Alexandre Amato

<p><strong>SpamAnvil is a free, open-source WordPress anti-spam plugin that uses artificial intelligence to block comment spam.</strong> Unlike Akismet (which requires a paid plan for commercial sites) or simple keyword-based filters, SpamAnvil leverages large language models (LLMs) to actually <em>understand</em> your comments and detect even the most sophisticated spam.</p>
<p>Traditional spam filters rely on static word lists and link counting. Spammers have evolved. <strong>SpamAnvil fights back with AI that understands context, intent, and language patterns</strong> – catching spam that looks legitimate and approving real comments that others would flag.</p>
<h4>Why SpamAnvil?</h4>
<ul>
<li><strong>100% Free</strong> – No premium tier, no subscription, no hidden costs. Bring your own API key (free options available).</li>
<li><strong>Smarter Than Rules</strong> – AI understands context. A comment about “buying a new home” won’t be flagged just because it contains “buy”.</li>
<li><strong>Works With Free AI Models</strong> – Use OpenRouter’s free Llama models for $0 cost, or connect premium models for maximum accuracy.</li>
<li><strong>Privacy-First</strong> – Your data stays between you and your chosen AI provider. IP addresses are stored as irreversible SHA-256 hashes. GDPR/LGPD compliant by design.</li>
<li><strong>No Cloud Lock-in</strong> – Choose from 6+ AI providers. Switch anytime. Your anti-spam, your rules.</li>
</ul>
<h4>Supported AI Providers</h4>
<ul>
<li><strong>OpenAI</strong> (GPT-4o-mini, GPT-4o, etc.)</li>
<li><strong>Anthropic Claude</strong> (Claude Sonnet, Haiku, etc.)</li>
<li><strong>Google Gemini</strong> (Gemini 2.0 Flash, Pro, etc.)</li>
<li><strong>OpenRouter</strong> (100+ models, including FREE ones)</li>
<li><strong>Featherless.ai</strong> (Open-source models)</li>
<li><strong>Any OpenAI-compatible API</strong> (LM Studio, Ollama via proxy, vLLM, etc.)</li>
</ul>
<h4>Key Features</h4>
<ul>
<li><strong>AI-Powered Spam Detection</strong> – Each comment is analyzed by an LLM that scores it 0-100 for spam probability</li>
<li><strong>Intelligent Heuristics Engine</strong> – Pre-analyzes comments with regex patterns, spam word detection, URL counting, and prompt injection detection to catch obvious spam without API calls</li>
<li><strong>Async Background Processing</strong> – Comments are queued and processed via WP-Cron so your site stays fast</li>
<li><strong>Smart IP Blocking</strong> – Automatically blocks repeat offenders with escalating ban durations (24h, 48h, 96h…)</li>
<li><strong>Automatic Retry with Backoff</strong> – Failed API calls retry up to 3 times with exponential delays</li>
<li><strong>Encrypted API Key Storage</strong> – AES-256-CBC encryption for all stored API keys. Optional wp-config.php constants for maximum security</li>
<li><strong>Statistics Dashboard</strong> – Track how many comments were checked, how much spam was caught, API usage and errors</li>
<li><strong>Full Evaluation Logs</strong> – See the AI’s reasoning for every comment scored, with provider, model, response time, and score</li>
<li><strong>Customizable AI Prompts</strong> – Full control over what the AI is instructed to do</li>
<li><strong>Fallback Provider</strong> – Configure a backup AI so spam checking never stops</li>
<li><strong>Prompt Injection Defense</strong> – Multi-layered protection prevents attackers from manipulating the AI through crafted comments</li>
<li><strong>Configurable Spam Threshold</strong> – Slide between aggressive (catch more spam) and permissive (fewer false positives)</li>
<li><strong>Moderator Bypass</strong> – Trusted users skip spam checking entirely</li>
</ul>
<h4>How It Works</h4>
<ol>
<li>A visitor submits a comment</li>
<li>SpamAnvil checks if the IP is blocked from previous spam attempts</li>
