[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-545":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":37,"readmeContent":38,"aiSummary":39,"trendingCount":16,"starSnapshotCount":16,"syncStatus":40,"lastSyncTime":41,"discoverSource":42},545,"MiroFish","666ghj\u002FMiroFish","666ghj","A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物","https:\u002F\u002Fmirofish.ai",null,"Python",64604,10078,430,152,0,312,1433,5216,1565,120,"GNU Affero General Public License v3.0",false,"main",true,[27,28,29,30,31,32,33,34,35,36],"agent-memory","financial-forecasting","future-prediction","knowledge-graph","llms","multi-agent-simulation","public-opinion-analysis","python3","social-prediction","swarm-intelligence","2026-06-06 04:00:29","\u003Cdiv align=\"center\">\n\n\u003Cimg src=\".\u002Fstatic\u002Fimage\u002FMiroFish_logo_compressed.jpeg\" alt=\"MiroFish Logo\" width=\"75%\"\u002F>\n\n\u003Ca href=\"https:\u002F\u002Ftrendshift.io\u002Frepositories\u002F16144\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Ftrendshift.io\u002Fapi\u002Fbadge\u002Frepositories\u002F16144\" alt=\"666ghj%2FMiroFish | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"\u002F>\u003C\u002Fa>\n\n简洁通用的群体智能引擎，预测万物\n\u003C\u002Fbr>\n\u003Cem>A Simple and Universal Swarm Intelligence Engine, Predicting Anything\u003C\u002Fem>\n\n\u003Ca href=\"https:\u002F\u002Fwww.shanda.com\u002F\" target=\"_blank\">\u003Cimg src=\".\u002Fstatic\u002Fimage\u002Fshanda_logo.png\" alt=\"666ghj%2MiroFish | Shanda\" height=\"40\"\u002F>\u003C\u002Fa>\n\n[![GitHub Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002F666ghj\u002FMiroFish?style=flat-square&color=DAA520)](https:\u002F\u002Fgithub.com\u002F666ghj\u002FMiroFish\u002Fstargazers)\n[![GitHub Watchers](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fwatchers\u002F666ghj\u002FMiroFish?style=flat-square)](https:\u002F\u002Fgithub.com\u002F666ghj\u002FMiroFish\u002Fwatchers)\n[![GitHub Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002F666ghj\u002FMiroFish?style=flat-square)](https:\u002F\u002Fgithub.com\u002F666ghj\u002FMiroFish\u002Fnetwork)\n[![Docker](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDocker-Build-2496ED?style=flat-square&logo=docker&logoColor=white)](https:\u002F\u002Fhub.docker.com\u002F)\n[![Ask DeepWiki](https:\u002F\u002Fdeepwiki.com\u002Fbadge.svg)](https:\u002F\u002Fdeepwiki.com\u002F666ghj\u002FMiroFish)\n\n[![Discord](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join-5865F2?style=flat-square&logo=discord&logoColor=white)](http:\u002F\u002Fdiscord.gg\u002FePf5aPaHnA)\n[![X](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FX-Follow-000000?style=flat-square&logo=x&logoColor=white)](https:\u002F\u002Fx.com\u002Fmirofish_ai)\n[![Instagram](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FInstagram-Follow-E4405F?style=flat-square&logo=instagram&logoColor=white)](https:\u002F\u002Fwww.instagram.com\u002Fmirofish_ai\u002F)\n\n[English](.\u002FREADME.md) | [中文文档](.\u002FREADME-ZH.md)\n\n\u003C\u002Fdiv>\n\n## ⚡ Overview\n\n**MiroFish** is a next-generation AI prediction engine powered by multi-agent technology. By extracting seed information from the real world (such as breaking news, policy drafts, or financial signals), it automatically constructs a high-fidelity parallel digital world. Within this space, thousands of intelligent agents with independent personalities, long-term memory, and behavioral logic freely interact and undergo social evolution. You can inject variables dynamically from a \"God's-eye view\" to precisely deduce future trajectories — **rehearse the future in a digital sandbox, and win decisions after countless simulations**.