🚀 The Vibe Coding Handbook

Awesome License: CC0-1.0 PRs Welcome

The definitive handbook for the next era of software development. Vibe coding simplifies development through AI agents, enabling builders to ship highly complex products rapidly.

The term was coined by Andrej Karpathy in February 2025:

"There's a new kind of coding I call 'vibe coding', where you fully give in to the vibes, embrace exponentials, and forget that the code even exists."

If you find this useful, please star this repo - it helps others discover it!

Note from the maintainer: I built this handbook because I was drowning in AI coding tool launches and couldn't find a single place that had everything organized with honest, actionable advice. Whether you're a senior dev evaluating agents or a complete beginner who just heard about "vibe coding" - this is the resource I wish existed when I started. I personally test and verify tools before adding them. If something is missing or outdated, open an issue or submit a PR.

🧭 What Should I Use? (The Complete 2026 Decision Guide)

The AI coding landscape shifted radically in early 2026 (the "Agentic Engineering" era). It's no longer about fancy autocomplete; it's about composing stacks of autonomous software agents.

Don't just pick one tool. Pick your workflow.

🟢 Level 1: "I Have Zero Coding Experience"

You want to describe an app in plain English and get a working product—without ever touching a terminal.

  • 🎯 For Full-Stack Web Apps: 👉 Use Lovable

    • Why it wins: Lovable auto-generates your Next.js frontend, connects it to a real Supabase backend PostgreSQL database, and handles one-click deployments to platforms like Vercel.
    • The "Vibe" Setup: Create an account, connect GitHub, type: "Build a habit tracker with user auth."
    • Limitations: Struggles with complex, non-standard backend logic (e.g., custom webhooks or heavy cron jobs).
    • Cost Thresholds: Free to start, but you hit message limits quickly. Pro is $20/mo.

  • 🎨 For Landing Pages & UI Blocks: 👉 Use v0 or bolt.new

    • Why it wins: v0 is unmatched for generating pixel-perfect React + Tailwind designs. Bolt.new goes further by running a full Node.js environment in your browser via WebContainers.
    • Quick Start: Go to v0.dev. Prompt: "A dark-mode pricing table with glassmorphism."

🟡 Level 2: "I Want An AI-Native IDE"

You are a developer who wants visual feedback, a rich ecosystem, and AI deeply integrated into every keystroke.

  • 👑 The Industry Standard: 👉 Use Cursor

    • Why it wins: Cursor's "Composer" feature orchestrates parallel AI agents to handle massive multi-file refactors. It sits on top of VS Code, so all your extensions work flawlessly.
    • Setup: Download app → Log in → (Optional) Add your own Anthropic API key to bypass Pro limits.
    • Pro Tip (Composability): Start your app in Lovable, push it to GitHub, then clone and open it in Cursor for advanced architectural changes.
    • Cost Thresholds: Free tier is very restrictive (slow requests). Pro ($20/mo) is essential for daily drivers.

  • ⚡ The Context-Aware Alternative: 👉 Use Windsurf

    • Why it wins: "Cascade" offers deeper, more persistent codebase awareness out of the box without needing extensive .cursorrules configurations. Features a generous free tier.

🔴 Level 3: "I'm a Power User. Give me Terminal Agents."

You want maximum control, privacy, and the ability to pipe different AI models (like Claude, Gemini, or Local Models) into your workflow.

  • 🧠 For Maximum Reasoning Power (API/CLI): 👉 Use Claude Code or OpenAI Codex

    • Why Claude wins: Anthropic's terminal agent natively harnesses Claude's 1M+ token context window. Best-in-class for deeply complex debugging.
    • Why Codex wins: The pioneer in generative coding models, heavily updated for 2026. OpenAI's direct Codex CLI integrations offer unmatched latency and deep logical puzzle-solving via o1/Codex reasoning architectures.
    • Performance Context: As of April 2026, Claude Opus variants and OpenAI Codex (o1-tier) paired with agentic scaffolding dominate the SWE-bench Verified leaderboard (consistently hitting between 75% and 82%).
    • Quick Start: npm install -g @anthropic-ai/claude-code → claude
    • Cost Thresholds: Pay-per-token API pricing. Warning: Extensive context use can rack up a $10 bill in a few hours if you aren't careful.