<li>The heuristic engine runs a quick pre-analysis (URL count, spam words, suspicious patterns)</li>
<li>If the heuristic score is very high, the comment is instantly marked as spam – no API call needed</li>
<li>Otherwise, the comment is queued for AI analysis (or processed immediately in sync mode)</li>
<li>The AI analyzes the comment in context (post title, author info, heuristic data) and returns a spam score</li>
<li>Comments scoring above your threshold are marked as spam; clean comments are auto-approved</li>
<li>Repeat offender IPs are automatically blocked with escalating durations</li>
</ol>
<h4>Use Cases</h4>
<ul>
<li><strong>Blogs</strong> receiving hundreds of spam comments per day</li>
<li><strong>WooCommerce stores</strong> where comment spam affects SEO and credibility</li>
<li><strong>Membership sites</strong> that need to protect community discussions</li>
<li><strong>Multilingual sites</strong> – AI understands comments in any language, unlike keyword-based filters</li>
<li><strong>High-traffic sites</strong> – Async processing handles any volume without slowing down your site</li>
<li><strong>Sites tired of Akismet</strong> – Free alternative with no cloud dependency and full data control</li>
</ul>
<h4>Security</h4>
<p>SpamAnvil follows WordPress security best practices throughout:</p>
<ul>
<li>AES-256-CBC encrypted API key storage</li>
<li>wp-config.php constant support for API keys (never touch the database)</li>
<li>Nonce verification on all forms and AJAX requests</li>
<li>Capability checks on all admin actions</li>
<li>Prepared SQL statements on every database query</li>
<li>Output escaping on all rendered content</li>
<li>Prompt injection defense: boundary tags, system prompt hardening, heuristic injection detection, strict JSON validation, temperature 0</li>
</ul>
<h4>Languages</h4>
<ul>
<li>English (default)</li>
<li>Translation-ready (.pot file included)</li>
</ul>
<h4>Third-Party Services</h4>
<p>SpamAnvil sends comment data (content, author name, email, and URL) to external AI services for spam analysis. The specific service used depends on your configuration. No data is sent until you configure and enable a provider.</p>
<ul>
<li><strong>OpenAI</strong> — <a href="https://openai.com" rel="nofollow ugc">https://openai.com</a> — <a href="https://openai.com/policies/terms-of-use" rel="nofollow ugc">Terms of Use</a> — <a href="https://openai.com/policies/privacy-policy" rel="nofollow ugc">Privacy Policy</a></li>
<li><strong>Anthropic (Claude)</strong> — <a href="https://www.anthropic.com" rel="nofollow ugc">https://www.anthropic.com</a> — <a href="https://www.anthropic.com/policies#terms" rel="nofollow ugc">Terms of Service</a> — <a href="https://www.anthropic.com/policies#privacy" rel="nofollow ugc">Privacy Policy</a></li>
<li><strong>Google Gemini</strong> — <a href="https://ai.google.dev" rel="nofollow ugc">https://ai.google.dev</a> — <a href="https://ai.google.dev/gemini-api/terms" rel="nofollow ugc">Terms of Service</a> — <a href="https://policies.google.com/privacy" rel="nofollow ugc">Privacy Policy</a></li>
<li><strong>OpenRouter</strong> — <a href="https://openrouter.ai" rel="nofollow ugc">https://openrouter.ai</a> — <a href="https://openrouter.ai/terms" rel="nofollow ugc">Terms of Service</a> — <a href="https://openrouter.ai/privacy" rel="nofollow ugc">Privacy Policy</a></li>
<li><strong>Featherless.ai</strong> — <a href="https://featherless.ai/" rel="nofollow ugc">https://featherless.ai</a> — <a href="https://featherless.ai/terms" rel="nofollow ugc">Terms of Service</a> — <a href="https://featherless.ai/privacy" rel="nofollow ugc">Privacy Policy</a></li>
</ul>
<p>When using the “Generic OpenAI-Compatible” option, data is sent to the URL you configure. You are responsible for ensuring compliance with the privacy policies of your chosen service.</p>


