{"slug": "i-don-t-know-if-this-page-explains-why-the-product-exists", "title": "I don't know if this page explains why the product exists", "summary": "Durabl launched a production-ready React Router codebase that ships a persistent AI context system, built around a single CONTEXT.md entry point, to keep LLM coding tools consistent across sessions. Durabl claims the setup lets developers review a plan in 3 minutes instead of 3 hours and keep a codebase understandable 6 months in, countering what it describes as AI-invented patterns and self-contradicting code on other boilerplates. The codebase uses React Router's loader, action and component model with full SSR, file-based routing and typed data loading on web standards like Request and Response, and supports any LLM on a stack including Base UI and Zod.", "body_md": "Build with any LLM on the tech stack you trust, including:\n\nBase UI\n\nZod\n\nWhy it matters\n\nWhat does 3 months of architectural drift actually cost you?\n\nWhen you code with LLMs that suffer amnesia after every session, you aren’t building an app. You’re building a house of cards. The worst part? It looks fine. Until the day it doesn’t. And by then, the decay runs deeper than you want to admit.\n\nBuilding with AI on a self-correcting foundation\n\nYou start a new session. The AI picks up exactly where you left off.\n\nYou check the plan, not every line. 3 minutes, not 3 hours\n\nSix months in, you can still open any file and understand it.\n\nYou’re not afraid of your own codebase\n\nShip. Again.\n\nYou start a new project\n\nBuilding with AI on any other codebase\n\nAI invents plausible-but-wrong patterns\n\nAI code contradicts itself — and keeps going\n\nMore energy spent reviewing AI code than time saved writing it\n\nA codebase that ‘works’ but you’re too scared to touch\n\nStart again\n\nDecision-making compounds\n\nYou start a new project\n\nBuilding with AI on any other codebase\n\nAI invents plausible-but-wrong patterns\n\nAI code contradicts itself — and keeps going\n\nMore energy spent reviewing AI code than time saved writing it\n\nA codebase that ‘works’ but you’re too scared to touch\n\nBuilding with AI on a self-correcting foundation\n\nYou start a new session. The AI picks up exactly where you left off.\n\nYou check the plan, not every line. 3 minutes, not 3 hours\n\nSix months in, you can still open any file and understand it.\n\nYou’re not afraid of your own codebase\n\nStart again\n\nDecision-making compounds\n\nShip. Again.\n\nMeet Durabl\n\nThe only codebase engineered for how AI coding tools actually work\n\nOther boilerplates hand you a static template and hope for the best. Durabl ships with the persistent context your AI needs to build correctly — today and 6 months from now.\n\nProduction-ready codebase\n\nStart with every hard decision already made\n\nBuilt on React Router. Three concepts: loader, action, component. That's the entire model. Fewer abstractions. Fewer things AI can get wrong. Full SSR, file-based routing, and typed data loading — built on web standards like Request and Response, not proprietary APIs. Deploy anywhere, no vendor lock-in.\n\nThese cookies are essential in order to use the website and use its features.\n\nPersistent AI context\n\nGive your AI the correct context. Every session. Every task.\n\nAI forgets your app — and you can’t fit your entire codebase into a context window. Durabl ships a knowledge system with a single entry point. Your AI knows what to read before planning, what to understand before building, and where to find the relevant docs. So you can build fast, knowing your code will work.\n\nAI instruction files\n\nAI instruction files (CONTEXT.md) act as your AI's entry point into your project. Whatever AI tool you use, simply add one line to your config file pointing at CONTEXT.md, and your AI has all the context it needs to keep your code consistent.\n\nDocumentation files\n\nDocumentation files store the rules, rationale, and trade-offs that span your codebase. Your AI coding tool consults the relevant docs before modifying a file.\n\nInline comments\n\nInline comments embed the logic behind hyper-local decisions in the code itself. So instead of “improving” your decisions, AI preserves the behavior you prefer.