`backend/config/profiles.yaml`**: LLM 提供商配置(API Key、Base URL、模型名称)。 * **`backend/config/user_profile.yaml`**: 存储 Agent 记住的关于你的个人偏好和项目路径。 --- ## 🛠️ 技术栈 | 模块 | 技术方案 | | :--- | :--- | | **Backend** | FastAPI, HostAgent (Custom Core), Psutil, Watchdog | | **LLM Orchestration** |
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.