# ogbuilds

> ogbuilds is og's independent app studio. 18 products, all designed and built in-house: moggd, invoice·me, seo·check, agent·shield, nudge, quality·vibes, spotlight, gromitor, robot·guard, echo, accent·ai, reportr, dsl·ai, verif·ai, gif·ai, tokki, flingdows, and omniscia.

ogbuilds is an independent, solo-run app studio. Each app below is designed and built in-house. Copy here is the canonical description of each product.

A fuller version with a short summary for every guide: https://ogbuilds.ai/llms-full.txt

## Apps
- [moggd](https://ogbuilds.ai/moggd): who mogs more?. moggd settles it: who mogs more? Point your phone at you and a friend, both pull your hardest mog face, and moggd scores it on the spot. In person, in seconds. Then share who won.
- [invoice·me](https://ogbuilds.ai/invoiceme): professional invoices, exported in seconds. Fill in your details and line items, set your tax and currency, and download a perfectly formatted invoice as PDF, PNG, or Word. Free to create, with your own branding and a saved history on Pro.
- [seo·check](https://ogbuilds.ai/seocheck): score your page for search + ai answer engines. Paste a URL and get a scored audit of on-page SEO, GEO (how ready a page is for AI answer engines), and sitemap health. Every check is marked pass, warn, or fail with a one-line fix. Free, no account, nothing stored.
- [agent·shield](https://ogbuilds.ai/agentshield): a human in the loop for your ai agents. A security firewall for AI agents. Point your agent at agent·shield and it forwards safe traffic instantly, holds destructive actions for a human to approve, and logs every decision. No agent rewrite. Just change one url.
- [nudge](https://ogbuilds.ai/nudge): one-tap nudges between friends. Connect with a friend by scanning a QR code, then nudge each other with one tap. Every nudge fires a push notification to their phone and a burst of particles in the app. Installable, no login screen, nothing to set up.
- [quality·vibes](https://ogbuilds.ai/qualityvibes): security scores for vibe-coded apps. Paste a GitHub repo and get a security score with six subscores, every issue found with file and line, and ready-to-paste Claude prompts that fix them. Built for apps that shipped faster than their security review. The same scan returns a second 0-100 score for code cleanliness, and it'll review an open pull request on that same quality scale.
- [spotlight](https://ogbuilds.ai/spotlight): crystal-clear web ui feedback. Contextual feedback for web UI. Comment directly on the html elements that matter, then share it with your whole team. It's a Chrome extension plus a web app, built for product teams, designers, and QA.
- [gromitor](https://ogbuilds.ai/gromitor): real-time container monitoring, one agent away. Real-time, cross-platform container resource monitoring as a lightweight SaaS. Drop one read-only agent on Docker or Kubernetes and watch live CPU, memory, network, and disk per container, with threshold alerts and no open-source tools to deploy.
- [robot·guard](https://ogbuilds.ai/robot.guard): smart robots.txt that pays for itself. A robots.txt manager that keeps the crawlers you want and leaves out the AI scrapers you don't. Pick the good bots, skip the ones eating your bandwidth, and ship a clean file in a click.
- [echo](https://ogbuilds.ai/echo): email that sounds like you. An AI email assistant that learns your communication style from your own gmail, then drafts replies in your voice. Connect one account, review the draft, send. Nothing leaves without your tap.
- [accent·ai](https://ogbuilds.ai/accentai): practice english by talking. An AI conversational tutor for english learners. Pick a real-life scenario, speak your side out loud, and get instant grammar and phrasing feedback after every line. Judgment-free practice you can do alone, any time.
- [reportr](https://ogbuilds.ai/reportr): one-click client reports. A Chrome extension that reconciles insurance commission statements into branded, white-label client reports. It checks every line against your book of business, flags what's short-paid or unpaid, and exports a PDF with your own logo. No spreadsheets, no copy-paste.
- [dsl·ai](https://ogbuilds.ai/dslai): make any llm speak your dsl. Paste your domain-specific language's grammar and dsl·ai turns it into generation that can't be syntactically wrong, plus a deterministic validator that pinpoints where input breaks. No fine-tune, no GPU.
- [path·ai](https://ogbuilds.ai/pathai): curated paths through ai/ml. A free tool that turns any ai/ml topic into an ordered learning path. Each module pairs the best resource to read or watch with runnable code. No account.
- [verif·ai](https://ogbuilds.ai/verifai): spot ai-generated content. A Chrome extension that detects and highlights AI-generated images and text on the page you're reading. One click, a clear confidence score, no account.
- [gif·ai](https://ogbuilds.ai/gifai): edit any gif with a prompt. A Chrome extension. Paste any GIF, describe the change, and gif·ai re-renders it consistently across every frame, no flicker, no redraw.
- [tokki](https://ogbuilds.ai/tokki): turn clout into competition. The friends-first growth game for TikTok. Connect your account, compete with friends you invite, and earn collectible badges. No ads. 18+.
- [flingdows](https://ogbuilds.ai/flingdows): throw your windows around. A free, open-source Mac window manager with a twist: flick a window and it flies across the screen with real momentum, glides to a stop, and springs back from the edges. Free and MIT-licensed.
- [omniscia](https://omniscia.app): ai creative intelligence for advertisers. A platform for performance marketers. omniscia scores your video and image ad creative, flags creative-clustering risk against Meta's Andromeda algorithm, and ties every score back to real spend across Meta, Google, and TikTok.

## Guides
- [How to run a silly face-off with friends online (the committed-to-the-bit kind)](https://ogbuilds.ai/moggd/compare-faces-with-friends-online): A face-off with friends has nothing to do with who looks better. It's about who commits hardest to the dumbest face. Here's how to run a lighthearted online face-off and turn it into something you can share.
- [What is the 'mog face' trend, and how to join in without taking it seriously](https://ogbuilds.ai/moggd/what-is-the-mogging-trend): The 'mog face' trend is about pulling the most exaggerated, committed silly face for the camera. A bit, not a beauty contest. Here's what it means and how to join in for the joke.
- [The best way to make funny face-off videos with friends (vs. generic comparison apps)](https://ogbuilds.ai/moggd/best-apps-for-funny-faceoff-videos): Generic photo and video comparison apps weren't built for the silly-face bit. Here's how a purpose-built face-off game like moggd compares for making funny head-to-head videos with friends.
- [What is a 'mog score' and how is it calculated? (Spoiler: it scores the bit, not your face)](https://ogbuilds.ai/moggd/how-mog-score-is-calculated): A 'mog score' is a playful number out of 100 for how hard you committed to a silly face. It's a comedy device, not a looks rating. Here's what it measures and how to push yours higher.
- [Making shareable content with your friend group (without needing to be a creator)](https://ogbuilds.ai/moggd/make-shareable-content-with-friends): Inside jokes between friends get shared harder than anything polished. Here's how to turn a silly group bit into something worth posting, and where a face-off game like moggd fits.
- [TikTok challenge ideas: make your own face-off content with friends](https://ogbuilds.ai/moggd/tiktok-challenge-ideas-faceoff-content): Want a TikTok challenge your friends will actually do? Face-off content is easy, repeatable, and funny. Here are challenge ideas built around the silly-face head-to-head bit.
- [Gen Z's guide to lighthearted social-media rivalry (the fun kind)](https://ogbuilds.ai/moggd/gen-z-guide-to-lighthearted-rivalry): Not all online competition is toxic. A lighthearted rivalry with friends, like a silly-face face-off, is one of the best ways to stay close. Here's how to keep the rivalry fun.
- [Easy ways to make animated comparison videos for Instagram Reels](https://ogbuilds.ai/moggd/make-animated-comparison-videos-for-reels): Animated head-to-head comparison videos do well on Reels, but building them by hand is fiddly. Here's the easy way to make a funny animated face-off video sized for Instagram Reels.
- [How to write an invoice](https://ogbuilds.ai/invoiceme/how-to-write-an-invoice): Learn how to write an invoice step by step: the header, your details, client details, itemised charges, tax, totals and payment terms. A clear, practical walkthrough.
- [What to include on an invoice](https://ogbuilds.ai/invoiceme/what-to-include-on-an-invoice): The complete checklist of what to include on a professional invoice: invoice number, dates, business and client details, itemised charges, tax, totals and payment terms.