\n\nconst event = awaitgetStripeEvent(request, stripe) // verifies the signature\n\n// Stripe delivers at-least-once: a retry or network blip means the\n\n// same event.id can arrive twice. Without this guard, a duplicate\n\n// 'checkout.session.completed' double-applies the subscription.\n\nif (awaiteventAlreadyHandled(event.id)) returndata({}, { status: 200 })\n\nswitch (event.type) {\n\ncase'checkout.session.completed': {\n\nconst session = event.data.object\n\nawaitupdateSubscriptionByUserId(session /* … */)\n\nreturndata({}, { status: 200 })\n\n}\n\n}\n\n}\n\nDocs entry\n\nIndex\n\nCONTEXT.md\n\nEntry point\n\nPayments\n\nArchitecture\n\nWebhooks\n\nPatterns\n\nTesting\n\nConventions\n\nADR-005\n\nWhy Stripe\n\nBackground\n\nJobs\n\nUI\n\nComponents\n\nMonitoring\n\nSetup\n\nBuilt-in AI skills\n\nAI that plans, tests, and self-corrects.\n\nBy default, AI assistants only do what you type. No testing. Missed edge cases. And fixing bugs is all on you. Building with Durabl is different. When you create new features, AI will load the right skills for each phase of work. Automatically.\n\nYou don’t need to configure a thing.\n\nWhat is an AI skill in Durabl?\n\nBetter input. Better output. Zero extra work.\n\nDurabl’s skills are Markdown files that give your AI expert-level instructions for a specific task. Readable, editable, and version-controlled. Giving you senior–dev standard prompting — even if you’re not a prompt engineer.\n\nDurabl’s growing library of AI skills includes:\n\nPlan\n\nDefine intended state → map current-to-intended → surface hidden assumptions → validate with developer\n\nImplement\n\nExecute plan → check off items → review code → write tests\n\nValidate\n\nRun ESLint → type check → format → commit → push → wait for CI\n\nBug-squash\n\nOn any failure, re-enter the full cycle: re-plan → re-implement → re-validate\n\nExpand docs\n\nWrite decisions back into your docs → your AI gets smarter with every feature\n\nMost AI tools treat your conversations as disposable. With Durabl, every plan is stored as a file in your repo. So if your laptop dies or you close the wrong window, nothing is lost. Start a new session, say \"continue,\" and the AI picks up exactly where you left off. No re-explaining. No lost context. No starting over.\n\nAI skills don't run in sequence — they compose.\n\nPlan\n\nDone\n\nDefine intended state → map current-intended → surface hidden assumptions → validate with developer\n\nImplement\n\nDone\n\nExecute plan → check off items → review code → write tests\n\nValidate\n\nRunning\n\nRun ESLint → type check → format → commit → push → wait for CI\n\nDone\n\nSelf-correcting workflows for new features\n\nYour AI loads the planning skill, surfaces every hidden assumption, and waits for your sign-off — before writing a line of code. Once you approve, implementation and validation skills take over automatically. No manual handoffs.\n\nPlan\n\nDone\n\nDefine intended state → map current-intended → validate with developer\n\nImplement\n\nDone\n\nExecute plan → check off items → review code → write tests\n\nValidate\n\nFail\n\nRun ESLint → type check → format → fail\n\nCheck failed - bug squash activates\n\nRe-plan\n\nDiagnose failure → update plan\n\nRe-implement\n\nApply fix → update plan\n\nRe-validate\n\nRun checks again\n\nAll checks pass - exit loop\n\nDone\n\nDebugging that doesn’t stop until the result is clean\n\nWhen a check fails — and it will — the bug-squashing skill kicks in, cycling back through planning, implementation, and validation. It keeps going until every check passes. You don't intervene. You don't re-explain. It just works.\n\nSee how it works\n\nSee how Durabl prevents your codebase decaying over time\n\nWatch a real-life example of AI following a project's patterns, not inventing its own.\n\nAI Integrations\n\nMaintain consistent code with any AI\n\nCopilot\n\nCursor AI\n\nClaude\n\nDevin Desktop\n\nGemini\n\nChatGPT\n\nPremium code quality\n\nFind a bug? Claim your bounty.\n\nSome boilerplates are notorious for security issues. We’re so confident in Durabl’s codebase that if you find any vulnerability — we’ll literally pay you for it.\n\nI’ve built more than 100 software applications over 20+ years, working with clients including Monster Energy and NBC News.