  • 🔧 For TUI Workflows & Open Source: 👉 Use OpenCode or Aider

    • Why OpenCode: Exploded in popularity in 2026. A powerful Terminal UI (TUI) that supports 75+ LLMs natively (use whatever API key you want).
    • Why Aider: The veteran open-source tool with the most battle-tested, git-aware, multi-file editing capabilities.
    • Quick Start (Aider): pip install aider-chat → aider --model claude-3-5-sonnet

🟣 Level 4: "I Want an Autonomous AI Software Engineer"

You want to assign a Jira ticket to an AI and go get coffee. Benchmark: Handling end-to-end multi-file implementations autonomously.

  • 🤖 For Enterprise-Grade Autonomy: 👉 Use Devin

    • Why it wins: The first fully sandboxed autonomous SWE. Incredible capabilities for handling full DevOps pipelines and deployments independently.
    • Cost: Enterprise pricing.

  • ✨ For Advanced Concurrent Agentic Power: 👉 Use Google Antigravity

    • Why it wins: Designed by Google DeepMind, Antigravity introduces revolutionary "Planning Mode" paradigms combined with extreme parallel tool execution. It acts less like a simple code editor and more like a Chief Technology Officer managing a local multi-agent system.
    • Performance Benchmark: Antigravity excels in navigating massive monorepos by dynamically creating multi-step implementation plans and requesting human architectural feedback before mutating code.

  • 🔓 The Open Source Champion: 👉 Use OpenHands

    • Why it wins: The premier free, self-hosted alternative to Devin. Run it locally via Docker, hook it up to Claude's API, and let it resolve your GitHub PRs autonomously.
    • Performance Benchmark: OpenHands + Claude scores incredibly high because the sophisticated agentic scaffolding allows the LLM to run bash commands and test its own code before submitting.
    • Quick Start (Docker required): 
      docker run -it --pull=always \
  -e WORKSPACE_BASE=$(pwd)/workspace \
  -v /var/run/docker.sock:/var/run/docker.sock \
  -p 3000:3000 docker.all-hands.dev/all-hands-ai/openhands:0.8

🥊 Deep Dives & Architectural Comparisons

If you are evaluating tools for an engineering team, don't rely on generic feature matrices. We have built deep technical head-to-head comparisons detailing workflow philosophies, actual SWE-bench data, and vendor lock-in risks for April 2026:

  1. The AI-Native IDE Battle: Cursor vs. Windsurf
  2. Terminal Agents: Claude Code vs. OpenCode (vs. Aider)
  3. App Builders: Lovable vs. Bolt.new vs. v0
  4. Autonomous SWEs: Devin vs. OpenHands
  5. System Architectures: Google Antigravity vs. OpenAI Codex

⚡ Instant Value: Copy/Paste Templates

Don't start from scratch. Use our April 2026 standardized templates to instantly upgrade how your AI coding tools behave. Drop these into your repositories right now:

🍳 The Prompt Recipes Cookbook

Context Engineering is the hardest part of AI development. Don't write prompts from scratch; use our framework-agnostic snippets:

📦 Vibe Coding Starter Kits

Need to instantiate a perfect environment? Use our setup guides:

🚧 How to Not Fail: Common Mistakes

AI coding tools are force multipliers, meaning they multiply your mistakes just as fast as your successes. Read our Deep Dive guides so you don't fall into the same expensive traps as everyone else:

Contents

AI Coding Agents

IDE-Based

Full-featured code editors with deeply integrated AI that can understand your entire codebase, edit multiple files, and execute commands autonomously.

  • Cursor - AI-first code editor built on VS Code. Industry benchmark for agentic IDE experience. Features Composer for multi-file editing, Tab for intelligent autocomplete, and deep codebase awareness. Personal pick - the one most people should start with. [Freemium] [Pro $20/Mo]
  • Windsurf - AI coding IDE by Codeium (acquired by Cognition in 2025). Strong context awareness across large codebases at competitive pricing. Features Cascade for multi-step agentic flows. [Freemium]
  • Void - Open-source AI code editor. Privacy-first alternative that lets you bring your own model/API key. No vendor lock-in. [Free] [Open Source]
  • Zed - High-performance editor written in Rust with built-in AI assistant. Known for blazing speed and multiplayer editing. [Free]
  • PearAI - Open-source AI code editor forked from VS Code with integrated AI chat and inline editing. Community-driven. [Free] [Open Source]
  • Melty - Open-source AI code editor that watches what you do and understands your codebase changes in real-time. [Free] [Open Source]
  • Trae - AI-native IDE by ByteDance. Free access to Claude and GPT models with agentic Builder mode. [Free]
  • VS Code + Copilot - Microsoft's editor with GitHub Copilot chat, inline suggestions, and agent mode deeply integrated. [Copilot Free Tier Available]
  • JetBrains IDEs + AI Assistant - IntelliJ, PyCharm, WebStorm etc. with JetBrains' own AI assistant and Copilot support. [Paid]
  • Neovim + AI Plugins - The hackable text editor with AI plugins like Copilot.vim, ChatGPT.nvim, and Avante.nvim for terminal purists. [Free] [Open Source]
  • Emacs + GPTel - AI assistant for Emacs. Chat with LLMs, generate code, inline editing. For Emacs die-hards. [Free] [Open Source]
  • Fleet - JetBrains' lightweight editor with AI capabilities. Polyglot, fast, collaborative. [Free]