- [Invoice vs receipt](https://ogbuilds.ai/invoiceme/invoice-vs-receipt): Invoice vs receipt explained: an invoice requests payment before it's made, a receipt proves payment was received. Learn when to issue each and what they must show.
- [What is a VAT invoice?](https://ogbuilds.ai/invoiceme/what-is-a-vat-invoice): A VAT invoice is a tax document showing VAT charged on a sale. Learn what it must show, when you must issue one, and the difference between full and simplified VAT invoices.
- [How to add tax to an invoice](https://ogbuilds.ai/invoiceme/how-to-add-tax-to-an-invoice): How to add VAT, GST or sales tax to an invoice: tax-exclusive vs tax-inclusive pricing, calculating the tax amount, and showing multiple tax lines correctly.
- [How to invoice as a freelancer](https://ogbuilds.ai/invoiceme/how-to-invoice-as-a-freelancer): How to invoice as a freelancer or sole trader: what details to include, when to send, how to set rates and terms, and how to keep records clean for tax time.
- [Proforma vs commercial invoice](https://ogbuilds.ai/invoiceme/proforma-vs-commercial-invoice): Proforma vs commercial invoice explained: a proforma is a preliminary quote-style document; a commercial invoice is the final demand for payment. When to use each.
- [Invoice payment terms explained](https://ogbuilds.ai/invoiceme/invoice-payment-terms-explained): Invoice payment terms explained: what Net 30, Net 14, Due on Receipt and EOM mean, how to choose terms, and how clear terms help you get paid on time.
- [How to get invoices paid faster](https://ogbuilds.ai/invoiceme/how-to-get-invoices-paid-faster): How to get invoices paid faster and reduce late payment: invoice promptly, set short clear terms, make paying easy, automate reminders and follow up consistently.
- [A free SEO checker: paste any URL, get a scored audit, no account](https://ogbuilds.ai/seocheck/free-seo-checker): Free SEO checker: paste any URL and seo·check scores your on-page SEO, GEO readiness, and sitemap health in seconds. No sign-up, no paywall, no crawl limit.
- [A GEO checker tool: see if AI answer engines can use your page](https://ogbuilds.ai/seocheck/geo-checker-tool): GEO checker tool: seo·check scores your page for AI answer-engine readiness, covering JSON-LD, llms.txt, and AI-crawler access for GPTBot, ClaudeBot, and PerplexityBot.
- [Is my site optimized for AI search? Run a free readiness check](https://ogbuilds.ai/seocheck/is-my-site-optimized-for-ai-search): Is your site optimized for AI search? seo·check scores AI-crawler access, JSON-LD, llms.txt, and sitemap freshness from a URL. Free, no account, in seconds.
- [How to check if AI crawlers can access your site (and why they might not)](https://ogbuilds.ai/seocheck/check-if-ai-can-crawl-my-site): How to check if AI can crawl your site: seo·check reads your robots.txt and reports whether GPTBot, ClaudeBot, PerplexityBot, and Google-Extended are allowed.
- [How to check your llms.txt: does it exist, and is it reachable?](https://ogbuilds.ai/seocheck/how-to-check-llms-txt): How to check llms.txt: seo·check looks for an llms.txt at your site root, confirms it's reachable, and folds the result into your GEO readiness score. Free.
- [A structured data checker: see if your JSON-LD helps search and AI engines](https://ogbuilds.ai/seocheck/structured-data-checker): Structured data checker: seo·check detects JSON-LD on your page and scores it as part of your SEO and GEO readiness. Free, from a URL, no account needed.
- [An AI search readiness checker: one score for crawler access, schema, and llms.txt](https://ogbuilds.ai/seocheck/ai-search-readiness-checker): AI search readiness checker: seo·check rolls AI-crawler access, JSON-LD, llms.txt, and sitemap freshness into one GEO readiness score from a URL. Free.
- [A free SEO audit: on-page, GEO, and sitemap, in one report](https://ogbuilds.ai/seocheck/free-seo-audit): Free SEO audit: seo·check scores your title, meta, H1, canonical, and OG tags plus GEO readiness and sitemap health from a URL. Free, no account, no crawl cap.
- [seo·check vs paid SEO audit suites: when a free checker is all you need](https://ogbuilds.ai/seocheck/seocheck-vs-paid-seo-audit-tools): seo·check vs paid SEO audit tools: free, no-account on-page + GEO + sitemap scoring from a URL vs heavyweight subscription suites. When each one is the right call.
- [What is generative engine optimization (GEO)?](https://ogbuilds.ai/seocheck/what-is-generative-engine-optimization-geo): GEO is optimizing your content to be cited by AI answer engines like ChatGPT, Perplexity, and Google AI Overviews. Here's what it is and how it differs from SEO.
- [How to get cited by ChatGPT and Perplexity](https://ogbuilds.ai/seocheck/how-to-get-cited-by-chatgpt-and-perplexity): AI answer engines cite sources they can read and quote with confidence. Here are the concrete on-page changes that get your content cited by ChatGPT and Perplexity.
- [llms.txt explained: the sitemap for AI](https://ogbuilds.ai/seocheck/llms-txt-explained): llms.txt is a plain-text file that gives AI answer engines a clean, link-rich map of your best content. Here's what it is, what goes in it, and how to write one.
- [JSON-LD structured data for AI search](https://ogbuilds.ai/seocheck/json-ld-structured-data-for-ai-search): JSON-LD tells search and AI answer engines exactly what your content is. Here's which schema types matter for AI search and how to add them correctly.
- [FAQ and HowTo schema: a practical guide](https://ogbuilds.ai/seocheck/faq-and-howto-schema-guide): FAQPage and HowTo schema turn your Q&A and step content into rich results and AI-answer fodder. Here's how to implement both correctly and avoid penalties.
- [E-E-A-T signals for AI search](https://ogbuilds.ai/seocheck/e-e-a-t-signals-for-ai-search): Experience, Expertise, Authoritativeness, and Trust shape what search and AI engines cite. Here are the on-page E-E-A-T signals that actually move the needle.
- [robots.txt for AI crawlers: GPTBot, ClaudeBot & more](https://ogbuilds.ai/seocheck/robots-txt-for-ai-crawlers): AI crawlers like GPTBot, ClaudeBot, PerplexityBot, and Google-Extended obey robots.txt. Here's how to allow (or block) them and avoid blocking yourself by accident.
- [XML sitemap best practices](https://ogbuilds.ai/seocheck/sitemap-best-practices): A clean sitemap.xml helps search and AI engines discover and prioritize your pages. Here are the sitemap best practices that actually affect crawling and indexing.
- [The on-page SEO checklist](https://ogbuilds.ai/seocheck/on-page-seo-checklist): A practical on-page SEO checklist: titles, meta descriptions, headings, canonicals, Open Graph, image alt text, internal links, and structured data, and what to fix first.
- [AI agent guardrails: stop the agent at the dangerous request, not after it](https://ogbuilds.ai/agentshield/ai-agent-guardrails): AI agent guardrails should stop a destructive action before it lands, not log it after. agent·shield holds DELETEs, drop-table and rm -rf for human approval.
- [How to put a human in the loop for an AI agent's destructive actions](https://ogbuilds.ai/agentshield/human-approval-for-ai-agents): Add human approval to an AI agent without rewriting it. Route its traffic through agent·shield, write hold policies, then approve or deny in a queue.
- [Approve AI agent actions: a manual checkpoint for the calls that matter](https://ogbuilds.ai/agentshield/approve-ai-agent-actions): Approve AI agent actions before they execute. agent·shield holds risky requests in a queue so you can read the request and the matched policy first.
- [Your AI agent can delete production data. Here's how to make that safe.](https://ogbuilds.ai/agentshield/ai-agent-that-can-delete-production-data): An AI agent with write access can delete production data on one bad inference. agent·shield holds DELETEs, drop-table and kubectl delete for approval.
- [AI agent firewall: the category, what it controls, and how agent·shield does it](https://ogbuilds.ai/agentshield/ai-agent-firewall): An AI agent firewall sits between an agent and the systems it calls, inspecting every request and holding destructive ones. What to expect, with agent·shield.
