{"slug": "n-code-ai-studio-turning-website-audits-into-a-side-hustle-with-open-weight-ai", "title": "N-CODE AI Studio: Turning Website Audits into a Side Hustle with Open-Weight AI", "summary": "A developer built N-CODE AI Studio, an open-source website auditing platform that runs Lighthouse in headless Chrome via GitHub Actions and feeds the audit findings to a locally hosted Gemma 3 model through Ollama to generate prioritized improvement recommendations. In a test against ncodest.com, the October 15, 2026 mobile Lighthouse run scored 57/100 for performance, 78/100 for accessibility, and 100/100 for SEO and best practices, with Gemma producing recommendations on accessibility, semantic structure, labels, contrast, and performance. The project, released under the MIT License, is an early-stage prototype whose business concept has not been validated with paying customers.", "body_md": "*This is a submission for the [Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle](https://dev.to/challenges/hacktoberfest-week2-2026-10-12).*\n\nI built **N-CODE AI Studio**, an open-source AI-powered website auditing platform designed to help freelancers, small businesses, and web development agencies understand website performance and identify opportunities for improvement.\n\nMany small business owners struggle to understand technical reports or know which website problems to fix first.\n\nN-CODE AI Studio aims to turn technical website measurements into clear, actionable recommendations using open-weight AI.\n\n**The side hustle idea:** Freelancers can use this tool to prepare website health assessments and offer professional performance optimization, accessibility improvements, SEO consulting, and website redesign services.\n\nThe product is an early-stage prototype. This business concept has not yet been validated with paying customers.\n\n**Application:** [https://ncode-ai-studio-hf26.vercel.app/](https://ncode-ai-studio-hf26.vercel.app/)\n\n**Case Study:** [https://ncode-ai-studio-hf26.vercel.app/case-study](https://ncode-ai-studio-hf26.vercel.app/case-study)\n\n**Verified Lighthouse + Gemma AI Execution:**\n\n[https://github.com/Deshan217/ncode-ai-studio-hf26/actions/runs/38784847640](https://github.com/Deshan217/ncode-ai-studio-hf26/actions/runs/38784847640)\n\n**Raw Test Evidence:**\n\n[https://github.com/Deshan217/ncode-ai-studio-hf26/actions/runs/38784847640/artifacts/11998425425](https://github.com/Deshan217/ncode-ai-studio-hf26/actions/runs/38784847640/artifacts/11998425425)\n\nThe verified demonstration runs Lighthouse in a GitHub Actions environment and generates recommendations using Gemma 3 through Ollama.\n\nThe hosted Vercel application currently demonstrates the interface and case study. Live cloud AI inference and production PageSpeed API quota configuration remain separate deployment improvements.\n\nThe project is publicly available on GitHub under the MIT License.\n\n**GitHub Repository:**\n\n[https://github.com/Deshan217/ncode-ai-studio-hf26](https://github.com/Deshan217/ncode-ai-studio-hf26)\n\nThe repository contains the Next.js application, audit processing logic, Ollama integration, test workflows, documentation, and reproducible AI testing configuration.\n\nI used the following technologies:\n\nThe application is designed to accept a public HTTPS website URL, collect audit findings, and generate an understandable improvement report.\n\nFor the verified demonstration, GitHub Actions runs Lighthouse directly in headless Chrome, extracts website audit findings, and provides those findings to a locally running Gemma model through Ollama.\n\nThe AI then generates prioritized recommendations that a developer or website consultant can review.\n\nI tested the workflow against the N-CODE STUDIO website:\n\n**Website:** [https://ncodest.com/](https://ncodest.com/)\n\nThe October 15, 2026 Lighthouse run produced the following mobile lab scores:\n\n| Category | Score | \n|---|---|\n| Performance | 57/100 | \n| Accessibility | 78/100 | \n| SEO | 100/100 | \n| Best Practices | 100/100 | \n\nThe Gemma model successfully generated recommendations related to accessibility, semantic structure, accessible labels, contrast, and performance optimization.\n\nThese results come from a single lab run and should not be interpreted as ongoing measurements or a guarantee of user experience. AI-generated recommendations require human review.\n\nOne challenge was Google PageSpeed Insights API quota limits.\n\nAlthough local Gemma inference worked, the first end-to-end attempt could not retrieve audit data because the PageSpeed API quota had been exceeded.\n\nTo produce reproducible evidence, I implemented a separate GitHub Actions workflow using Lighthouse directly with headless Chrome, without depending on the PageSpeed API.\n\nThis workflow successfully completed both a real Lighthouse audit and real open-weight AI inference.\n\nAnother challenge is hosting: an Ollama instance running locally is not automatically accessible to a cloud-hosted Next.js application. A secure production AI service is part of the future roadmap.\n\nOpen innovation gives independent developers the freedom to experiment, learn, customize, and build useful products without depending entirely on proprietary AI platforms.\n\nUsing Gemma through Ollama makes it possible to run the language model under developer control.\n\nFor N-CODE AI Studio, this provides several advantages:\n\nThe complete application is shared under the MIT License.\n\nMy goal is to make useful AI-assisted website consulting more accessible to independent developers and smaller businesses.\n\nMy future plans for N-CODE AI Studio include a securely hosted AI inference service, better audit reporting, user authentication, rate limiting, audit history, and professional client-ready reports.\n\nI also want to collect feedback from freelancers and small business owners to see whether this tool can become a practical, affordable website consulting product.\n\n**Built by N-CODE STUDIO for Hacktoberfest 2026.**\n\nThank you to the open-source community and the developers building accessible AI tools!\n\n**Best Use of Gemma**\n\nN-CODE AI Studio uses Google's open-weight Gemma 3 1B model through Ollama to transform real Lighthouse audit measurements into actionable website improvement recommendations.\n\nThe model was successfully executed and tested using GitHub Actions, with real inference results and supporting evidence available in the public repository.", "url": "https://wpnews.pro/news/n-code-ai-studio-turning-website-audits-into-a-side-hustle-with-open-weight-ai", "canonical_source": "https://dev.to/deshan_nethmina_0789e81a2/n-code-ai-studio-turning-website-audits-into-a-side-hustle-with-open-weight-ai-bh", "published_at": "2026-10-16 04:59:05+00:00", "updated_at": "2026-10-16 05:04:56.209785+00:00", "lang": "en", "topics": ["ai-tools", "large-language-models", "developer-tools", "ai-products"], "entities": ["N-CODE AI Studio", "Gemma 3", "Ollama", "Lighthouse", "GitHub Actions", "Google PageSpeed Insights", "Vercel", "ncodest.com"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/n-code-ai-studio-turning-website-audits-into-a-side-hustle-with-open-weight-ai", "markdown": "https://wpnews.pro/news/n-code-ai-studio-turning-website-audits-into-a-side-hustle-with-open-weight-ai.md", "text": "https://wpnews.pro/news/n-code-ai-studio-turning-website-audits-into-a-side-hustle-with-open-weight-ai.txt", "jsonld": "https://wpnews.pro/news/n-code-ai-studio-turning-website-audits-into-a-side-hustle-with-open-weight-ai.jsonld"}}