EasyIT AI Chat vs AI Chatbot Free Models – Customer Support, Live Chat, Virtual Assistant

EasyIT AI Chat is the most feature-rich free AI chatbot plugin for WordPress. Drop in [eaic_chat] 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. 🌐 Website: easyit.com.bd 📺 Tutorials: youtube.com/@easybdit 💬 Community: facebook.com/easybdit 🎯 How It Works (3 Steps) Connect a provider — Add an API key (OpenAI, Claude, Gemini, DeepSeek, Together AI) or point it at a free local Ollama server. No API key needed for Ollama. Drop in a shortcode — Paste [eaic_chat] into any page or post, or just turn on the floating chat button in Settings → UI. No coding required. Done — Visitors get a ChatGPT-style assistant instantly. A built-in Test Chat page lets you try it from the dashboard before it ever reaches a visitor. 🏆 Why EasyIT AI Chat? Actually free, not “freemium” — every feature listed on this page, including the WooCommerce bots, is built into the free plugin. No Pro tier, no feature paywall, no upsell nags. Bring your own key, no markup — connect directly to your chosen AI provider with your own API key, or run Ollama locally for $0. You pay the provider directly, if at all — this plugin is never in the middle of your bill. Not locked to one AI vendor — most chatbot plugins pick a single provider for you. Here, one shortcode attribute (provider="gemini") switches the backend, even per page, anytime. Your data stays yours — zero telemetry to the plugin author, an optional No-Storage Mode, configurable retention, and a built-in GDPR consent gate. WooCommerce-aware, for free — Order Status, Product Q&A, Return/Refund, and Smart Product Finder bots activate automatically once WooCommerce is active; most store-chat plugins charge extra for this. Open source, fully auditable — GPL-2.0-or-later. Read every line yourself; nothing hidden in a compiled or obfuscated bundle. ✨ Supported AI Providers 🦙 Ollama — Run open-source models (Llama, Mistral, Gemma, Qwen, etc.) on your own server. 100% private, 100% free. 🤖 OpenAI (ChatGPT) — GPT-4o, GPT-4o-mini, GPT-4.1, o3, o4-mini and more. 🧠 Anthropic (Claude) — Claude 3.7 Sonnet, Claude 3.5 Sonnet, Claude 3.5 Haiku, Claude 3 Opus. 🔍 DeepSeek — DeepSeek-Chat, DeepSeek-Reasoner. ✦ Google Gemini — Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 2.0 Flash, Gemini 1.5 Flash. 🔧 Custom Providers — Any OpenAI-compatible endpoint (LM Studio, custom gateway, proxies, etc.). 🚀 Core Features One shortcode, any provider — [eaic_chat provider="gemini"] — switch provider per page, no settings change needed ChatGPT-style UI — Sidebar with conversation history, code blocks with copy button, markdown rendering Auto-title sessions — First message auto-generates a meaningful conversation title via the AI Conversation memory — Sessions saved per logged-in user or guest (cookie-scoped, never cross-user) Custom system prompt — Set globally in settings or override per shortcode Lock system prompt — Prevent front-end prompt injection; admin-configured prompt only Test Connection button — Verify your API key or Ollama URL before going live Rate limiting — Per-user, per-session, and per-IP throttle to prevent abuse Data retention — Auto-purge old conversations after a configurable number of days Context window control — Choose how many previous messages to include per AI request (1–20) Privacy notice — Optional configurable notice linking to your Privacy Policy Lightweight — Assets load only on pages using the shortcode No telemetry — Zero external calls except to the AI provider you choose Open source — GPL-2.0-or-later, fully auditable 💬 Chat UX & Interaction Typing indicator — Smooth 3-dot animated bubble while AI is responding (accent-color matched) Stop & Regenerate — Cancel a response mid-stream with the ⏹ Stop button; re-run with 🔄 Regenerate Message timestamps — HH:MM time shown next to every message label Copy & Download message — Copy or download any AI response with one click; buttons always visible below each message Read aloud (TTS) — 🔊 Speaker button reads any AI message using the browser’s built-in Speech Synthesis API Voice input — 🎤 Microphone button transcribes speech directly into the input field (Web Speech API) Fullscreen mode — Expand the chat widget to full-screen overlay; press Escape to exit Message feedback — 👍 / 👎 buttons below AI responses; ratings stored in your DB Session search — Search box in the sidebar filters conversations by title in real time 🎨 Customization Welcome message — Custom AI greeting bubble when a new chat starts (supports markdown) Suggested questions — Clickable chip buttons that send a question instantly Custom AI avatar — Replace the 🤖 emoji with any image from your Media Library Color customization — Accent, user bubble, and bot bubble colors via color pickers; reset to default in one click Floating chat widget — Fixed launcher button on every page; configurable position (bottom-right / bottom-left) and label Bot profiles — Save named configurations (provider, title, system prompt) and load with [eaic_chat profile="slug"] Multiple providers per site — Different providers on different pages using shortcode attributes 📊 Analytics & Insights Analytics dashboard — Total conversations, total messages, messages today, active chats (7 days), most-used provider 7-day bar chart — Pure CSS message chart — no external libraries Feedback stats — Helpful / Not helpful rating counts from user feedback 🔧 Developer & Admin Tools Shortcode Builder — Visual admin page: configure provider, title, height, system prompt — shortcode updates live, copy with one click Conversation export — Download any conversation as a .txt file Webhook support — POST to any URL after each AI response; JSON payload with session UUID, message, provider, timestamp; optional HMAC-SHA256 signature header Configurable message length — Set max characters per user message (50–4000) 🔒 Security Suite (v2.0) Access restriction — Allow everyone, logged-in users only, or specific WordPress user roles IP blocklist — Block specific IPv4 / IPv6 addresses from sending messages Word filter — Block or warn when a message contains banned words; configurable action Prompt injection detection — Auto-detect and block jailbreak patterns (“ignore all previous instructions”, “DAN mode”, etc.) No-storage mode — Opt out of saving conversations to the database entirely (GDPR-strict setups) Anti-bot math captcha — Simple arithmetic challenge before the first message; no external API or cookies required Abuse alert email — Get an email notification when the rate limit is exceeded; configurable recipient GDPR consent gate — Show an accept banner before the chat activates; consent stored in a browser cookie (365 days) 📚 Knowledge Base (RAG) Document upload — Upload PDF files to a private Knowledge Base; the AI answers questions using only your document data Semantic + keyword search — Queries are matched against document chunks via Ollama embeddings with automatic keyword fallback Accurate counting — “How many X” queries scan every chunk for an exact count — not just the top-K semantic results Context-aware answers — Matched chunks are injected into the system prompt so the AI gives specific, document-grounded answers Admin test tool — Test Query UI lets you inspect which chunks are retrieved for any query before going live Re-process on demand — Change embedding model or chunk settings and reprocess any document without re-uploading 🌐 Ask This Site (v2.5.0) Zero-setup site knowledge — Enable one toggle and the AI automatically learns your published posts/pages (or any public content type) — no manual document upload required Always current — Re-indexes automatically whenever content is published or updated; removed automatically if content is unpublished, made private, or deleted Works on any WordPress site — Not just WooCommerce stores — any site with content can have an AI that already knows it Bulk reindex — One click indexes your entire existing site content in batches, with a progress bar Privacy-respecting by default — Only publicly published, non-password-protected content is ever indexed 🛒 WooCommerce Bots (v2.4.0 — now free!) Everything below used to require the paid Pro add-on. It’s now built into the free plugin — no license, no upsell. Requires WooCommerce to be active. Order Status Bot ([eaic_order_chat]) — Customers check order status by chatting. Guests verify via order number + billing email; logged-in users are verified automatically. Product Q&A Bot ([eaic_product_chat]) — AI answers questions about any product (price, stock, description, variations) using real store data, with keyword search across your catalog. Return/Refund Bot ([eaic_return_chat]) — Conversationally collects the item + reason for a return and files a return request automatically, with an order note added for your team. Smart Product Finder ([eaic_product_finder]) — Natural-language product search (“red dress under $50”) that returns real product cards with add-to-cart links. “Ask Your Store” — Admin-only AI chat (EasyIT AI Chat menu, requires Shop Manager or Admin) that answers questions about revenue, orders, top products, low stock, and new customers from your own store data. Smart Floating Widget — Set the floating widget to “Smart” mode in Settings and it automatically shows the Order Bot on order pages, the Product Bot on product pages, and a general assistant everywhere else. Lead Capture — Optional pre-chat name + email form on the WooCommerce bots; leads are saved to your database and shown on the Analytics page. 🔧 Shortcode Examples 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: provider, title, placeholder, system_prompt, height, profile 💡 Use the Shortcode Builder (EasyIT AI Chat → Shortcode Builder) to generate shortcodes visually — no typing required. WooCommerce bots (requires WooCommerce active): [eaic_order_chat] — Order Status Bot [eaic_product_chat] or `[eaic_product_chat product_id="42"]` — Product Q&A Bot [eaic_return_chat] or `[eaic_return_chat order_id="123"]` — Return/Refund Bot [eaic_product_finder] — Smart Product Finder 🔒 Privacy 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. External Services 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. OpenAI 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 Anthropic (Claude) 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 DeepSeek 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 Google Gemini 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 Ollama 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. WooCommerce bots: When a WooCommerce bot is used, relevant store data needed to answer the question (e.g. order status/items, product details, or — for the admin-only “Ask Your Store” tool — aggregate revenue/order/customer data) is included in the request sent to your configured AI provider. This data never goes anywhere except the AI provider you’ve chosen; it is not sent to the plugin author.