- [MCP server security: put a gate in front of the tools your agent can call](https://ogbuilds.ai/agentshield/mcp-server-security-proxy): MCP servers give agents real tool access, destructive ones included. agent·shield proxies the traffic and holds dangerous tool calls for human approval.
- [AI agent audit log: a defensible record of every action the agent took](https://ogbuilds.ai/agentshield/ai-agent-audit-log): An AI agent audit log should record every action, not just chat. agent·shield logs every request (forwarded, blocked, held, approved, denied) append-only.
- [Securing your AI agent vs shipping it unguarded: the real trade-off](https://ogbuilds.ai/agentshield/ai-agent-security-vs-doing-nothing): The realistic comparison for most AI agents is a security gate vs nothing, not tool A vs tool B. What 'nothing' costs, and what agent·shield adds.
- [Stop destructive agent SQL: hold DROP, TRUNCATE and WHERE-less updates](https://ogbuilds.ai/agentshield/ai-agent-database-security-proxy): Stop an AI agent running destructive SQL. Route its database traffic through agent·shield to hold DROP TABLE, TRUNCATE and WHERE-less updates for approval.
- [Vibe coding security risks: why AI-built apps ship the same six problems](https://ogbuilds.ai/qualityvibes/vibe-coding-security-risks): Vibe coding security risks follow a pattern: committed secrets, string-built SQL, debug mode left on. How quality·vibes catches what AI tools ship.
- [The pre-launch security checklist for vibe-coded apps](https://ogbuilds.ai/qualityvibes/security-checklist-vibe-coded-apps): Security checklist for vibe-coded apps: secrets out of the repo, SQL parameterised, debug off, .env ignored. Or scan it all at once with quality·vibes.
- [How to check a GitHub repo for security issues (by hand, and in one paste)](https://ogbuilds.ai/qualityvibes/check-github-repo-for-security-issues): Check a GitHub repo for security issues two ways: grep keys and eyeball SQL by hand, or paste the link into quality·vibes for a scored report in a minute.
- [You committed an API key to GitHub. Here's the order of operations.](https://ogbuilds.ai/qualityvibes/exposed-api-keys-github): Exposed API keys on GitHub live on in git history after deletion. Rotate the credential, purge with git filter-repo, then prevent repeats with quality·vibes.
- [AI-code security scanner: what the category is for, and what to expect from one](https://ogbuilds.ai/qualityvibes/ai-code-security-scanner): An AI code security scanner should check the mistakes AI tools actually make, point at exact lines, and hand back fixes. How quality·vibes approaches it.
- [quality·vibes vs Snyk and enterprise SAST: different tools for different builders](https://ogbuilds.ai/qualityvibes/snyk-alternative-for-vibe-coders): Snyk alternative for vibe coders: quality·vibes does fast heuristic repo scans with paste-ready AI fix prompts. How it compares with enterprise SAST/SCA.
- [SQL injection in AI-generated code: the string-built query problem](https://ogbuilds.ai/qualityvibes/sql-injection-ai-generated-code): SQL injection in AI-generated code: f-strings and template literals build injectable queries. The parameterised fix, and how quality·vibes flags it.
- [Your codebase's security score, explained: the exact math behind quality·vibes's 0–100](https://ogbuilds.ai/qualityvibes/security-score-for-your-codebase): Security score for your codebase: quality·vibes grades repos 0–100 from six weighted categories. The exact math, weights, and grade bands, no black box.
- [How to fix security findings with Claude Code: what a good fix prompt contains](https://ogbuilds.ai/qualityvibes/claude-prompts-to-fix-security-issues): Claude prompts to fix security issues should state the issue, file, line, and exact change. The anatomy, and how quality·vibes writes one per finding.
- [The state of vibe-coded security: we scanned 549 self-described AI-built repos](https://ogbuilds.ai/qualityvibes/state-of-vibe-coded-security): State of vibe-coded security: quality·vibes scanned 549 AI/vibe-coded GitHub repos. 20.4% had exposed secrets, 26.8% a critical or high finding.
- [The 6 most common security findings in vibe-coded apps, measured rather than guessed](https://ogbuilds.ai/qualityvibes/most-common-security-findings-vibe-coded-apps): Most common security findings in vibe-coded apps: dangerouslySetInnerHTML, .env not ignored, wildcard CORS. The fixes, from a quality·vibes scan of 549 repos.
- [How we security-benchmarked 549 vibe-coded repos: corpus, engine, caps, and caveats](https://ogbuilds.ai/qualityvibes/how-we-security-benchmarked-vibe-coded-repos): How we security-benchmarked 549 public GitHub repos: scanned in memory by the quality·vibes rules engine, AI pass off. Every choice and limitation.
- [Claude Code security: the tool, the code it writes, and how to harden both](https://ogbuilds.ai/qualityvibes/claude-code-security): Claude Code security is two problems: running the agent safely (permissions, secrets, prompt injection) and the code it ships. How to harden both.
- [Is Lovable safe? Judge the app it generated, not the builder](https://ogbuilds.ai/qualityvibes/is-lovable-safe): Lovable itself is reasonably secure. The apps it generates have a history of exposed data: missing row-level security, keys in the frontend. What to check.
- [Supabase row-level security: why AI skips it, how to find it, how to fix it](https://ogbuilds.ai/qualityvibes/supabase-row-level-security-missing): Missing row-level security is the most common vulnerability in vibe-coded Supabase apps: one user can read another's rows. How to check every table and fix it.
- [Is Bolt.new safe? The tool is fine. The app it generates needs a check](https://ogbuilds.ai/qualityvibes/is-bolt-safe): Bolt.new is safe to use. The apps it generates share the vibe-coded patterns: keys in the frontend, missing authorisation, no row-level security. What to check.
- [Vibe coding cleanup specialist: what the work is, and where it starts](https://ogbuilds.ai/qualityvibes/vibe-coding-cleanup-specialist): Cleaning up an AI-built app starts with triage, not refactoring. What a vibe coding cleanup job involves, and how to scope one before quoting or hiring.
- [AI code review tools: what they check, and the gap they leave](https://ogbuilds.ai/qualityvibes/ai-code-review-tools): AI code review tools read your pull requests for logic and style. They mostly don't audit a whole repo for committed secrets. Where each fits, honestly.
- [AI code review overhead is the new review tax. Here's where it goes, and how to cut it](https://ogbuilds.ai/qualityvibes/reduce-ai-code-review-overhead): AI tools ship more code, so reviewers spend longer de-slopping verbose comments and pasted blocks. How a specialized AI reviewer cuts PR review time.
- [How to keep AI-generated code quality high: a practical workflow for teams shipping with agents](https://ogbuilds.ai/qualityvibes/managing-ai-generated-code-quality): Manage AI-generated code quality with a clear workflow: set standards, scope PRs small, flag slop on the diff, keep humans on judgment. A step-by-step guide.
- [quality·vibes vs linters and static analysis: different tools for the AI-slop problem](https://ogbuilds.ai/qualityvibes/qualityvibes-vs-linters): Linters catch syntax and rule violations; they pass AI slop that's syntactically perfect. How quality·vibes differs, and why you want both for AI-generated code.
- [Preventing architectural drift: keeping a codebase coherent when agents write most of it](https://ogbuilds.ai/qualityvibes/preventing-architectural-drift): AI agents optimize for the local change, not the system's shape, so architecture drifts PR by PR. How to catch structural deviations on the diff with quality·vibes.
- [Your codebase's cleanliness score, explained: how quality·vibes gets from findings to a number out of 100](https://ogbuilds.ai/qualityvibes/code-cleanliness-score): Code cleanliness score, explained: quality·vibes grades repos out of 100 from six weighted categories. The exact math, weights, and grade bands, no black box.
- [How to clean up vibe-coded apps: the tidy-up pass AI-built repos never get](https://ogbuilds.ai/qualityvibes/clean-up-ai-generated-code): Clean up AI-generated code in order: giant files, pasted blocks, commented-out leftovers, warring styles. The cleanup pass, and how quality·vibes runs it.
- [How to detect and delete dead code (commented-out blocks, TODO piles, debug leftovers)](https://ogbuilds.ai/qualityvibes/dead-code-detection): Dead code detection: find commented-out blocks, stale TODOs, and leftover console.logs in any repo, by hand or in one paste with quality·vibes.