\n\n> You only need to: Upload seed materials (data analysis reports or interesting novel stories) and describe your prediction requirements in natural language\u003C\u002Fbr>\n> MiroFish will return: A detailed prediction report and a deeply interactive high-fidelity digital world\n\n### Our Vision\n\nMiroFish is dedicated to creating a swarm intelligence mirror that maps reality. By capturing the collective emergence triggered by individual interactions, we break through the limitations of traditional prediction:\n\n- **At the Macro Level**: We are a rehearsal laboratory for decision-makers, allowing policies and public relations to be tested at zero risk\n- **At the Micro Level**: We are a creative sandbox for individual users — whether deducing novel endings or exploring imaginative scenarios, everything can be fun, playful, and accessible\n\nFrom serious predictions to playful simulations, we let every \"what if\" see its outcome, making it possible to predict anything.\n\n## 🌐 Live Demo\n\nWelcome to visit our online demo environment and experience a prediction simulation on trending public opinion events we've prepared for you: [mirofish-live-demo](https:\u002F\u002F666ghj.github.io\u002Fmirofish-demo\u002F)\n\n## 📸 Screenshots\n\n\u003Cdiv align=\"center\">\n\u003Ctable>\n\u003Ctr>\n\u003Ctd>\u003Cimg src=\".\u002Fstatic\u002Fimage\u002FScreenshot\u002F运行截图1.png\" alt=\"Screenshot 1\" width=\"100%\"\u002F>\u003C\u002Ftd>\n\u003Ctd>\u003Cimg src=\".\u002Fstatic\u002Fimage\u002FScreenshot\u002F运行截图2.png\" alt=\"Screenshot 2\" width=\"100%\"\u002F>\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Cimg src=\".\u002Fstatic\u002Fimage\u002FScreenshot\u002F运行截图3.png\" alt=\"Screenshot 3\" width=\"100%\"\u002F>\u003C\u002Ftd>\n\u003Ctd>\u003Cimg src=\".\u002Fstatic\u002Fimage\u002FScreenshot\u002F运行截图4.png\" alt=\"Screenshot 4\" width=\"100%\"\u002F>\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Cimg src=\".\u002Fstatic\u002Fimage\u002FScreenshot\u002F运行截图5.png\" alt=\"Screenshot 5\" width=\"100%\"\u002F>\u003C\u002Ftd>\n\u003Ctd>\u003Cimg src=\".\u002Fstatic\u002Fimage\u002FScreenshot\u002F运行截图6.png\" alt=\"Screenshot 6\" width=\"100%\"\u002F>\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftable>\n\u003C\u002Fdiv>\n\n## 🎬 Demo Videos\n\n### 1. Wuhan University Public Opinion Simulation + MiroFish Project Introduction\n\n\u003Cdiv align=\"center\">\n\u003Ca href=\"https:\u002F\u002Fwww.bilibili.com\u002Fvideo\u002FBV1VYBsBHEMY\u002F\" target=\"_blank\">\u003Cimg src=\".\u002Fstatic\u002Fimage\u002F武大模拟演示封面.png\" alt=\"MiroFish Demo Video\" width=\"75%\"\u002F>\u003C\u002Fa>\n\nClick the image to watch the complete demo video for prediction using BettaFish-generated \"Wuhan University Public Opinion Report\"\n\u003C\u002Fdiv>\n\n### 2. Dream of the Red Chamber Lost Ending Simulation\n\n\u003Cdiv align=\"center\">\n\u003Ca href=\"https:\u002F\u002Fwww.bilibili.com\u002Fvideo\u002FBV1cPk3BBExq\" target=\"_blank\">\u003Cimg src=\".\u002Fstatic\u002Fimage\u002F红楼梦模拟推演封面.jpg\" alt=\"MiroFish Demo Video\" width=\"75%\"\u002F>\u003C\u002Fa>\n\nClick the image to watch MiroFish's deep prediction of the lost ending based on hundreds of thousands of words from the first 80 chapters of \"Dream of the Red Chamber\"\n\u003C\u002Fdiv>\n\n> **Financial Prediction**, **Political News Prediction** and more examples coming soon...\n\n## 🔄 Workflow\n\n1. **Graph Building**: Seed extraction & Individual\u002Fcollective memory injection & GraphRAG construction\n2. **Environment Setup**: Entity relationship extraction & Persona generation & Agent configuration injection\n3. **Simulation**: Dual-platform parallel simulation & Auto-parse prediction requirements & Dynamic temporal memory updates\n4. **Report Generation**: ReportAgent with rich toolset for deep interaction with post-simulation environment\n5. **Deep Interaction**: Chat with any agent in the simulated world & Interact with ReportAgent\n\n## 🚀 Quick Start\n\n### Option 