iFrameMX

iFrameMX AI Chat for Web adds a sleek, mobile-friendly floating chat widget to your WordPress site. Choose your AI provider — DeepSeek, OpenAI, Gemini, Claude, Grok, Groq, OpenRouter, or any OpenAI-compatible custom endpoint — and start chatting with visitors in minutes.
Key Features:
<ul>
<li>🤖 Multi-AI support — DeepSeek, OpenAI, Gemini, Claude, Grok, Groq, OpenRouter + custom</li>
<li>🔑 Your own API keys — full control, no middleware, you bring the credentials</li>
<li>📋 Lead capture form — name, email, phone, interest (configurable fields)</li>
<li>🛡️ Built-in AI guardrails — safe, helpful responses always</li>
<li>💬 Conversation storage — searchable tickets in your WordPress admin</li>
<li>🎨 Customizable appearance — icon, color, position, text, field layout</li>
<li>📱 Fully responsive — works great on mobile devices</li>
<li>📥 Export conversations — JSON or CSV export from admin panel</li>
<li>🔔 Email notifications — get alerted when a new chat starts</li>
<li>⏰ Auto-close inactive chats — keep your dashboard clean</li>
<li>🧩 Shortcode <code>[iframemx_chat]</code> — embed the chat in any page or post</li>
<li>🌐 Translation-ready — Spanish-first, fully internationalized</li>
<li>♿ Accessibility — keyboard navigable, screen-reader friendly</li>
</ul>
Perfect for:
<ul>
<li>Small businesses wanting 24/7 AI customer support</li>
<li>E-commerce sites needing to capture and qualify leads</li>
<li>Service companies automating first-contact conversations</li>
<li>Any WordPress site wanting a customizable, brand-safe AI assistant</li>
</ul>
<h3>External Services</h3>
This plugin communicates with third-party AI APIs to generate chat responses. You choose which provider to use and provide your own API key.
Supported providers and their data policies:
<ul>
<li>DeepSeek — API key required. Data sent to api.deepseek.com. <a href="https://platform.deepseek.com/terms" rel="nofollow ugc">Terms</a> | <a href="https://platform.deepseek.com/privacy" rel="nofollow ugc">Privacy</a></li>
<li>OpenAI — API key required. Data sent to api.openai.com. <a href="https://openai.com/policies/terms-of-use" rel="nofollow ugc">Terms</a> | <a href="https://openai.com/policies/privacy-policy" rel="nofollow ugc">Privacy</a></li>
<li>Google Gemini — API key required. Data sent to generativelanguage.googleapis.com. <a href="https://ai.google.dev/terms" rel="nofollow ugc">Terms</a> | <a href="https://policies.google.com/privacy" rel="nofollow ugc">Privacy</a></li>
<li>Anthropic Claude — API key required. Data sent to api.anthropic.com. <a href="https://www.anthropic.com/legal/consumer-terms" rel="nofollow ugc">Terms</a> | <a href="https://www.anthropic.com/legal/privacy" rel="nofollow ugc">Privacy</a></li>
<li>Grok (xAI) — API key required. Data sent to api.x.ai. <a href="https://x.ai/legal/terms-of-service" rel="nofollow ugc">Terms</a></li>
<li>Groq — API key required. Data sent to api.groq.com. <a href="https://groq.com/terms-of-service/" rel="nofollow ugc">Terms</a> | <a href="https://groq.com/privacy-policy/" rel="nofollow ugc">Privacy</a></li>
<li>OpenRouter — API key required. Data sent to openrouter.ai. <a href="https://openrouter.ai/terms" rel="nofollow ugc">Terms</a> | <a href="https://openrouter.ai/privacy" rel="nofollow ugc">Privacy</a></li>
</ul>
What data is sent: Chat conversation messages, the visitor’s name, email, phone (if provided), interest, and your configured company information are sent to the selected AI provider as part of the conversation context. This is necessary for the AI to personalize responses (e.g., greeting the visitor by name).
When data is sent: Only when a visitor actively fills out the lead form (name/email) and sends a chat message. No data is transmitted on page load or idle periods.
Consent requirement: The plugin includes a mandatory consent checkbox on the lead capture form. Visitors must explicitly opt in before their data is sent to any AI provider. The consent checkbox is enabled by default and cannot be bypassed.
Your responsibility: As the site owner, you must inform your visitors that their messages are processed by a third-party AI service and comply with the selected provider’s terms. Update your privacy policy accordingly.
Privacy: Visitor IP addresses are stored in your local WordPress database for spam prevention but are never sent to third-party AI providers.
WhatsApp Handoff (api.whatsapp.com): When the optional WhatsApp handoff feature is enabled, the plugin constructs a <code>https://api.whatsapp.com/send</code> link containing the visitor’s chat summary when the AI determines human intervention is needed (purchase intent, complex quotes, or user request). The phone number and message are encoded in the URL. The visitor must tap the link to open WhatsApp — no data is automatically sent. WhatsApp is a service provided by Meta Platforms, Inc. <a href="https://www.whatsapp.com/legal/terms-of-service" rel="nofollow ugc">Terms of Service</a> | <a href="https://www.whatsapp.com/legal/privacy-policy" rel="nofollow ugc">Privacy Policy</a>.