- [How much code duplication is too much, and which copies actually matter](https://ogbuilds.ai/qualityvibes/code-duplication-how-much-is-too-much): Code duplication: how much is too much? A practical line between harmless copies and bugs you fix four times, and how quality·vibes detects and scores it.
- [Consistency in a codebase: filenames, indentation, and the phantom diffs they cause](https://ogbuilds.ai/qualityvibes/naming-consistency-guide): Naming consistency: mixed tabs, three filename conventions, two package managers add up to phantom diffs. What consistency buys, how quality·vibes scores it.
- [Repo hygiene checklist: README, .gitignore, lockfile, and the junk that shouldn't be in git](https://ogbuilds.ai/qualityvibes/repo-hygiene-checklist): Repo hygiene checklist: node_modules committed, no README, no lockfile, zero tests. The easiest fixes, in order, checked by quality·vibes in one paste.
- [Refactoring a messy repo with Claude Code: prompts that tidy without breaking](https://ogbuilds.ai/qualityvibes/claude-refactor-messy-repo): Claude refactor prompts for a messy repo should state the mess, file, line, and exact change. The anatomy, and how quality·vibes writes one per finding.
- [Code quality metrics that actually predict pain, and the vanity numbers to ignore](https://ogbuilds.ai/qualityvibes/code-quality-metrics-that-matter): Code quality metrics that matter: file size, nesting depth, duplication, and dead code predict pain. Which to ignore, and how quality·vibes scores the rest.
- [quality·vibes vs manual code review: what a scan catches, what only a human can](https://ogbuilds.ai/qualityvibes/cleanvibes-vs-manual-code-review): quality·vibes vs manual code review: a human catches design problems, a scanner checks every file every time. Honest comparison, since most get neither.
- [The state of vibe-coded code quality: we scanned 549 self-described AI-built repos](https://ogbuilds.ai/qualityvibes/state-of-vibe-coded-code-quality): State of vibe-coded code quality: quality·vibes scanned 549 AI/vibe-coded GitHub repos. 55.6% had duplication, 63.2% dead code, 71 graded F. Honest numbers.
- [The most common mess in AI-generated code, counted across 549 repos](https://ogbuilds.ai/qualityvibes/most-common-mess-ai-generated-code): Most common mess in AI-generated code: commented-out code (59.2%), deep nesting, large files, duplication. From a quality·vibes scan of 549 repos, with fixes.
- [How we benchmarked 549 vibe-coded repos for code quality: corpus, engine, caps, and caveats](https://ogbuilds.ai/qualityvibes/how-we-benchmarked-vibe-coded-repos): How we benchmarked 549 vibe-coded repos: public GitHub projects scanned in memory by the quality·vibes rules engine, AI pass off. Every choice and limitation.
- [Code quality checker: score a whole repo from its GitHub link](https://ogbuilds.ai/qualityvibes/code-quality-checker): A code quality checker scores maintainability, not whether code runs. quality·vibes grades a GitHub repo out of 100 across six categories and names the messy files.
- [Code smells: the common ones, with examples and how to catch them](https://ogbuilds.ai/qualityvibes/code-smells): Duplication, long files, dead code, deep nesting: the code smells that make a repo hard to maintain, with examples and how to find them across a whole codebase.
- [Spaghetti code: what it is, why it happens, and how to untangle a repo](https://ogbuilds.ai/qualityvibes/spaghetti-code): Tangled code where everything depends on everything. What causes spaghetti code, why AI tools produce it, and how to measure and untangle a repo.
- [what is contextual feedback and why your team needs it](https://ogbuilds.ai/spotlight/what-is-contextual-feedback): contextual feedback is feedback attached to the exact element it's about. learn what it is, why it beats screenshots, and how it speeds up your team.
- [how to give precise ui feedback without screenshots](https://ogbuilds.ai/spotlight/ui-feedback-without-screenshots): stop pasting screenshots into docs. learn how to comment directly on website elements so your ui feedback is precise, current, and easy to act on.
- [browser extensions for web ui commenting: a comparison](https://ogbuilds.ai/spotlight/browser-extensions-for-web-commenting): comparing browser extensions for commenting on live web pages: what to look for in web annotation tools and which approach actually saves your team time.
- [streamlining qa: faster bug reporting with direct ui comments](https://ogbuilds.ai/spotlight/faster-qa-bug-reporting): speed up qa bug reporting by commenting directly on the broken element. capture the selector and url automatically so developers can reproduce issues fast.
- [design review made easy: commenting directly on live prototypes](https://ogbuilds.ai/spotlight/design-review-on-live-prototypes): run design reviews by commenting directly on live prototypes in the browser. capture the element and url so feedback is precise and easy to act on.
- [product managers: get clear stakeholder feedback on features](https://ogbuilds.ai/spotlight/stakeholder-feedback-for-pms): product managers can get clear, specific stakeholder feedback by having reviewers comment directly on the feature in the browser instead of in long email threads.
- [how to share specific web ui feedback links with your team](https://ogbuilds.ai/spotlight/share-web-ui-feedback-links): learn how to share feedback links that point to a specific element on a live page, so teammates land exactly where the comment is instead of hunting for it.
- [the hidden cost of unclear web ui feedback (and how to fix it)](https://ogbuilds.ai/spotlight/hidden-cost-of-unclear-feedback): unclear web ui feedback quietly drains hours through rework and back-and-forth. learn where the cost hides and how contextual comments fix it.
- [spotlight vs. traditional annotation tools: what's the difference?](https://ogbuilds.ai/spotlight/spotlight-vs-traditional-annotation): what's the difference between spotlight and traditional annotation tools? contextual feedback anchors comments to live elements; annotation freezes pixels.
- [how to monitor docker container cpu usage in real-time, minus the open-source overhead](https://ogbuilds.ai/gromitor/monitor-docker-cpu-usage-real-time): learn how to monitor docker container cpu usage in real-time without deploying Prometheus or Grafana yourself. gromitor gives you live metrics in minutes.
- [kubernetes resource utilization monitoring for devops teams: a saas alternative](https://ogbuilds.ai/gromitor/kubernetes-resource-monitoring-saas): skip the Prometheus+Grafana setup. gromitor gives devops teams live kubernetes pod cpu, memory, and i/o metrics in one dashboard. no infrastructure to operate.
- [agent-based container monitoring vs. manual open-source tools](https://ogbuilds.ai/gromitor/agent-based-vs-open-source-container-monitoring): compare agent-based container monitoring (like gromitor) vs. self-hosted Prometheus, Grafana, and cadvisor. understand the real trade-offs before you choose.
- [simplifying container memory alerts across multiple cloud environments](https://ogbuilds.ai/gromitor/container-memory-alerts-multi-cloud): container memory alerts across AWS, GCP, and Azure are painful without one view. gromitor gives you a single dashboard and threshold alerts across all three.
- [getting started with real-time docker container metrics for developers](https://ogbuilds.ai/gromitor/real-time-docker-container-metrics-for-developers): what to track in real-time docker container metrics, what the numbers actually mean, and how to get live visibility without running a monitoring stack.
- [the benefits of lightweight agents for container performance monitoring](https://ogbuilds.ai/gromitor/lightweight-agents-container-performance-monitoring): lightweight monitoring agents add under 2% host CPU and collect live docker and kubernetes metrics, with no storage or infrastructure to operate.
- [understanding network i/o for kubernetes pods: a simple guide](https://ogbuilds.ai/gromitor/kubernetes-pod-network-io-guide): what rx/tx bytes mean in kubernetes pod network i/o, how to spot anomalies, and how gromitor shows live per-pod traffic without Prometheus.
- [why your devops team needs cross-platform container monitoring saas](https://ogbuilds.ai/gromitor/cross-platform-container-monitoring-saas): docker and kubernetes side by side in one dashboard. gromitor's cross-platform SaaS means you don't run a separate monitoring stack per runtime.
- [setting up cpu and memory alerts for containerized applications](https://ogbuilds.ai/gromitor/cpu-memory-alerts-containerized-applications): how to set cpu and memory alert thresholds for containerized apps that fire when they should and stay quiet when they shouldn't. no alertmanager config.
- [robot·guard gives you one place to whitelist the bots you want and block the ones you don't](https://ogbuilds.ai/robot.guard/product): robot·guard turns robots.txt into a control panel: whitelist Googlebot and crawlers that send traffic, block AI scrapers like GPTBot, preview and download.