Terminal / CLI

AI agents that operate from your terminal, reading, writing, and executing code with full system access.

  • Claude Code - Anthropic's terminal-native agentic coding tool. Best-in-class reasoning with Claude Opus/Sonnet. Can read/write files, run commands, search codebases, and manage git. Personal pick - best for complex, multi-file tasks. [Requires Claude Max Subscription]
  • Codex CLI - OpenAI's open-source CLI coding agent. Lightweight, fast, runs locally with configurable autonomy levels. [Free] [Open Source]
  • Aider - Open-source AI pair programming in your terminal. Git-aware, works with any LLM. One of the original CLI coding tools. Best-in-class for its edit format system. Personal pick - best open-source option. [Free] [Open Source]
  • Gemini CLI - Google's open-source terminal AI agent. Integrates with Gemini models with 1M token context. [Free] [Open Source]
  • Amazon Q Developer CLI - AWS's AI coding assistant for terminal with deep AWS infrastructure integration. [Free Tier Available]
  • Mentat - Open-source AI coding agent that understands your entire repo and coordinates changes across multiple files. [Free] [Open Source]
  • GPT Engineer - Specify what you want it to build in natural language. The AI asks clarifying questions, then generates the entire codebase. [Free] [Open Source]
  • Cline - Autonomous coding agent for VS Code terminal that can create/edit files, run commands, use the browser, and ask for human approval at each step. [Free] [Open Source]
  • Roo Code - Fork of Cline with additional features like multiple agent modes (Code, Architect, Ask) and custom instructions per-mode. [Free] [Open Source]
  • Goose - Open-source AI agent by Block (formerly Square) that automates coding tasks in your terminal. Extensible via MCP. [Free] [Open Source]
  • Plandex - Terminal-based AI coding agent designed for complex, multi-file tasks with built-in version control for AI changes. [Free] [Open Source]
  • Amp - AI coding agent from Sourcegraph. Terminal and IDE modes with deep code intelligence integration. [Free Tier Available]
  • Blackbox AI - Multi-model AI coding agent that uses a "Chairman" architecture - sends tasks to multiple models in parallel and picks the best result. [Freemium]

Browser-Based

Full development environments that run in your browser - no local setup required.

  • Replit - Cloud IDE with AI Agent that can build, debug, and deploy full-stack apps from natural language. All-in-one: editor, hosting, database, auth. [Freemium]
  • GitHub Codespaces - Full VS Code environment in the browser with Copilot integration and configurable compute. [Free Tier: 60 Hrs/Month]
  • Gitpod - Cloud development environments with AI integration. Spins up pre-configured dev environments instantly. [Free Tier Available]
  • StackBlitz - Browser-based IDE running Node.js natively via WebContainers technology. Zero-install, full npm support. [Free Tier Available]
  • Project IDX - Google's AI-enabled browser-based IDE for full-stack and multi-platform app development including Flutter, Angular, and more. [Free]
  • CodeSandbox - Instant cloud development environments with AI integration. Popular for frontend prototyping and sharing. [Freemium]
  • Glitch - Build full-stack web apps in your browser with instant hosting. Great for learning and quick prototyping. [Free]

Autonomous Software Engineers

AI agents designed to work as fully autonomous "junior developers" - they plan, code, test, and iterate with minimal human intervention.

