Code Engine – PHP Snippets, AI Functions & Automation for WordPress vs Smart Local AI – Browser-Based Private AI Tools

Code Engine is a snippets manager that doesn’t stop at snippets. Yes, it runs your PHP and JavaScript exactly where and when you want: frontend, backend, on a schedule, or inside your content. But its real magic is what happens after you write a function: the same little piece of code instantly becomes a tool your AI chatbots can call, a step you can drag into a visual workflow, and an endpoint the outside world can trigger. One function, three superpowers. Most “code snippets” plugins stop at a textarea and a toggle. Code Engine treats your functions as first-class building blocks for the whole Meow Apps ecosystem, and for anything that can speak REST. Think out of the box, let your creativity flow, because the possibilities really are endless! ✨ For more, check the official website and come say hi on the Discord. Quick Intro Hello! ☀️ I built Code Engine because I was tired of pasting mystery snippets into functions.php and praying. I wanted a place where small bits of code are organized, safe, AI-assisted, and reusable everywhere. Here’s the idea. You write a function (or let the AI write it for you from a plain-English description). That function immediately shows up in three places: AI Engine: your chatbots and MCP clients (Claude, ChatGPT, Claude Code) can call it as a tool, with real arguments. Ask “how many orders shipped today?” and your chatbot runs your function to answer. Workflow Engine: your function appears in the step picker as its very own block. Drag it onto the canvas, wire it between an AI step and a Slack step, done. No glue code. REST / External tools: give it a secure endpoint and a token, then trigger it from Make.com, n8n, Zapier, a cron job, or a webhook. You never wrote an “integration.” You just wrote a function. Code Engine did the rest. 🤝 Core Modules 🧩 Snippets Manager Backend, Frontend, Persistent, Scheduled, Functions, and in-content (PHP/JS) snippets, all in one clean dashboard with tags, search, scope filters, and priorities. 🪄 AI-Assisted Coding Describe what you want in plain English and let AI Engine write the snippet: code, name, arguments, and scope included. Refine existing code or implement it straight from your comments. 🤖 Functions as AI Tools Every Function snippet becomes a function-calling tool and an MCP tool, so your AI Engine chatbots (and external AI agents) can actually do things on your site, not just talk. 🔀 Functions as Workflow Steps Workflow Engine surfaces each of your functions as its own draggable step. Your custom logic becomes a first-class citizen on the automation canvas. 🌐 External Access (REST) Expose any runnable snippet through a secured REST endpoint with a bearer token. Perfect for Make.com, n8n, webhooks, and scheduled external jobs. 🛡️ Safe Mode A snippet that throws a fatal error is automatically caught and disabled before it can take your site down. Code with confidence. ⏰ Scheduling Run a snippet daily at a chosen time via WP-Cron (reports, cleanups, syncs) without touching the server crontab. 🧱 Code Blocks & Shortcodes (Pro) Drop PHP or JS straight into a post or page with a Gutenberg block or the [code-engine] shortcode, with safety guards. 🧩 Snippets, the way they should be Code Engine organizes your code by scope, so each snippet runs exactly where it belongs: Persistent: runs everywhere (frontend and backend). Your everyday “add this to functions.php” code, but managed. Frontend: runs only on the public site. Backend: runs only in the admin. Function: a named, callable function with typed arguments and defaults. This is the reusable building block (see below). Scheduled: runs on a WP-Cron schedule, at the hour and minute you pick. Content (PHP / JS): runs inside a specific post or page, via a Gutenberg Code Block or the [code-engine] shortcode (Pro). Everything is searchable, taggable, sortable by priority, and importable/exportable. The CodeMirror editor gives you proper syntax highlighting and keyboard shortcuts (Cmd+S to save, Cmd+Enter to run). A nikic/php-parser pass validates your PHP before it ever runs. 