- [What is robots.txt, and why it matters more than ever](https://ogbuilds.ai/robot.guard/what-is-robots-txt): What is robots.txt? A text file at your site root telling crawlers what they may visit. What it can't do, and why AI scrapers make robot·guard useful.
- [How to block specific AI bots from scraping your website](https://ogbuilds.ai/robot.guard/block-ai-bots): Block AI bots like GPTBot, ClaudeBot, CCBot and Google-Extended in robots.txt by user-agent, and let robot·guard keep the blocklist current for you.
- [The hidden cost of unwanted bot traffic, and how AI scrapers inflate it](https://ogbuilds.ai/robot.guard/cost-of-bot-traffic): Cost of bot traffic: bots are roughly half of traffic, and AI scrapers give nothing back. How that hits bandwidth and hosting, and how robot·guard cuts it.
- [robots.txt for SEO: how to whitelist Googlebot without locking out the rest](https://ogbuilds.ai/robot.guard/robots-txt-for-seo): robots.txt for SEO: keep Googlebot, Bingbot and key crawlers reaching what they should while blocking costly bots. robot·guard scopes every rule right.
- [robots.txt vs firewall: choosing the right bot protection](https://ogbuilds.ai/robot.guard/robots-txt-vs-firewall): robots.txt vs firewall: one asks compliant bots to stay out; one blocks any request. Most sites need both, and robot·guard handles the robots.txt half.
- [A developer's guide to robots.txt rules that don't bite you later](https://ogbuilds.ai/robot.guard/developer-guide-robots-txt): A developer's guide to robots.txt rules: user-agent matching, Allow vs Disallow precedence, wildcards, and the gotchas. robot·guard keeps the file valid.
- [How to generate an intelligent robots.txt for the modern web](https://ogbuilds.ai/robot.guard/generate-robots-txt): Generate a robots.txt that welcomes the search and social crawlers you want and blocks AI scrapers. robot·guard builds it from toggles, with no hand-writing.
- [How to protect your content from AI training with robots.txt](https://ogbuilds.ai/robot.guard/block-ai-training): Block AI training crawlers. GPTBot, CCBot, Google-Extended and more honour a robots.txt opt-out. robot·guard keeps your work out while you stay in search.
- [Small business website security: robots.txt strategies that actually help](https://ogbuilds.ai/robot.guard/small-business-robots-txt): Small business robots.txt strategies: what to allow, what to block, and the mistakes to avoid. robot·guard makes it five minutes, no security team needed.
- [How to block GPTBot in robots.txt](https://ogbuilds.ai/robot.guard/block-gptbot): Block GPTBot, OpenAI's training crawler, with two lines in robots.txt. The exact rule, GPTBot vs OAI-SearchBot, and how robot·guard keeps search intact.
- [How to block ClaudeBot and anthropic-ai](https://ogbuilds.ai/robot.guard/block-claudebot): Block ClaudeBot and anthropic-ai, Anthropic's crawlers, in robots.txt. robot·guard covers both user-agents, and your search ranking is untouched.
- [How to block CCBot (Common Crawl)](https://ogbuilds.ai/robot.guard/block-ccbot-common-crawl): Block CCBot, the Common Crawl bot, with two lines in robots.txt. Learn why blocking one crawler cuts off the dataset that trains many downstream AI models.
- [What is Google-Extended (and should you block it)?](https://ogbuilds.ai/robot.guard/what-is-google-extended): Google-Extended is Google's separate AI-training token. Block it in robot·guard to opt out of Gemini and Vertex AI training while keeping Search ranking.
- [Do AI bots actually respect robots.txt?](https://ogbuilds.ai/robot.guard/do-ai-bots-respect-robots-txt): Do AI bots respect robots.txt? Mostly. The major identifiable crawlers honour it, though some ignore it. robot·guard handles the compliant majority, not a wall.
- [The AI crawler user-agents to know in 2026](https://ogbuilds.ai/robot.guard/ai-crawler-user-agents-list): AI crawler user-agents to know in 2026, grouped by operator with what each does, plus why robot·guard's maintained block list beats a static copy-paste.
- [How to edit robots.txt in WordPress](https://ogbuilds.ai/robot.guard/robots-txt-wordpress): Robots.txt in WordPress is virtual: no physical file exists. How to override it and add a robot·guard set that allows search and blocks AI bots.
- [Robots.txt on Shopify: what you can and can't change](https://ogbuilds.ai/robot.guard/robots-txt-shopify): Robots.txt on Shopify is auto-generated, but robots.txt.liquid lets you add rules like robot·guard's AI-scraper blocks. What you can change and the limits.
- [robots.txt vs noindex: which one keeps a page out of Google?](https://ogbuilds.ai/robot.guard/robots-txt-vs-noindex): robots.txt controls crawling, noindex controls indexing. Learn why blocking a page in robots.txt can leave a bare URL in Google, and which to use when.
- [robots.txt vs llms.txt: do you need both?](https://ogbuilds.ai/robot.guard/robots-txt-vs-llms-txt): robots.txt vs llms.txt: one blocks crawlers you don't want, one helps AI engines understand your site. How they differ, and where robot·guard fits in.
- [AI email assistant, explained: what it does, what it shouldn't, and how to choose](https://ogbuilds.ai/echo/ai-email-assistant): An AI email assistant helps you handle email faster. The ones worth trusting learn your own voice and never send without you. Here's where echo fits.
- [echo vs Superhuman: two different bets on what makes email faster](https://ogbuilds.ai/echo/superhuman-alternative): Superhuman alternative? Superhuman speeds up moving through email; echo speeds up the writing, drafting replies in your voice on your existing Gmail.
- [ChatGPT for email replies: where it helps, and where echo is less work](https://ogbuilds.ai/echo/chatgpt-for-email): ChatGPT for email means re-explaining your tone and copy-pasting every reply. echo learns your voice once from your sent mail and drafts in your inbox.
- [How echo writes email replies that actually sound like you](https://ogbuilds.ai/echo/email-that-sounds-like-you): Email that sounds like you, not a robot: echo learns your tone, phrasings and sign-offs from your own sent mail, so drafts read like your writing.
- [Founder email, handled: faster replies in your voice without hiring an EA](https://ogbuilds.ai/echo/email-management-for-founders): Email management for founders: echo drafts investor, customer and candidate replies in your voice so you clear the queue without hiring an EA.
- [Manage high-volume email with drafts in your voice, not copy-paste templates](https://ogbuilds.ai/echo/manage-high-volume-email): Manage high-volume email without sounding canned: echo drafts each reply in your voice, so volume doesn't cost you your tone or force templates.
- [Generate Gmail replies in your own voice with echo](https://ogbuilds.ai/echo/gmail-ai-reply-generator): Gmail AI reply generator: echo connects to your Gmail, learns your voice from your sent mail, and generates replies you review and send from Gmail.
- [How to get AI to write email in your style (without re-prompting it every time)](https://ogbuilds.ai/echo/how-to-train-ai-on-your-writing-style): How to train AI on your writing style: feed it samples and rate output, or let echo learn it automatically from your sent mail. Here's how it works.
- [Why echo only drafts: review every AI email reply before it sends](https://ogbuilds.ai/echo/ai-email-drafts-you-review-before-sending): AI email drafts you review before sending: echo only ever drafts. Every reply opens for you to edit and approve, and sends only when you tap send.
- [How to reply to emails faster without sacrificing quality](https://ogbuilds.ai/echo/how-to-reply-to-emails-faster): Practical systems for cutting email reply time in half: inbox triage, AI drafting, keyboard habits, and when to use each so your replies stay high-quality.
- [AI email tone matching, explained](https://ogbuilds.ai/echo/ai-email-tone-matching-explained): How AI email assistants match your tone and style: style profiles, context signals, knowledge bases, and the privacy considerations to understand before connecting your inbox.
- [AI email assistant for freelancers: proposals, follow-ups, and client comms](https://ogbuilds.ai/echo/ai-email-assistant-for-freelancers): How freelancers use AI email assistants to write faster proposals, follow up consistently, and manage client communications without spending hours on email every week.