\n\nOver the last 2 years, I kept seeing the same failure pattern play out. AI generates code fast. But it has no memory between sessions. Codebases degrade. Entropy compounds until the whole thing becomes unmaintainable.\n\nCorrectness, not speed, is now the biggest bottleneck.\n\nEvery boilerplate I looked at was solving the old problem: save time on setup. So I built a codebase that solves the new one: keeping code correct as AI builds at velocity.\n\nI use it for every new project. It's the foundation I wish I'd had 2 years ago.\n\nTestimonials\n\nWhat devs say about Durabl\n\n“As a seasoned developer, I’ve spent countless hours wrestling with infrastructure, best practices, and endless decisions. It’s exhausting. With Durabl, I had a production-ready app and staging environment set up in 10 minutes. Unreal. Where has this been all my life?”\n\n“I used to spend a lot of time setting up everything, the environments, deploying, choosing the tools that I wanted to use. With Durabl, I can spend time building and not setting up. I’m really excited to use it more, to build new products and to launch it fast.”\n\n“Durabl saved me a lot of time and work that I would have spent designing components that could be reused. Now I can focus more on the software architecture and commercial aspects of our products.”\n\n“I had an excellent experience using Durabl, especially as someone new to working with React Router. The comprehensive documentation that comes with it made getting up to speed easy.”\n\nNo vendor lock-in. Switch vendors with a single line of code\n\nGuarantee\n\n90-day satisfaction guarantee\n\nWe’re confident your app will stay maintainable over time with Durabl. Not so after 90 days? You get your money back — no questions asked.\n\n(OK, maybe some questions. But only to improve our product.)\n\nSATISFACTION\n\n90-day\n\nGUARANTEE\n\nPricing\n\nStart building on a codebase you can still maintain after 3 months\n\n449€\n\n349€\n\nSpecial launch discount\n\nOne-time fee 90-day satisfaction guarantee\n\nINCLUDES\n\nProduction-ready React Router framework\n\nResend email integration\n\nStripe payments integration\n\nOAuth authentication integration\n\nSQLite & PostgreSQL database integration\n\nSEO-optimized\n\nComplete UI library with Tailwind CSS & shadcn/ui\n\nProduction-ready CI/CD workflow\n\nVitest & Playwright testing integrations\n\nSentry & Grafana monitoring integration\n\nGoogle Analytics (GA4) & Microsoft Clarity integration\n\nPersistent AI context\n\nBuilt-in AI error correction\n\nCustomer support via GitHub/email\n\nLifetime access to updates\n\nStart Building with Durabl\n\nNot ready yet? Get an email when Durabl changes.\n\nEmailEmail me\n\nFrequently asked questions\n\nGot questions?\n\nWe have answers.\n\nWhat is a boilerplate?\n\nA boilerplate is a starting state for a software project. It encodes decisions — architecture, tooling, patterns, conventions — so you don’t start from zero. The value is: decisions already made, correctly.\n\nHow is Durabl different from other boilerplates?\n\nWhy should I buy a codebase when so many are free?\n\nWon’t codebases like Durabl become irrelevant as AI improves?\n\nCan’t I just add AI governance files to my existing project?\n\nI have different tools in my tech stack. Can I still use Durabl?\n\nHow do I get access to the Durabl codebase?\n\nHow fast can I set up an app with Durabl?\n\nWhere is Durabl deployed to?\n\nAre there any 3rd party costs associated with using Durabl?", "url": "https://wpnews.pro/news/i-don-t-know-if-this-page-explains-why-the-product-exists", "canonical_source": "https://durabl.dev", "published_at": "2026-10-26 09:17:33+00:00", "updated_at": "2026-10-26 09:47:22.802532+00:00", "lang": "en", "topics": ["ai-tools", "developer-tools", "large-language-models", "ai-agents"], "entities": ["Durabl", "React Router", "Base UI", "Zod", "Stripe"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/i-don-t-know-if-this-page-explains-why-the-product-exists", "markdown": "https://wpnews.pro/news/i-don-t-know-if-this-page-explains-why-the-product-exists.md", "text": "https://wpnews.pro/news/i-don-t-know-if-this-page-explains-why-the-product-exists.txt", "jsonld": "https://wpnews.pro/news/i-don-t-know-if-this-page-explains-why-the-product-exists.jsonld"}}