  • Devin - Cognition AI's autonomous software engineer. Has its own IDE, terminal, and browser in a sandboxed environment. Can plan, code, test, and deploy entire features. [Paid] [From $500/Mo]
  • OpenHands - Open-source AI software development agent (formerly OpenDevin). Can browse the web, write code, execute commands. Free alternative to Devin. [Free] [Open Source]
  • SWE-agent - Princeton research project. Autonomous agent that solves real GitHub issues by reading code, making edits, and running tests. [Free] [Open Source]
  • Sweep - AI-powered junior developer that turns GitHub issues into pull requests automatically. [Free] [Open Source]
  • AutoCodeRover - Autonomous program improvement agent from NUS. Combines LLMs with code search to fix bugs and add features. [Free] [Open Source]
  • Agentless - Simpler, agentless approach to solving coding tasks - no complex agent scaffolding needed. [Free] [Open Source]
  • Cosine Genie - AI software engineer trained on real-world codebases. Understands complex repos and makes changes autonomously. [Paid]
  • Factory AI - Enterprise autonomous coding platform. Droids that handle refactoring, migrations, and code modernization. [Enterprise]

AI App Builders (No-Code)

Platforms where you describe an app in plain English and get a working, deployable application - the purest form of vibe coding. No coding knowledge needed.

  • Lovable - Describe your app → get a full-stack web app with UI, backend, auth, and database (Supabase). The current leader for non-technical founders building MVPs. Personal pick - closest to "describe and ship." [Freemium]
  • bolt.new - StackBlitz's AI app builder. Generates and runs full-stack apps in the browser with real-time preview and one-click deploy to Netlify. [Freemium]
  • v0 - Vercel's AI UI generator. Creates production-quality React + Tailwind CSS components from text prompts. Best for frontend/UI components. [Freemium]
  • Replit Agent - Replit's app builder agent. Describe what you want, it builds the full app including frontend, backend, database, and deploys it. [Paid]
  • Vybe - AI app builder that creates "living systems" - apps that include AI agents for ongoing monitoring, operation, and updates after build. [Beta]
  • Create - Describe the tool you need in plain English → get a working web app. Focused on internal tools and utilities. [Freemium]
  • Durable - AI website builder that generates a complete business website with copy, images, and contact forms in 30 seconds. [Paid]
  • Tempo - Visual AI editor for React apps. WYSIWYG editing where AI generates and modifies the code underneath. [Beta]
  • Softgen - AI full-stack app generator focused on Firebase-backed applications. Prompt → working app with database, auth, hosting. [Freemium]
  • Lazy AI - Build and deploy web apps from prompts with built-in backend, database support, and API integration. [Freemium]
  • Marblism - Generate SaaS boilerplate from descriptions. Outputs a deployable Next.js + Prisma + PostgreSQL codebase. [Freemium]
  • Base44 - AI-powered app builder (acquired by Wix). Build web apps from natural language descriptions. [Freemium]
  • Bubble - Visual no-code app builder with AI assistance. One of the most mature no-code platforms. [Freemium]
  • GPT Engineer (web) - Web version of GPT Engineer. Describe → build → deploy with a visual interface. [Freemium]
  • Vercel AI Playground - Vercel's suite of AI tools for building and deploying AI-powered web applications. [Freemium]
  • Appy Pie - No-code platform with AI for building mobile apps, websites, and chatbots. [Freemium]
  • Databutton - AI-powered app builder focused on data apps and internal tools. Prompt → working data app. [Freemium]
  • Buzzy - Turn Figma designs into working apps with AI. Design-first approach to app building. [Freemium]
  • Pico - Build micro-apps with a single prompt. Fast, simple, shareable web apps in seconds. [Free]
  • Literally Anything - Type anything → get a working web app. The simplest possible vibe coding interface. [Freemium]

AI Code Completion & Assistants

Inline code suggestions, autocomplete, and chat-based coding assistants - the broadest category of AI coding tools.