- [Reaching inbox zero with AI: a practical workflow](https://ogbuilds.ai/echo/reaching-inbox-zero-with-ai): How to combine AI email drafting, triage rules, and a knowledge base to reach and maintain inbox zero, without spending hours on email every day.
- [AI email assistant vs. templates vs. Smart Reply: an honest comparison](https://ogbuilds.ai/echo/ai-email-assistant-vs-templates-and-smart-reply): A fair comparison of AI style-learning email assistants, canned templates, and Gmail Smart Reply/Smart Compose: tradeoffs, best use cases, and which to use when.
- [accent·ai vs Duolingo: conversation practice instead of vocab drills](https://ogbuilds.ai/accentai/duolingo-alternative): Duolingo alternative for speaking: Duolingo builds vocabulary with drills; accent·ai is built for actually speaking. How they compare and which fits you.
- [AI vs human English tutor: cost, availability, and when a person still wins](https://ogbuilds.ai/accentai/ai-vs-human-language-tutor): AI vs human language tutor: a human gives judgment and accountability; accent·ai gives unlimited, judgment-free speaking practice on demand, for free.
- [How to practise speaking English by yourself (no partner needed)](https://ogbuilds.ai/accentai/practice-speaking-english-alone): Practice speaking English alone: a practical routine from self-talk to AI role-play with instant feedback in accent·ai. No conversation partner needed.
- [How to improve English fluency: conversation reps and feedback loops](https://ogbuilds.ai/accentai/improve-english-fluency): Improve English fluency by speaking, not more grammar study: short daily conversation reps and spoken role-play in accent·ai that corrects you as you go.
- [Practise your English job interview out loud with an AI interviewer](https://ogbuilds.ai/accentai/practice-english-job-interview): Practice an English job interview out loud: accent·ai role-plays the interview and corrects and rephrases your answers more naturally, turn by turn.
- [Practise ordering food in English before you're at the counter](https://ogbuilds.ai/accentai/practice-ordering-food-english): Practice ordering food in English: accent·ai's cafe and restaurant role-play lets you speak the whole exchange aloud and corrects your phrasing each turn.
- [Practise travel English out loud before your trip, with feedback](https://ogbuilds.ai/accentai/practice-travel-english): Practice travel English out loud: check-ins, hotels, directions. accent·ai's travel role-play lets you rehearse the exchanges and corrects your phrasing.
- [How to overcome speaking anxiety in English (and finally talk)](https://ogbuilds.ai/accentai/overcome-fear-of-speaking-english): Overcome fear of speaking English: why it happens and a practical way through it, using judgment-free AI role-play in accent·ai to build confidence first.
- [Free English conversation practice: the real options compared](https://ogbuilds.ai/accentai/free-english-conversation-practice): Free English conversation practice: how the free options compare, from exchanges to tutor minutes, plus on-demand AI role-play in accent·ai with no partner needed.
- [Commission reconciliation, explained (and how to automate it)](https://ogbuilds.ai/reportr/commission-reconciliation): Commission reconciliation means checking what carriers paid against what your agency was owed. Why payments go short, and how reportr matches every line.
- [Choosing insurance commission reconciliation software when your data is stuck in carrier portals](https://ogbuilds.ai/reportr/insurance-commission-reconciliation-software): Insurance commission reconciliation software must reach carrier portals with no APIs. What it actually needs to do, and how reportr closes that gap.
- [How to reconcile carrier commission statements against your book of business](https://ogbuilds.ai/reportr/how-to-reconcile-carrier-commission-statements): How to reconcile carrier commission statements each month: capture each portal, load your roster, and let reportr match expected vs paid and flag the gaps.
- [How to find the commissions your carriers never paid you](https://ogbuilds.ai/reportr/find-unpaid-commissions): Find unpaid and short-paid commissions: compare what you're owed against what carriers actually paid, line by line. reportr builds the dispute list.
- [AgencyAnalytics alternative: reporting for data that lives behind a portal with no API](https://ogbuilds.ai/reportr/agencyanalytics-alternative): AgencyAnalytics alternative for sources with no API: reportr reads the carrier portal you're already logged into and builds the branded report anyway.
- [Whatagraph alternative: reporting when your source has no API to connect to](https://ogbuilds.ai/reportr/whatagraph-alternative): Whatagraph alternative for data behind a login with no usable API: reportr reads the portal you're already logged into and builds a branded report.
- [Put your own brand on client reports, built from the actual numbers](https://ogbuilds.ai/reportr/white-label-client-reports): reportr generates white-label PDF reports with your logo, brand colors, and footer, built from live source data. Paid plans remove the reportr mark.
- [Client reports from sources that have no API](https://ogbuilds.ai/reportr/client-reports-without-an-api): Client reports without an API: reportr builds them client-side, from the portal session you're already in, covering sources API-based reporting tools can't reach.
- [Reporting software for insurance agencies](https://ogbuilds.ai/reportr/insurance-agency-reporting-software): Insurance agency reporting software for numbers stuck behind carrier portals: reportr reconciles commission with no API needed and outputs branded reports.
- [Commission statement errors: the six types, and how to catch every one](https://ogbuilds.ai/reportr/commission-statement-errors): Short-pays, missed renewals, wrong splits, chargeback surprises. The commission statement errors carriers make, why they go unnoticed, and how to catch them.
- [Insurance commission chargebacks: what triggers them, and how to see them coming](https://ogbuilds.ai/reportr/insurance-commission-chargebacks): Insurance commission chargebacks claw back pay when a policy lapses, cancels, or NSFs. What triggers them, how they hit your statement, and how to track them.
- [Commission calculator: estimate what your book of business should earn](https://ogbuilds.ai/reportr/commission-calculator): Free insurance commission calculator. Enter premium, rate and policy count for expected commission, advance and chargeback exposure, then check what was paid.
- [What Medicare Advantage plans file for agent pay, 2018 to 2026](https://ogbuilds.ai/reportr/medicare-agent-commission-rates): We read 40,657 CMS compensation filings across nine years. 99.6% of Medicare Advantage plans post the maximum, 95.6% post a floor of $0, and renewal is filed at half.
- [Constrained decoding vs fine-tuning: the right way to get valid DSL out of an LLM](https://ogbuilds.ai/dslai/constrained-decoding-vs-fine-tuning): Constrained decoding vs fine-tuning: dsl·ai makes invalid DSL impossible by constraining the grammar, which beats fine-tuning on cost, speed and correctness.
- [How to make an LLM output valid DSL every time (without fine-tuning)](https://ogbuilds.ai/dslai/llm-output-valid-dsl): Valid DSL from an LLM is a grammar problem, not a prompting problem. dsl·ai turns your grammar into a decoding constraint and a deterministic validator.
- [Validate your DSL in CI: reject malformed config in a pull request](https://ogbuilds.ai/dslai/validate-dsl-in-ci): Validate DSL in CI: dsl·ai generates a deterministic validator from your grammar, so invalid DSL fails the pull request with a precise, reproducible error.
- [Fine-tuning an LLM on your DSL: when it's worth it, and when it isn't](https://ogbuilds.ai/dslai/fine-tune-llm-on-dsl): Fine-tune an LLM on your DSL? Usually the wrong first move. Here's when fine-tuning helps, and the cheaper wedge (dsl·ai) to try before it.
- [Structured LLM output for your own language, guaranteed rather than hoped for](https://ogbuilds.ai/dslai/structured-llm-output-custom-language): Structured LLM output for a custom language: dsl·ai constrains generation to your grammar, so it's valid by construction and deterministically validated.
- [JSON schema vs grammar-constrained decoding: when JSON mode isn't enough for your language](https://ogbuilds.ai/dslai/json-schema-vs-grammar-constrained-output): JSON schema vs grammar-constrained output: schemas stop at JSON shapes; a full grammar covers any language. Where dsl·ai's grammar constraints take over.
- [Stop LLM syntax errors: make broken code and DSL impossible by construction](https://ogbuilds.ai/dslai/stop-llm-syntax-errors): Stop LLM syntax errors: dsl·ai compiles your grammar into a decoding constraint, so the model can't emit a token that breaks the language.
- [Generate a parser from your grammar: valid or invalid, with the exact position it broke](https://ogbuilds.ai/dslai/generate-a-parser-from-your-grammar): Generate a parser from your grammar: dsl·ai builds a deterministic validator that says valid or invalid, where it broke, and what it expected there.