🪄 Let AI write it for you Don’t feel like writing the boilerplate? Describe the snippet in plain language and Code Engine, powered by AI Engine, generates the whole thing: the code, a sensible name, a description, the right scope, and, for functions, the argument list with names, types, and defaults. Already have code? Ask the AI to modify it from a prompt, or write a few comments describing what you want and let it fill in the implementation. It’s pair programming, right inside your dashboard. ✨ The big idea: write once, use everywhere This is what makes Code Engine different. A Function snippet is not just code you call from other code. It’s a reusable capability that the rest of your stack can plug into. The moment you save it, the same function is available in three places at once: 1. As an AI tool, for chatbots and AI agents With AI Engine active, your functions are exposed through function calling and over MCP (Model Context Protocol). Your on-site chatbot can run them mid-conversation, and external AI agents (Claude, Claude Code, ChatGPT, OpenClaw) can call them too. Want a chatbot that checks stock, looks up a booking, or kicks off a process? Write the function; the chatbot gains the skill. 2. As a workflow step, for automation With Workflow Engine, every active function shows up in the Add-step picker as its own block, named after your snippet, with one input per argument. Drag it onto the canvas and wire it between other steps: an AI step that summarizes, your function that saves, a Social Engine step that posts. There’s also a generic “Execute snippet (by ID / by name)” step when you want to call one dynamically. You never write integration code; your function is the integration. 3. As a REST endpoint, for the outside world Give a snippet a custom endpoint name and a bearer token, and it’s instantly callable from anywhere: POST /wp-json/code-engine/v1/snippets-endpoint/your-endpoint Pass arguments as JSON in the body, secure it with a token, and trigger it from Make.com, n8n, Zapier, GitHub Actions, or a humble cron job. Automation without a middleware bill. 🛡️ Safe by default Running arbitrary code is powerful, so Code Engine takes safety seriously: Safe Mode catches fatal errors and auto-disables the offending snippet, so a typo never white-screens your site. REST whitelisting means global snippets only run on trusted REST routes by default, so you choose what to open up. Per-snippet tokens secure your external endpoints. Validation with a real PHP parser before code is saved. For developers who want fewer guardrails, there’s a “Bypass REST Security” option and filters (mwcode_rest_authorized, mwcode_rest_whitelist) to tailor exactly what’s allowed. Works beautifully with the Meow Apps family Code Engine is one engine in a connected set, each one useful alone, magical together: AI Engine: chatbots, content generation, and MCP. Turns your functions into AI tools. Workflow Engine: visual automation. Turns your functions into draggable steps. SEO Engine: smart, lightweight AI SEO. Social Engine: schedule and automate social posts. Why Code Engine? Reusable, not throwaway Other snippet plugins give you a place to paste code. Code Engine gives you a place to build capabilities that your AI, your workflows, and your external tools can all use. Native to WordPress Clean, fast, and built the WordPress way. No clunky external dashboards, no bloat. AI-native Write snippets with AI, expose them to AI. The whole loop lives in your wp-admin. Developer friendly REST API, MCP tools, function calling, scheduling, import/export, and plenty of filters to hook into. Cared for Part of the Meow Apps family, with regular updates and a real human behind it. 💕

Smart Local AI brings machine learning directly to the browser. Every ML model runs on-device in the visitor’s or editor’s browser using Transformers.js and WebGPU/WASM. No data is ever sent to external servers, no cloud API keys are needed, and there are zero recurring costs. Modules RelevantFlow — Semantic Content Recommendations Traditional related-posts plugins match by shared tags or categories. RelevantFlow uses a sentence-transformer model (all-MiniLM-L6-v2) to understand the meaning of your content and recommend posts that are genuinely related — even when they share no tags at all. Understands synonyms and concepts (e.g. “Salah” and “Islamic Prayer” match) Works with any content type — Posts, Pages, WooCommerce Products, or custom post types Displays a responsive card widget below your content Three layout templates: cards, list, and grid Custom placement via CSS selector or shortcode [atlas_ai_relevantflow] Theme customization with presets (Default, Light, Dark, Minimal) and custom colors Embedding index built in-browser by editors — zero server load Nightly cron flags new/updated content for re-indexing PersonaFlow — Personalized Content Recommendations PersonaFlow delivers personalized content recommendations based on visitor behavior — like Netflix for your WordPress site. It tracks 30 behavioral signals (scroll depth, reading time, click patterns, etc.) and computes a per-visitor taste vector to surface the most relevant content for each individual