  • GitHub Copilot - The OG and most widely adopted AI coding assistant (90%+ developer awareness). Works in VS Code, JetBrains, Neovim, Xcode, and more. Now features agent mode. [Free Tier Available] [Pro $10/Mo]
  • Supermaven - Extremely fast code completion with the lowest latency in the industry (acquired by Cursor). 300K token context window. [Freemium]
  • Codeium - Free AI code completion supporting 70+ languages and 40+ IDEs. Also powers Windsurf IDE. [Free]
  • Tabnine - AI assistant focused on code privacy and enterprise security. Can run models fully on-premises for air-gapped environments. [Freemium]
  • Continue - Open-source AI code assistant for VS Code and JetBrains. Bring your own model - works with any LLM provider. [Free] [Open Source]
  • Tabby - Open-source, self-hosted AI coding assistant. Full control over your data, models, and infrastructure. [Free] [Open Source]
  • Sourcegraph Cody - AI assistant with unmatched codebase understanding via Sourcegraph's code graph. Best for navigating massive monorepos. [Freemium]
  • Augment Code - Enterprise-focused AI assistant designed for massive codebases (400K+ files). Deep architectural reasoning and team-wide context. [Paid]
  • FittenCode - Free AI coding assistant supporting VS Code, JetBrains, Vim, and more. Multi-language support. [Free]
  • CodeGeeX - Open-source multilingual AI coding assistant. Supports 20+ programming languages with IDE plugins. [Free] [Open Source]
  • Blackbox AI Code - AI code generation and search. Multi-model architecture for best results. [Freemium]
  • Bito - AI assistant for code generation, explanation, and performance optimization. Enterprise-friendly with on-prem options. [Freemium]
  • Pieces - AI coding assistant with a focus on workflow efficiency. Saves, organizes and contextualizes code snippets with AI. [Freemium]
  • Qodo (formerly CodiumAI) - AI that focuses on code integrity - generates meaningful tests, reviews logic, finds edge cases. [Freemium]
  • Morph - Fast AI coding assistant with competitive pricing. Focuses on code generation speed and accuracy. [Paid]
  • Poolside - Enterprise AI coding assistant trained on high-quality synthetic code data. Focus on security and privacy. [Enterprise]
  • Mintlify Writer - VS Code extension that auto-generates docstrings when you highlight a function. [Free]
  • AI Commits (VS Code) - Conventional commit message helper integrated into VS Code source control. [Free]

AI Code Review

AI tools that automatically review pull requests, catch bugs, and enforce standards.

  • CodeRabbit - AI-powered code review for pull requests. Catches bugs, security vulnerabilities, style issues. Has Issue Planner for proactive architecture suggestions. [Freemium Free For Open Source]
  • PR-Agent - Open-source AI tool for automated PR reviews, descriptions, and suggestions. By the makers of Qodo. [Free] [Open Source]
  • Ellipsis - AI code reviewer that runs on every PR. Catches bugs, suggests improvements, enforces coding standards. [Freemium]
  • Codacy - Automated code quality and security platform with AI analysis. Supports 40+ languages. [Freemium]
  • Sourcery - AI-powered code review focused on Python. Suggests refactorings and catches anti-patterns. [Freemium]
  • What The Diff - AI that writes PR descriptions and reviews your code changes in human-readable language. [Freemium]
  • GitHub Copilot Code Review - GitHub's built-in AI code review in pull requests. [Included With Copilot Subscription]

AI for Design → Code

Turn designs, mockups, screenshots, and wireframes into working code.

  • Screenshot to Code - Upload a screenshot → get working HTML/Tailwind/React/Vue code. Supports video → app demos too. Open-source. [Free] [Open Source]
  • Uizard - Hand-drawn wireframes → working UI designs → exportable code. Great for rapid prototyping ideas. [Freemium]
  • Galileo AI - Generate editable, high-fidelity UI designs from text descriptions. Produces clean, production-ready layouts. [Paid]
  • Locofy - Convert Figma/Adobe XD designs into production-ready frontend code (React, Next.js, React Native, etc.). [Freemium]
  • TeleportHQ - AI-powered website builder with Figma import and code export. Visual editor + code generation. [Freemium]
  • Anima - Figma-to-code tool. Generates React, Vue, HTML, and CSS from Figma designs with AI assistance. [Freemium]
  • Builder.io - Visual editor with Figma-to-code functionality. Generate React, Vue, Svelte, Angular code from designs. [Freemium]
  • Relume - AI website builder that generates sitemaps and wireframes from text, then exports to Figma or Webflow. [Paid]
  • Visily - AI-powered wireframing and prototyping tool. Convert screenshots, sketches, or text to editable wireframes. [Freemium]
  • Slicer - Capture interactive UI (animations, hover states) from live sites as AI-ready prompts. Pull components to a canvas for restyling, then export directly to Lovable, Claude Code, or Cursor. [Design To Code] [Freemium]

AI Debugging & Testing

AI tools that help find bugs, generate tests, explain errors, and ensure code quality.