iFrameMX AI Chat for Web

Add an intelligent floating AI chatbot to your WordPress site with lead capture, multi-provider AI support, conversation tickets, and a full admin das …

easyit

Md Murad Hosen

EasyIT AI Chat is the most feature-rich free AI chatbot plugin for WordPress. Drop in <code>[eaic_chat]</code> on any page to add a fully-featured ChatGPT-style assistant — powered by OpenAI, Anthropic Claude, Google Gemini, DeepSeek, or a 100% free local Ollama model. No coding required.
You own your data, you control your keys. No tracking, no telemetry, no subscription — ever.
<blockquote>
🌐 Website: <a href="https://easyit.com.bd" rel="nofollow ugc">easyit.com.bd</a> 
 📺 Tutorials: <a href="https://www.youtube.com/@easybdit" rel="nofollow ugc">youtube.com/@easybdit</a> 
 💬 Community: <a href="https://www.facebook.com/easybdit" rel="nofollow ugc">facebook.com/easybdit</a>
</blockquote>
<h4>✨ Supported AI Providers</h4>
<ul>
<li>🦙 Ollama — Run open-source models (Llama, Mistral, Gemma, Qwen, etc.) on your own server. 100% private, 100% free.</li>
<li>🤖 OpenAI (ChatGPT) — GPT-4o, GPT-4o-mini, GPT-4.1, o3, o4-mini and more.</li>
<li>🧠 Anthropic (Claude) — Claude 3.7 Sonnet, Claude 3.5 Sonnet, Claude 3.5 Haiku, Claude 3 Opus.</li>
<li>🔍 DeepSeek — DeepSeek-Chat, DeepSeek-Reasoner.</li>
<li>✦ Google Gemini — Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 2.0 Flash, Gemini 1.5 Flash.</li>
<li>🔧 Custom Providers — Any OpenAI-compatible endpoint (LM Studio, custom gateway, proxies, etc.).</li>
</ul>
<h4>🚀 Core Features</h4>
<ul>
<li>One shortcode, any provider — <code>[eaic_chat provider="gemini"]</code> — switch provider per page, no settings change needed</li>
<li>ChatGPT-style UI — Sidebar with conversation history, code blocks with copy button, markdown rendering</li>
<li>Auto-title sessions — First message auto-generates a meaningful conversation title via the AI</li>
<li>Conversation memory — Sessions saved per logged-in user or guest (cookie-scoped, never cross-user)</li>
<li>Custom system prompt — Set globally in settings or override per shortcode</li>
<li>Lock system prompt — Prevent front-end prompt injection; admin-configured prompt only</li>
<li>Test Connection button — Verify your API key or Ollama URL before going live</li>
<li>Rate limiting — Per-user, per-session, and per-IP throttle to prevent abuse</li>
<li>Data retention — Auto-purge old conversations after a configurable number of days</li>
<li>Context window control — Choose how many previous messages to include per AI request (1–20)</li>
<li>Privacy notice — Optional configurable notice linking to your Privacy Policy</li>
<li>Lightweight — Assets load only on pages using the shortcode</li>
<li>No telemetry — Zero external calls except to the AI provider you choose</li>
<li>Open source — GPL-2.0-or-later, fully auditable</li>
</ul>
<h4>💬 Chat UX & Interaction</h4>
<ul>
<li>Typing indicator — Smooth 3-dot animated bubble while AI is responding (accent-color matched)</li>
<li>Stop & Regenerate — Cancel a response mid-stream with the ⏹ Stop button; re-run with 🔄 Regenerate</li>
<li>Message timestamps — HH:MM time shown next to every message label</li>
<li>Copy & Download message — Copy or download any AI response with one click; buttons always visible below each message</li>
<li>Read aloud (TTS) — 🔊 Speaker button reads any AI message using the browser’s built-in Speech Synthesis API</li>
<li>Voice input — 🎤 Microphone button transcribes speech directly into the input field (Web Speech API)</li>