visitor. Personalized recommendations powered by real-time behavioral tracking 30 behavioral signals including scroll depth, reading time, and engagement patterns Per-visitor taste profile computed entirely in the browser — no server-side tracking WooCommerce integration for product recommendations Three layout templates: cards, list, and grid Custom placement via CSS selector or shortcode [atlas_ai_personaflow] Theme customization with presets and custom colors All tracking data stays on the visitor’s device — fully GDPR compliant Automatic taste decay ensures recommendations stay fresh and relevant AltGenius — Automatic Alt Text Generation Missing alt text hurts SEO rankings and violates ADA/WCAG accessibility guidelines. AltGenius generates descriptive alt text for every image in your media library — entirely in the browser. Two AI models: ViT-GPT2 (fast) and Florence-2 (detailed) Bulk Scan to audit and fix your entire media library at once Auto-generate on media upload Editor sidebar panel for per-image control with prefix/suffix No per-image fees, no cloud processing Key Features Zero Cost — No API keys, no subscriptions, no per-request fees Privacy by Architecture — All ML inference runs in the browser; data never leaves the device GDPR Compliant — No external data transmission means no DPA required Shared Hosting Compatible — No server-side ML dependencies; works anywhere WordPress runs WebGPU + WASM — Hardware-accelerated inference with automatic fallback Modular — Enable only the modules you need; each can work standalone Cached Models — ML models are cached in IndexedDB after first download for instant reuse Themeable — Built-in theme presets and custom color options to match any WordPress theme Upgrade to Pro Get more powerful AI modules and premium features with Smart Local AI Pro. Have questions or need support? Contact us. How It Works All AI processing runs in your browser. No server-side ML is required. On first use, models are downloaded from Hugging Face and cached in the browser’s IndexedDB — this one-time download may take 1–2 minutes depending on your connection. After that, models load instantly. RelevantFlow (Related Posts) Go to Smart Local AI > Dashboard and enable the RelevantFlow module (or follow the setup wizard after activation) Select which content type to index from the Content Type selector on the Dashboard (defaults to Posts) Go to the RelevantFlow tab and click Build Index — this downloads the MiniLM model (~23 MB) and generates an embedding for each published item of the selected content type You need at least 2 published items of the selected content type for recommendations to appear Visit any item on the frontend — a “You Might Also Enjoy” section will appear below the content showing semantically related items PersonaFlow (Personalized Recommendations) Go to Smart Local AI > Dashboard and enable the PersonaFlow module Go to the PersonaFlow tab to configure display settings (number of recommendations, layout template, appearance) Visit posts on the frontend — PersonaFlow will track reading behavior and build a taste profile After a few page views, personalized recommendations will appear below the content based on the visitor’s interests Use the shortcode [atlas_ai_personaflow] to place recommendations anywhere in your theme AltGenius (Image Alt Text) Go to Smart Local AI > Dashboard and enable the AltGenius module Upload an image via Media > Add New Media File — the model downloads on first use (~300 MB for ViT-GPT2) and alt text is generated automatically Or go to Smart Local AI > Bulk Alt Text and click Start Bulk Scan to generate alt text for all existing images missing it Or edit any post with images in the Block Editor — the AltGenius sidebar panel shows each image with a Generate Alt Text button External Services This plugin connects to the following external services. No user data or site content is transmitted to these services — only the ML model files are downloaded. Hugging Face Model Hub ML models are downloaded from the Hugging Face Model Hub (https://huggingface.co/) on first use and cached in the browser’s IndexedDB. The following models are used: RelevantFlow: Xenova/all-MiniLM-L6-v2 (~23 MB) — Sentence transformer for content embeddings AltGenius (ViT-GPT2): Xenova/vit-gpt2-image-captioning (~300 MB) — Image captioning model AltGenius (Florence-2): onnx-community/Florence-2-base-ft (~460 MB) — Advanced image captioning model These models are open-source and licensed under Apache 2.0 or MIT. No user content, images, or site data is uploaded to Hugging Face — the connection is download-only. Hugging Face Terms of Service Hugging Face Privacy Policy