[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72063":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":15,"forks30d":15,"starsTrendScore":19,"compositeScore":20,"rankGlobal":9,"rankLanguage":9,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":24,"hasPages":22,"topics":25,"createdAt":9,"pushedAt":9,"updatedAt":26,"readmeContent":27,"aiSummary":28,"trendingCount":15,"starSnapshotCount":15,"syncStatus":16,"lastSyncTime":29,"discoverSource":30},72063,"devin.cursorrules","grapeot\u002Fdevin.cursorrules","grapeot","Magic to turn Cursor\u002FWindsurf as 90% of Devin",null,"Python",5972,768,61,9,0,2,4,11,6,39.66,"MIT License",false,"master",true,[],"2026-06-12 02:02:58","# Transform your $20 Cursor into a Devin-like AI Assistant\n\nThis repository gives you everything needed to supercharge your Cursor\u002FWindsurf IDE or GitHub Copilot with **advanced** agentic AI capabilities—similar to the $25\u002Ftask (calculated from $2.25\u002FACU in the Core plan and 5-12.5ACU complexity horizon in the docs) Devin—but at a fraction of the cost. In under a minute, you'll gain:\n\n* Automated planning and self-evolution, so your AI \"thinks before it acts\" and learns from mistakes\n* Extended tool usage, including web browsing, search engine queries, and LLM-driven text\u002Fimage analysis\n* [Experimental] Multi-agent collaboration, with o1 doing the planning, and regular Claude\u002FGPT-4o doing the execution.\n\n## Why This Matters\n\nDevin impressed many by acting like an intern who writes its own plan, updates that plan as it progresses, and even evolves based on your feedback. But you don't need Devin's $25\u002Ftask pricing to get most of that functionality. By customizing the .cursorrules file, plus a few Python scripts, you'll unlock the same advanced features inside Cursor.\n\n## Key Highlights\n\n1.\tEasy Setup\n   \n   Two ways to get started:\n\n   **Option 1: Using Cookiecutter (Recommended)**\n   ```bash\n   # Install cookiecutter if you haven't\n   pip install cookiecutter\n\n   # Create a new project\n   cookiecutter gh:grapeot\u002Fdevin.cursorrules --checkout template\n   ```\n\n   **Option 2: Manual Setup**\n   Copy the `tools` folder and the following config files into your project root folder: Windsurf users need both `.windsurfrules` and `scratchpad.md` files. Cursor users only need the `.cursorrules` file. Github Copilot users need the `.github\u002Fcopilot-instructions.md` file.\n\n2.\tPlanner-Executor Multi-Agent (Experimental)\n\n   Our new [multi-agent branch](https:\u002F\u002Fgithub.com\u002Fgrapeot\u002Fdevin.cursorrules\u002Ftree\u002Fmulti-agent) introduces a high-level Planner (powered by o1) that coordinates complex tasks, and an Executor (powered by Claude\u002FGPT) that implements step-by-step actions. This two-agent approach drastically improves solution quality, cross-checking, and iteration speed.\n\n3.\tExtended Toolset\n\n   Includes:\n   \n   * Web scraping (Playwright)\n   * Search engine integration (DuckDuckGo)\n   * LLM-powered analysis\n\n   The AI automatically decides how and when to use them (just like Devin).\n\n   Note: For screenshot verification features, Playwright browsers will be installed automatically when you first use the feature.\n\n4.\tSelf-Evolution\n\n   Whenever you correct the AI, it can update its \"lessons learned\" in .cursorrules. Over time, it accumulates project-specific knowledge and gets smarter with each iteration. It makes AI a coachable and coach-worthy partner.\n\t\n## Usage\n\nFor a detailed walkthrough of setting up and using devin.cursorrules with Cursor, check out our [step-by-step tutorial](step_by_step_tutorial.md). This guide covers everything from initial Cursor setup to configuring devin.cursorrules and using the enhanced capabilities.\n\n1. Choose your setup method:\n   - **Cookiecutter (Recommended)**: Follow the prompts after running the cookiecutter command\n   - **Manual**: Copy the files you need from this repository\n\n2. Configure your environment:\n   - Set up your API keys (optional)\n\n3. Start exploring advanced tasks—such as data gathering, building quick prototypes, or cross-referencing external resources—in a fully agentic manner.\n\n## Want the Details?\n\nCheck out our [blog post](https:\u002F\u002Fyage.ai\u002Fcursor-to-devin-en.html) on how we turned $20\u002Fmonth into $25\u002Ftask level AI capabilities in just one hour. It explains the philosophy behind process planning, self-evolution, and fully automated workflows. You'll also find side-by-side comparisons of Devin, Cursor, and Windsurf, plus a step-by-step tutorial on setting this all up from scratch.\n\nLicense: MIT\n","该项目旨在将Cursor或Windsurf IDE转变为类似Devin的高级AI助手。其核心功能包括自动化规划与自我进化、扩展工具使用（如网页浏览、搜索引擎查询和基于大模型的文本\u002F图像分析）以及实验性的多智能体协作。通过简单的配置文件自定义和少量Python脚本，用户可以以远低于Devin的成本获得相似的功能。此项目特别适合需要提高开发效率、希望通过低成本实现高级AI辅助编程能力的开发者或团队使用。","2026-06-11 03:40:10","high_star"]