<li>Fullscreen mode — Expand the chat widget to full-screen overlay; press Escape to exit</li>
<li>Message feedback — 👍 / 👎 buttons below AI responses; ratings stored in your DB</li>
<li>Session search — Search box in the sidebar filters conversations by title in real time</li>
</ul>
<h4>🎨 Customization</h4>
<ul>
<li>Welcome message — Custom AI greeting bubble when a new chat starts (supports markdown)</li>
<li>Suggested questions — Clickable chip buttons that send a question instantly</li>
<li>Custom AI avatar — Replace the 🤖 emoji with any image from your Media Library</li>
<li>Color customization — Accent, user bubble, and bot bubble colors via color pickers; reset to default in one click</li>
<li>Floating chat widget — Fixed launcher button on every page; configurable position (bottom-right / bottom-left) and label</li>
<li>Bot profiles — Save named configurations (provider, title, system prompt) and load with <code>[eaic_chat profile="slug"]</code></li>
<li>Multiple providers per site — Different providers on different pages using shortcode attributes</li>
</ul>
<h4>📊 Analytics & Insights</h4>
<ul>
<li>Analytics dashboard — Total conversations, total messages, messages today, active chats (7 days), most-used provider</li>
<li>7-day bar chart — Pure CSS message chart — no external libraries</li>
<li>Feedback stats — Helpful / Not helpful rating counts from user feedback</li>
</ul>
<h4>🔧 Developer & Admin Tools</h4>
<ul>
<li>Shortcode Builder — Visual admin page: configure provider, title, height, system prompt — shortcode updates live, copy with one click</li>
<li>Conversation export — Download any conversation as a <code>.txt</code> file</li>
<li>Webhook support — POST to any URL after each AI response; JSON payload with session UUID, message, provider, timestamp; optional HMAC-SHA256 signature header</li>
<li>Configurable message length — Set max characters per user message (50–4000)</li>
</ul>
<h4>🔒 Security Suite (v2.0)</h4>
<ul>
<li>Access restriction — Allow everyone, logged-in users only, or specific WordPress user roles</li>
<li>IP blocklist — Block specific IPv4 / IPv6 addresses from sending messages</li>
<li>Word filter — Block or warn when a message contains banned words; configurable action</li>
<li>Prompt injection detection — Auto-detect and block jailbreak patterns (“ignore all previous instructions”, “DAN mode”, etc.)</li>
<li>No-storage mode — Opt out of saving conversations to the database entirely (GDPR-strict setups)</li>
<li>Anti-bot math captcha — Simple arithmetic challenge before the first message; no external API or cookies required</li>
<li>Abuse alert email — Get an email notification when the rate limit is exceeded; configurable recipient</li>
<li>GDPR consent gate — Show an accept banner before the chat activates; consent stored in a browser cookie (365 days)</li>
</ul>
<h4>📚 Knowledge Base (RAG)</h4>
<ul>
<li>Document upload — Upload PDF files to a private Knowledge Base; the AI answers questions using only your document data</li>
<li>Semantic + keyword search — Queries are matched against document chunks via Ollama embeddings with automatic keyword fallback</li>
<li>Accurate counting — “How many X” queries scan every chunk for an exact count — not just the top-K semantic results</li>
<li>Context-aware answers — Matched chunks are injected into the system prompt so the AI gives specific, document-grounded answers</li>
<li>Admin test tool — Test Query UI lets you inspect which chunks are retrieved for any query before going live</li>