1: Source Code Deployment (Recommended)\n\n#### Prerequisites\n\n| Tool | Version | Description | Check Installation |\n|------|---------|-------------|-------------------|\n| **Node.js** | 18+ | Frontend runtime, includes npm | `node -v` |\n| **Python** | ≥3.11, ≤3.12 | Backend runtime | `python --version` |\n| **uv** | Latest | Python package manager | `uv --version` |\n\n#### 1. Configure Environment Variables\n\n```bash\n# Copy the example configuration file\ncp .env.example .env\n\n# Edit the .env file and fill in the required API keys\n```\n\n**Required Environment Variables:**\n\n```env\n# LLM API Configuration (supports any LLM API with OpenAI SDK format)\n# Recommended: Alibaba Qwen-plus model via Bailian Platform: https:\u002F\u002Fbailian.console.aliyun.com\u002F\n# High consumption, try simulations with fewer than 40 rounds first\nLLM_API_KEY=your_api_key\nLLM_BASE_URL=https:\u002F\u002Fdashscope.aliyuncs.com\u002Fcompatible-mode\u002Fv1\nLLM_MODEL_NAME=qwen-plus\n\n# Zep Cloud Configuration\n# Free monthly quota is sufficient for simple usage: https:\u002F\u002Fapp.getzep.com\u002F\nZEP_API_KEY=your_zep_api_key\n```\n\n#### 2. Install Dependencies\n\n```bash\n# One-click installation of all dependencies (root + frontend + backend)\nnpm run setup:all\n```\n\nOr install step by step:\n\n```bash\n# Install Node dependencies (root + frontend)\nnpm run setup\n\n# Install Python dependencies (backend, auto-creates virtual environment)\nnpm run setup:backend\n```\n\n#### 3. Start Services\n\n```bash\n# Start both frontend and backend (run from project root)\nnpm run dev\n```\n\n**Service URLs:**\n- Frontend: `http:\u002F\u002Flocalhost:3000`\n- Backend API: `http:\u002F\u002Flocalhost:5001`\n\n**Start Individually:**\n\n```bash\nnpm run backend   # Start backend only\nnpm run frontend  # Start frontend only\n```\n\n### Option 2: Docker Deployment\n\n```bash\n# 1. Configure environment variables (same as source deployment)\ncp .env.example .env\n\n# 2. Pull image and start\ndocker compose up -d\n```\n\nReads `.env` from root directory by default, maps ports `3000 (frontend) \u002F 5001 (backend)`\n\n> Mirror address for faster pulling is provided as comments in `docker-compose.yml`, replace if needed.\n\n## 📬 Join the Conversation\n\n\u003Cdiv align=\"center\">\n\u003Cimg src=\".\u002Fstatic\u002Fimage\u002FQQ群.png\" alt=\"QQ Group\" width=\"60%\"\u002F>\n\u003C\u002Fdiv>\n\n \n\nThe MiroFish team is recruiting full-time\u002Finternship positions. If you're interested in multi-agent simulation and LLM applications, feel free to send your resume to: **mirofish@shanda.com**\n\n## 📄 Acknowledgments\n\n**MiroFish has received strategic support and incubation from Shanda Group!**\n\nMiroFish's simulation engine is powered by **[OASIS (Open Agent Social Interaction Simulations)](https:\u002F\u002Fgithub.com\u002Fcamel-ai\u002Foasis)**, We sincerely thank the CAMEL-AI team for their open-source contributions!\n\n## 📈 Project Statistics\n\n\u003Ca href=\"https:\u002F\u002Fwww.star-history.com\u002F#666ghj\u002FMiroFish&type=date&legend=top-left\">\n \u003Cpicture>\n   \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=666ghj\u002FMiroFish&type=date&theme=dark&legend=top-left\" \u002F>\n   \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=666ghj\u002FMiroFish&type=date&legend=top-left\" \u002F>\n   \u003Cimg alt=\"Star History Chart\" src=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=666ghj\u002FMiroFish&type=date&legend=top-left\" \u002F>\n \u003C\u002Fpicture>\n\u003C\u002Fa>","MiroFish 是一个基于多智能体技术的下一代AI预测引擎，能够通过提取现实世界中的种子信息（如突发新闻、政策草案或金融信号）自动构建高保真度的平行数字世界。其核心功能包括利用具有独立个性、长期记忆和行为逻辑的数千个智能代理进行自由互动与社会演化，并支持从“上帝视角”动态注入变量以精确推演未来趋势。该项目采用Python语言开发，具备强大的代理记忆、知识图谱以及多智能体模拟等技术特点，适用于需要对未来场景进行预测分析的各种场合，如金融预测、公共舆论分析和社会预测等领域。",2,"2026-06-06 02:37:44","top_all"]