- [Grammar-constrained decoding, explained: why the output is valid by construction](https://ogbuilds.ai/dslai/grammar-constrained-decoding-explained): Grammar-constrained decoding, explained: dsl·ai masks the LLM's token choices against your grammar at every step, so output is valid by construction.
- [The machine learning roadmap that actually links the resources, in order](https://ogbuilds.ai/pathai/machine-learning-roadmap): Machine learning roadmap as an ordered path: path·ai links the best free resource and runnable code to every step. Free, no account.
- [How to learn machine learning for free, in the right order, with code at every step](https://ogbuilds.ai/pathai/how-to-learn-machine-learning): How to learn machine learning without a paid course: follow an order and build with code. path·ai's free ordered paths give you both, step by step.
- [What order should you learn machine learning in?](https://ogbuilds.ai/pathai/what-order-to-learn-machine-learning): What order to learn machine learning: Python and math, classic ML, deep learning, then a specialisation, plus how path·ai encodes that sequence for you.
- [How to learn LLMs and transformers without skipping the foundations](https://ogbuilds.ai/pathai/how-to-learn-llms): How to learn LLMs: path·ai orders the path through tokens, embeddings, attention, transformers, and fine-tuning, with a resource and code at each step.
- [Learn AI for free on an ordered path, with no account and no paywall](https://ogbuilds.ai/pathai/learn-ai-for-free): Learn AI for free: the best resources already cost nothing. path·ai orders them into a free, no-account path with runnable code and checkpoints.
- [path·ai vs roadmap.sh: a topic graph or an ordered, resource-linked path?](https://ogbuilds.ai/pathai/vs-roadmap-sh): path·ai vs roadmap.sh: roadmap.sh maps what to learn; path·ai turns each node into an ordered module with a resource, runnable code, and a checkpoint.
- [don't let life derail your ai/ml learning: stay consistent with curated paths](https://ogbuilds.ai/pathai/stay-consistent-ai-learning): stay consistent learning AI/ML: how path·ai helps you overcome learning fatigue, pick up where you left off, and build lasting consistency.
- [the biggest ai career mistake in 2026: learning llms without ml fundamentals](https://ogbuilds.ai/pathai/llm-fundamentals-vs-frameworks): LLM fundamentals vs frameworks: don't jump straight to frameworks. path·ai guides you through the ML fundamentals real-world AI engineering is built on.
- [stop 'learning ai' and start 'building ai': your path to practical projects](https://ogbuilds.ai/pathai/from-ai-learner-to-builder): from AI learner to builder: path·ai helps you escape tutorial hell and move from passive study to building projects, with curated resources and code.
- [verif·ai vs paste-in AI detectors: check content where you read it](https://ogbuilds.ai/verifai/vs-online-ai-detectors): verif·ai vs online AI detectors: no paste box. The Chrome extension scans the page you're on, images and text together, and highlights likely AI content in place.
- [How to check if an image is AI-generated (without leaving the page)](https://ogbuilds.ai/verifai/how-to-detect-ai-images): How to detect AI images on any page: hit scan in verif·ai and it outlines likely AI-generated images with a confidence score out of 100, on-device.
- [How to tell if text was written by AI (on the page you're reading)](https://ogbuilds.ai/verifai/how-to-detect-ai-text): How to detect AI text on any page: hit scan in verif·ai and it tints likely AI-written passages with a confidence score out of 100, in place and on-device.
- [An AI content detector Chrome extension: scan the page, not a paste box](https://ogbuilds.ai/verifai/ai-content-detector-chrome-extension): AI content detector Chrome extension: verif·ai checks images and text on the page you're reading in one click, with a clear confidence score and no account.
- [Private AI detection: check images and text without an account or upload](https://ogbuilds.ai/verifai/private-ai-detection): Private AI detection: verif·ai runs on-device in your browser, with no account and no server-side history, so checking a page for AI content stays private.
- [Is this image AI-generated? How to check it on the page](https://ogbuilds.ai/verifai/is-this-image-ai-generated): Is this image AI-generated? Check without leaving the page: verif·ai scans your current tab and outlines likely AI images with a confidence score out of 100.
- [A free AI detector: no account, images and text, on demand](https://ogbuilds.ai/verifai/free-ai-detector): Free AI detector: verif·ai is a free Chrome extension that flags likely AI images and text on the page you're reading. No account, no sign-in, on-device.
- [How accurate are AI detectors, and how to read the score responsibly](https://ogbuilds.ai/verifai/how-accurate-are-ai-detectors): How accurate are AI detectors? What a confidence score really means, why false positives happen, and how to read verif·ai's levels without over-trusting.
- [Detect AI while you browse, in feeds and articles rather than a separate site](https://ogbuilds.ai/verifai/detect-ai-while-you-browse): Detect AI while you browse: verif·ai scans the page you're already on and flags likely AI images and text in place, on demand and on-device.
- [What is an AI content detector?](https://ogbuilds.ai/verifai/what-is-an-ai-content-detector): An AI content detector estimates whether text or an image was generated by AI. Here's how detectors work, what they can and can't do, and where verif·ai fits.
- [What is AI-generated content?](https://ogbuilds.ai/verifai/what-is-ai-generated-content): AI-generated content is text, images, audio or video produced by generative AI. Here's what it is, why it's flooding the web, and how to identify it.
- [Midjourney image detector](https://ogbuilds.ai/verifai/midjourney-image-detector): Spot Midjourney-generated images on any web page: the tells that give Midjourney away, and a free one-click browser check with verif·ai.
- [DALL·E image detector](https://ogbuilds.ai/verifai/dalle-image-detector): Detect DALL·E-generated images on any page: how OpenAI's C2PA content credentials help, the visual tells, and a free one-click check with verif·ai.
- [Stable Diffusion image detector](https://ogbuilds.ai/verifai/stable-diffusion-image-detector): Spot Stable Diffusion images and their many fine-tuned variants on any page: the tells, why open-source models vary, and a free one-click check with verif·ai.
- [ChatGPT text detector](https://ogbuilds.ai/verifai/chatgpt-text-detector): Spot ChatGPT-written text on any page: the phrasing and rhythm that give GPT-4 away, the limits of detection, and a free one-click check with verif·ai.
- [A free GPTZero alternative for your browser](https://ogbuilds.ai/verifai/gptzero-alternative): verif·ai is a free, in-browser alternative to GPTZero: scan any page for AI images and text in one click, on-device, no account. How the two differ and when to use each.
- [A free Originality.ai alternative for browsing](https://ogbuilds.ai/verifai/originality-ai-alternative): verif·ai is a free, private, in-browser alternative to Originality.ai: scan any page for AI content on-device with no account. How they compare and when to use each.
- [Looking for a Giphy alternative? Edit the GIF instead of settling for the closest match](https://ogbuilds.ai/gifai/giphy-alternative): Giphy and Tenor are libraries of GIFs other people made. gif·ai is a Chrome extension that edits any GIF from a prompt: caption, vibe, detail.
- [How to edit a GIF with a prompt (no timeline, no frame-by-frame)](https://ogbuilds.ai/gifai/how-to-edit-a-gif): Editing a GIF used to mean frame-by-frame work in a heavy editor. Paste one into the gif·ai Chrome extension, describe the change, and it re-renders.
- [How to add text to a GIF without it jittering across frames](https://ogbuilds.ai/gifai/add-text-to-gif): Most caption tools stick text on top of a GIF and it jitters or drifts. gif·ai re-renders the text into every frame, so your caption stays put. Here's how.
- [Custom Discord GIFs: edit a reaction nobody else in the server has](https://ogbuilds.ai/gifai/discord-gifs): Everyone pastes the same Discord GIFs. gif·ai edits any GIF from a prompt. Add the server in-joke, the right caption, or a restyle, so your reactions are yours.
- [Reaction GIF maker: get the exact reaction instead of the closest one](https://ogbuilds.ai/gifai/reaction-gif-maker): A reaction GIF is only good if it's the right reaction. gif·ai edits any GIF from a prompt: caption, context, vibe. Send the one you actually meant.
- [Looking for an ezgif alternative? Edit the GIF from a prompt instead of hand-tooling it](https://ogbuilds.ai/gifai/ezgif-alternative): ezgif alternative for AI editing: gif·ai is a Chrome extension that edits a GIF from a plain-English prompt and re-renders it consistently across frames.