<li>Re-process on demand — Change embedding model or chunk settings and reprocess any document without re-uploading</li>
</ul>
<h4>🛒 WooCommerce Add-on (Pro)</h4>
Looking for WooCommerce features? EasyIT AI Chat Pro adds:
<ul>
<li>Order Status Bot — Customers check order status by chatting. Guests verify via order number + billing email.</li>
<li>Product Q&A Bot — AI answers questions about any product (price, stock, description). Smart keyword search included.</li>
<li>Floating Smart Widget — Context-aware chat launcher that appears on all pages automatically.</li>
<li>Lead Capture — Collect visitor name and email before chat starts.</li>
</ul>
<h4>🔧 Shortcode Examples</h4>
Basic usage: 
 [eaic_chat]
Specify a provider: 
 [eaic_chat provider=”gemini” title=”Support Bot” height=”500″]
Custom system prompt: 
 [eaic_chat provider=”ollama” system_prompt=”You are a helpful gardening assistant.”]
Load a saved bot profile: 
 [eaic_chat profile=”support-bot”]
Full example: 
 [eaic_chat provider=”openai” title=”Ask Anything” placeholder=”Type your question…” height=”600″ system_prompt=”You are a helpful assistant for our website.”]
Available attributes: <code>provider</code>, <code>title</code>, <code>placeholder</code>, <code>system_prompt</code>, <code>height</code>, <code>profile</code>
💡 Use the Shortcode Builder (EasyIT AI Chat → Shortcode Builder) to generate shortcodes visually — no typing required.
<h4>🔒 Privacy</h4>
When a user sends a message, it is forwarded to your configured AI provider along with the conversation history. Messages are also stored in your own database so conversations can resume. Nothing is sent to the plugin author. You should mention your chosen provider in your site’s Privacy Policy.
<h3>External Services</h3>
This plugin connects to external AI services depending on which provider you configure. No data is transmitted unless a user actively sends a chat message.
<h4>OpenAI</h4>
Used when OpenAI is selected as the AI provider. 
* Service URL: https://api.openai.com/ 
* Terms of Use: https://openai.com/policies/row-terms-of-use 
* Privacy Policy: https://openai.com/policies/row-privacy-policy
<h4>Anthropic (Claude)</h4>
Used when Anthropic is selected as the AI provider. 
* Service URL: https://api.anthropic.com/ 
* Terms of Use: https://www.anthropic.com/legal/consumer-terms 
* Privacy Policy: https://www.anthropic.com/legal/privacy
<h4>DeepSeek</h4>
Used when DeepSeek is selected as the AI provider. 
* Service URL: https://api.deepseek.com/ 
* Terms of Use: https://chat.deepseek.com/downloads/DeepSeek%20Terms%20of%20Use.html 
* Privacy Policy: https://chat.deepseek.com/downloads/DeepSeek%20Privacy%20Policy.html
<h4>Google Gemini</h4>
Used when Google Gemini is selected as the AI provider. 
* Service URL: https://generativelanguage.googleapis.com/ 
* Terms of Use: https://ai.google.dev/gemini-api/terms 
* Privacy Policy: https://policies.google.com/privacy
<h4>Ollama</h4>
Used when Ollama is selected. Calls your own self-hosted Ollama server URL. 
No third-party service is involved unless you point it at a remote server.
Data sent to external services: The user’s chat message and recent conversation history (last 10 messages). No personal data beyond what the user types is transmitted.

EasyIT AI Chat — Chatbot for OpenAI, Claude, DeepSeek, Gemini & Ollama

AI chatbot for WordPress — OpenAI, Claude, Gemini, DeepSeek & Ollama via one shortcode. 30+ features. Bring your own API keys.

iFrameMX AI Chat for Web vs EasyIT AI Chat — Chatbot for OpenAI, Claude, DeepSeek, Gemini & Ollama