AI Chatbot Free Models is a fully self-contained AI chatbot platform for WordPress. It provides everything you need to run professional live chat, customer support and virtual-assistant experiences on your website while leaving the choice of the AI model entirely in your hands. There is no paid SaaS behind this plugin. No mandatory subscription, no premium gateway, no external dashboard, no account required with the plugin developer. The only thing you need is access to an AI model: a hosted provider (many of which offer generous free tiers) or a self-hosted, local inference server. Every other component – interface, conversations, knowledge base, notifications, styling – runs on your own WordPress installation and your own database. Bring your own model, keep control of your data Connect OpenRouter, OpenAI, Anthropic, Google or any OpenAI-compatible endpoint. Run completely free with free-tier models or a local server (llama.cpp, Ollama, LM Studio, vLLM, gateways and proxies). Conversations are stored only if you enable it, in dedicated tables inside your own database. The knowledge base is built from your own published posts and pages – no external crawling, no third-party index. Core features Provider-agnostic AI connection with configurable endpoint, API key and model Dynamic model selection where the provider supports model discovery Streaming responses with live typing indicator Stop generation at any time while a response is being streamed Retry failed responses and start a new conversation without reloading the page Configurable maximum response tokens and streaming timeout with inactivity watchdog Conversation context maintained with a configurable token budget Optional pre-chat form to collect name and email for support and lead generation Live knowledge base with FULLTEXT-indexed search over titles and content, response caching and clickable source citations in answers Per-IP rate limiting and server-side sanitization of conversation history Dedicated database storage with optional message and IP retention (disabled by default) Unread conversation notifications, search and conversation management in the WordPress admin Floating widget (bottom-left or bottom-right) or embedded chat via the [newcodebyte_chatbot] shortcode Extensive appearance customization: colors, images, sounds, widget position Translatable frontend interface, responsive layout, multilingual AI support Modern object-oriented codebase following current WordPress standards Requirements WordPress 5.0 or later (tested up to 7.1) PHP 7.4 or later (compatible with current PHP 8.x releases) MySQL 5.6 or later / MariaDB 10.0 or later (required by the FULLTEXT knowledge base index) An API key for the provider you choose – or none at all, if you use a local OpenAI-compatible server How it works A visitor sends a message from the floating widget or the embedded chat. WordPress receives the request and the plugin prepares the conversation context. The configured provider or endpoint is selected and the request is sent. The response is streamed back to the visitor when streaming is supported. The conversation can optionally be stored in your own database for review. A note on costs The plugin is free and adds no usage fees of its own. AI costs depend exclusively on the provider and model you configure: free models and free quotas are fully supported, and a self-hosted server removes usage costs entirely. Looking for a platform-independent version? A standalone build for non-WordPress websites (HTML, PHP and more) is available on GitHub: https://github.com/NewCodeByte/chatbot-ai-free-models Configuration Open the Chatbot settings page. Depending on the selected provider you can configure: Provider (OpenRouter, OpenAI, Anthropic, Google or OpenAI-compatible endpoint) API endpoint and API key Model, selected from discovery or entered manually Maximum response tokens and streaming timeout Knowledge base, pre-chat form, storage options, appearance and sounds Free models on OpenRouter are identified by the :free suffix. When using a local or self-hosted OpenAI-compatible server, simply point the endpoint to your server (for example http://localhost:8080/v1): no external account is required and your traffic never leaves your infrastructure. External Services The plugin can transmit the content of a visitor’s message to the AI provider you configure (OpenRouter, OpenAI, Anthropic, Google or a custom endpoint) in order to generate a response. The terms of service and privacy policy of the selected provider apply to that processing. The plugin developer does not control and is not responsible for external providers’ pricing, availability, retention policies or data processing. Privacy Message and IP storage are optional and disabled by default. When enabled, data is stored in dedicated tables inside your own database and can be reviewed, exported or deleted from the admin area. The plugin itself sets no cookies. If you enable storage or the pre-chat form, update your privacy policy to describe the processing. You are responsible for compliance with applicable data-protection laws, including GDPR. Disclaimer AI-generated content can be inaccurate. The plugin developer is not responsible for AI responses, decisions made based on them, provider outages, pricing or API changes, or data processing performed by external providers. Always verify important information independently. Supporting the project AI Chatbot Free Models is developed and maintained as an independent free project. If you find it useful, consider keeping the optional “Powered by NewCodeByte” attribution enabled or supporting development with a donation. Contributions fund development, maintenance, testing and infrastructure.