  • ChatGPT - / Claude - Paste your error message or buggy code → get an explanation and fix. The simplest vibe debugging flow. [Freemium]
  • Jam - AI-powered bug reporting that auto-captures reproduction steps, console logs, network requests, and suggests fixes. [Freemium]
  • Qodo (formerly CodiumAI) - Generates comprehensive test suites, finds edge cases, and validates code logic automatically. [Freemium]
  • Trunk - AI-powered code quality platform: linting, formatting, security checks, merge queue management. [Freemium]
  • Snyk - AI-assisted security scanning for dependencies, code, containers, and infrastructure-as-code. [Freemium]
  • Socket - Detects supply chain attacks and malicious code in open source dependencies before they reach your project. [Freemium]
  • Sentry AI - Error monitoring platform with AI-powered issue grouping, root cause analysis, and fix suggestions. [Freemium]
  • Codex by Machinet - AI unit test generation for Java. Generates JUnit tests with high code coverage. [Freemium]
  • Diffblue Cover - Autonomous AI that writes Java unit tests at scale. Enterprise-focused. [Paid]
  • Meticulous - AI-generated end-to-end tests. Records user sessions and auto-generates tests that catch visual and functional regressions. [Paid]
  • Playwright - Microsoft's end-to-end testing framework. AI agents generate Playwright tests for reliable cross-browser testing. [Free] [Open Source]
  • Cypress - Modern web testing framework. Combine with AI to auto-generate test suites for your vibe coded apps. [Freemium] [Open Source]
  • Checkly - Monitoring and testing for APIs and web apps. AI-assisted test creation with Playwright. [Freemium]

AI Documentation Tools

AI that writes, maintains, and improves your documentation.

  • Mintlify - AI-native documentation platform. Docs-as-code workflow (Git + MDX). Auto-generates llms.txt files and MCP servers so AI agents can read your docs. [Freemium]
  • ReadMe - Interactive API documentation platform with AI-powered search, content auditing, and developer analytics. [Freemium]
  • Swimm - Code-coupled documentation that stays in sync with your codebase. AI auto-detects when docs go stale. [Freemium]
  • Stenography - Passive, real-time code documentation. Generates explanations and docstrings as you code without you doing anything. [Paid]
  • Notion AI - AI writing assistant built into Notion. Generate, summarize, and improve technical documentation. [Add On To Notion] [$10/Mo]
  • Scribe - Auto-generates step-by-step process documentation from screen captures. Great for SOPs and tutorials. [Freemium]
  • Theneo - AI-powered API documentation generator. Import from Postman, Swagger, or GraphQL → get beautiful docs. [Freemium]

Prompt Engineering for Code

Guides & Techniques

How to write better prompts that produce better AI-generated code.

Prompt Libraries & Templates

Pre-built prompts optimized for common coding tasks.

  • Awesome ChatGPT Prompts - Massive collection of curated prompts including many for coding. 100K+ stars.
  • Fabric - Open-source framework for augmenting humans using AI. Includes coding-specific "patterns" for code review, security analysis, and more.
  • Prompt Hub - Library of tested, production-ready prompts for various coding tasks.
  • FlowGPT - Community platform for sharing and discovering effective AI prompts.

Rules Files & System Prompts

Configuration files that tell AI coding agents how to behave in your specific project.

Context Engineering

The emerging discipline of feeding AI the right context to improve output quality - arguably the most important skill in vibe coding.

  • Repomix - Pack your entire repository into a single AI-friendly file for pasting into LLM chats. Smart token management. [Free] [Open Source]
  • code2prompt - Convert your codebase into an LLM-ready prompt with directory traversal, filtering, and token counting. [Free] [Open Source]
  • Agentic Context - Tools for structuring and managing context in agentic coding workflows. [Free] [Open Source]
  • AI Context Files - Proposed standard for .context files that help AI tools understand your project structure and conventions. [Free] [Open Source]
  • Files to Prompt - Simple CLI tool by Simon Willison to concatenate multiple files into a single prompt. [Free] [Open Source]
  • Codetex - Convert your code into context-optimized formats for AI consumption. [Free]
  • llms.txt Standard - Proposed standard for websites to provide LLM-friendly versions of their content (like robots.txt but for AI). [Specification]
  • CONTRIBUTING.md / CLAUDE.md patterns - Using project documentation files to give AI agents architectural context, coding standards, and project-specific instructions.

MCP Servers for Coding

Model Context Protocol (MCP) is an open standard by Anthropic that lets AI agents securely connect to tools, databases, and services. Think of it as "plugins for AI."

Official MCP Servers

From the official MCP repository maintained by Anthropic.