- [How to make a GIF smoother: interpolate a choppy clip into cleaner motion](https://ogbuilds.ai/gifai/make-a-gif-smoother): Make a GIF smoother with gif·ai's Smooth engine: it interpolates between existing frames to fill in choppy motion. No prompt needed, around 2 credits.
- [How to recolour a GIF: change the colour from a prompt across every frame](https://ogbuilds.ai/gifai/recolor-a-gif): Recolour a GIF with gif·ai: describe the colour and it re-renders the recolour consistently across every frame. Includes a recolor purple preset.
- [AI GIF generator vs editor: why editing an existing clip beats generating from scratch](https://ogbuilds.ai/gifai/ai-gif-generator-vs-editor): AI GIF generator vs editor: a generator builds motion from nothing; gif·ai edits a GIF you already have. For reactions and memes, real motion wins.
- [Branded GIFs for marketing: restyle a real clip into something on-brand](https://ogbuilds.ai/gifai/branded-gifs-for-marketing): Branded GIFs for marketing: gif·ai edits a real clip to your brand colours, adds a mascot or product, and re-renders it so it looks made, not stickered.
- [Remove Unwanted Objects from GIFs Using AI Prompts](https://ogbuilds.ai/gifai/remove-object-from-gif-ai): Remove objects from a GIF with AI: gif·ai erases people, logos or text from a prompt and re-renders a clean, flicker-free result across every frame.
- [Change or Replace Objects in a GIF with AI Prompts](https://ogbuilds.ai/gifai/change-object-in-gif-ai): Change objects in a GIF with AI: gif·ai recolours, restyles or replaces any element from a text prompt, re-rendered consistently across every frame.
- [How to remove text from a GIF that's baked into the frames](https://ogbuilds.ai/gifai/remove-text-from-a-gif): Baked-in captions can't be deleted with an overlay tool. gif·ai re-renders the GIF without the text and rebuilds what sat behind it, frame by frame.
- [How to put a filter on a GIF without it flickering](https://ogbuilds.ai/gifai/gif-filters): Photo filters flicker when run over a GIF frame by frame. gif·ai applies the look you describe across the whole clip, so the grade holds while it moves.
- [What is an AI GIF editor, and how is it different from a generator?](https://ogbuilds.ai/gifai/what-is-an-ai-gif-editor): What is an AI GIF editor? A tool that changes an existing GIF from a text prompt, re-rendering every frame consistently. gif·ai is one Chrome extension.
- [How to remove a watermark from a GIF with a prompt](https://ogbuilds.ai/gifai/remove-watermark-from-a-gif): Remove a watermark from a GIF without cropping: describe it and gif·ai re-renders the GIF to fill in behind it, consistently across every frame.
- [How to change the background of a GIF from a prompt](https://ogbuilds.ai/gifai/change-a-gif-background): Change a GIF background from a prompt: gif·ai keeps the subject and replaces what's behind it, re-rendered consistently across every frame. No masking.
- [Strava for TikTok: turn solo growth into a friendly competition](https://ogbuilds.ai/tokki/strava-for-tiktok): Strava made exercise social by letting you compete with friends. tokki does the same for TikTok: connect your account, compete privately with friends you invite, and earn collectible badges.
- [Turn TikTok into a private leaderboard with your friends](https://ogbuilds.ai/tokki/tiktok-leaderboard): A public follower count tells you nothing about how you're doing against the people you know. tokki turns TikTok into a private, friends-first leaderboard with collectible badges.
- [Compete with friends on TikTok: why friendly rivalry beats chasing strangers](https://ogbuilds.ai/tokki/compete-with-friends): Chasing influencers you'll never catch is demotivating. tokki lets you invite friends and turn TikTok growth into a friendly rivalry, with collectible badges and no ads.
- [How to keep growing on TikTok when the grind gets boring](https://ogbuilds.ai/tokki/how-to-grow-on-tiktok): Most TikTok growth fails at consistency, not strategy. Here's a simple approach to staying consistent, and how tokki turns the grind into a friends-first game so you actually keep going.
- [Track your TikTok posting streak and keep it alive](https://ogbuilds.ai/tokki/tiktok-posting-streak-tracker): TikTok posting streak tracker: tokki turns daily posting into a visible streak with a segmented bar, a daily reminder, and a badge at 7 days in a row.
- [Turn your friends into a TikTok accountability group](https://ogbuilds.ai/tokki/tiktok-accountability-group): TikTok accountability group: tokki gives you a private circle, a milestone feed, reactions, and a growth leaderboard. Real friends, not strangers.
- [Beat TikTok creator burnout by making the posting a game](https://ogbuilds.ai/tokki/tiktok-creator-burnout-solution): TikTok creator burnout? tokki turns growth into a friends-first game with challenges and collectible badges, so creating feels fun again, not a grind.
- [What is a TikTok growth game?](https://ogbuilds.ai/tokki/what-is-a-tiktok-growth-game): What is a TikTok growth game? It turns the slow grind of growing an account into friendly competition and rewards. tokki is a friends-first one.
- [Looking for an app to compete with friends? tokki makes TikTok growth the game](https://ogbuilds.ai/tokki/apps-to-compete-with-friends): Apps to compete with friends: tokki does it for TikTok growth. Invite friends, race to grow, with a private leaderboard and badges. No ads, 18+.
- [Want a social-media accountability app? Compete with friends to stay consistent](https://ogbuilds.ai/tokki/social-media-accountability-app): Social-media accountability app: tokki turns TikTok growth into a friends-first competition with badges, giving you social pressure to keep posting.
- [flingdows is a free Mac window manager, open source and built on physics](https://ogbuilds.ai/flingdows/free-mac-window-manager): Free Mac window manager: flingdows is free and MIT-licensed, and adds what paid snappers don't have. Throw a window and it flies with real momentum.
- [Throw a window and let physics carry it across the screen](https://ogbuilds.ai/flingdows/throw-windows-with-momentum): Throw windows with momentum on your Mac: flingdows lets you flick a window so it glides with inertia, slows under friction, and springs back from edges.
- [How to fling windows on a Mac with flingdows](https://ogbuilds.ai/flingdows/how-to-fling-windows-on-mac): How to fling windows on a Mac: install flingdows, grant Accessibility access, and release a drag with speed. The full setup, plus how to tune the feel.
- [Tune the fling: strength, friction, edge stiffness, and elasticity](https://ogbuilds.ai/flingdows/tune-window-fling-physics): Tune the window-fling physics in flingdows: four live sliders (fling strength, friction, edge stiffness, elasticity) dial in exactly the feel you want.
- [Why an open-source window manager matters on macOS](https://ogbuilds.ai/flingdows/open-source-window-manager-mac): Open-source Mac window manager: flingdows is MIT-licensed, so you can read exactly what it does with Accessibility access, build it, and fork it.
- [Fluid Mac Window Placement: Move Windows Intuitively, Beyond Clunky Snapping](https://ogbuilds.ai/flingdows/fluid-mac-window-placement-beyond-snapping): Fluid Mac window placement beyond clunky snapping: flingdows moves windows with real momentum, a natural, responsive alternative to buggy macOS tiling.
- [Dynamic Desktop: Break Free from Static Grids with Flingdows](https://ogbuilds.ai/flingdows/dynamic-desktop-mac-window-management): Escape rigid, grid-based window managers on Mac. Flingdows offers a dynamic, physics-driven approach for expressive and precise window arrangement.
- [flingdows vs Rectangle and Magnet: snapping windows vs throwing them](https://ogbuilds.ai/flingdows/rectangle-alternative): Rectangle alternative? Rectangle and Magnet snap Mac windows to fixed zones; flingdows throws them with momentum. Here's where each one wins.
- [One flick instead of a long drag: covering distance on a big Mac desktop](https://ogbuilds.ai/flingdows/move-mac-windows-without-the-mouse-drag): Move Mac windows without the long mouse drag: flingdows lets you flick a window once and momentum carries it across a large or multi-display desktop.

## More
- [about](https://ogbuilds.ai/about): og (O Grover), the founder behind ogbuilds and omniscia.
- [contact](mailto:olly@ogbuilds.ai)