SpamAnvil

Stop comment spam with AI. Uses ChatGPT, Claude, Gemini and other LLMs to catch spam that traditional filters miss. 100% free.

kognetiks

<p><strong>Quiet Proof for Your Website</strong></p>
<p>Most websites are having conversations you never see.</p>
<p>Visitors ask questions, express confusion, or look for answers without ever filling out a form or opening a ticket. Traditional analytics don’t show this. Chat logs are too noisy to monitor at scale.</p>
<p><strong>Kognetiks Chatbot turns those invisible interactions into quiet proof of value.</strong></p>
<p>Instead of guessing whether your chatbot is helping, you receive clear, human-readable summaries that show what visitors asked, where AI helped, and where attention may be needed.</p>
<p>No dashboards to babysit.<br />
No transcripts to dig through.<br />
Just insight, delivered.</p>
<h3>What Makes This Different</h3>
<p>Kognetiks is not a novelty chatbot.  It is build for understanding, oversight, and long-term use.</p>
<p>It is designed for <strong>visibility, oversight, and measurable outcomes</strong>, so you can understand how AI is actually being used on your site.</p>
<p>AI assists.<br />
Humans decide.</p>
<h3>Who This Is For</h3>
<p>This plugin is a strong fit if you:</p>
<ul>
<li>Want to know what visitors are really asking</li>
<li>Care about intent, not just answers</li>
<li>Need proof that AI is providing value</li>
<li>Prefer insight delivered automatically</li>
<li>Value transparency over black-box automation</li>
</ul>
<p>Common users include:</p>
<ul>
<li>Agencies managing client websites</li>
<li>Consultants and site owners</li>
<li>Product and content teams</li>
<li>Founders who want clarity, not noise</li>
</ul>
<h3>Who This Is Not For</h3>
<p>This plugin may not be a fit if you:</p>
<ul>
<li>Only want a novelty chatbot</li>
<li>Expect AI to operate without human oversight</li>
<li>Prefer opaque or fully autonomous systems</li>
<li>Don’t want visibility into AI behavior</li>
</ul>
<h3>Key Outcomes</h3>
<p>With Kognetiks, you can:</p>
<ul>
<li>See what visitors asked without reading every transcript</li>
<li>Understand engagement and intent patterns over time</li>
<li>Identify unanswered questions and content gaps</li>
<li>Demonstrate real, ongoing value from conversational AI</li>
</ul>
<h3>Conversation Digest</h3>
<p>Automatically summarizes real chatbot interactions, including:</p>
<ul>
<li>Common questions and themes</li>
<li>Signals of confusion, friction, or opportunity</li>
<li>High-level engagement and sentiment indicators</li>
</ul>
<p>Reports are delivered automatically to your inbox.</p>
<p>No dashboards required.</p>
<h3>Proof-of-Value Reporting</h3>
<p>Turns invisible chatbot activity into visible outcomes:</p>
<ul>
<li>Usage and engagement trends</li>
<li>Evidence of support and efficiency gains</li>
<li>Insight you can act on or share</li>
</ul>
<p>Ideal for agencies, consultants, and teams who need to justify ongoing value.</p>
<h3>Key Features</h3>
<ul>
<li>Conversation Digest summaries</li>
<li>Proof-of-value reporting</li>
<li>Reports are designed to be shared as-is, without explanation</li>
<li>Supports multiple AI engines (OpenAI, Azure OpenAI, NVIDIA, Anthropic, Mistral, DeepSeek, Google, JAN.AI)</li>
<li>Knowledge Navigator for site-aware responses</li>
<li>Custom assistants for specific purposes</li>
<li>Conversation logging with export options</li>
<li>Sentiment and engagement signals</li>
<li>Optional voice and speech support</li>
<li>Embedded or floating chat via shortcode</li>
</ul>
<h3>Philosophy</h3>
<p><strong>Designed for visibility, not guesswork.</strong></p>
<p>The <strong>Kognetiks Chatbot</strong> helps you understand when AI is helping, when it needs adjustment, and where small changes can quietly make a big difference.</p>
<h3>External Services</h3>
<p>The <strong>Kognetiks Chatbot</strong> plugin relies on external AI services to provide chatbot functionality. It sends user queries and related data to a third-party AI provider for processing and response generation. By using this plugin, you agree to abide by each service’s terms of service and privacy policy:</p>
<ul>
<li><strong>OpenAI</strong>: <a href="https://platform.openai.com/terms" rel="nofollow ugc">Terms of Use</a> | <a href="https://openai.com/policies/privacy-policy/" rel="nofollow ugc">Privacy Policy</a></li>
<li><strong>Azure OpenAI</strong>: <a href="https://learn.microsoft.com/en-us/legal/cognitive-services/openai/data-privacy?tabs=azure-portal" rel="nofollow ugc">Terms of Use</a> | <a href="https://www.microsoft.com/en-us/privacy/privacystatement" rel="nofollow ugc">Privacy Policy</a></li>
<li><strong>NVIDIA</strong>: <a href="https://www.nvidia.com/en-us/about-nvidia/nv-accounts/" rel="nofollow ugc">Terms of Use</a> | <a href="https://www.nvidia.com/en-us/about-nvidia/privacy-policy/" rel="nofollow ugc">Privacy Policy</a></li>
<li><strong>Anthropic</strong>: <a href="https://www.anthropic.com/legal/consumer-terms" rel="nofollow ugc">Terms of Service</a> | <a href="https://docs.anthropic.com/en/docs/legal-center/privacy" rel="nofollow ugc">Privacy Policy</a></li>
<li><strong>DeepSeek</strong>: <a href="https://chat.deepseek.com/downloads/DeepSeek%20User%20Agreement.html" rel="nofollow ugc">Terms of Use</a> | <a href="https://chat.deepseek.com/downloads/DeepSeek%20Privacy%20Policy.html" rel="nofollow ugc">Privacy Policy</a></li>
<li><strong>Mistral</strong>: <a href="https://mistral.ai/terms#terms-of-service" rel="nofollow ugc">Terms of Service</a> | <a href="https://mistral.ai/terms#privacy-policy" rel="nofollow ugc">Privacy Policy</a></li>
<li><strong>Google</strong>: <a href="https://ai.google.dev/gemini-api/terms" rel="nofollow ugc">Terms of Use</a> | <a href="https://policies.google.com/privacy" rel="nofollow ugc">Privacy Policy</a></li>
<li><strong>JAN.AI</strong>: <a href="https://jan.ai/about" rel="nofollow ugc">About</a> | <a href="https://jan.ai/docs/privacy-policy" rel="nofollow ugc">Privacy Policy</a></li>
</ul>
<p><strong>IMPORTANT</strong>:</p>
<ul>
<li>
<p>This plugin requires an API key from OpenAI, NVIDIA, Anthropic, DeepSeek, Mistral, Google, or JAN.AI to function. Without an API key, the chatbot cannot process user queries.</p>
</li>
<li>
<p>Obtain API keys here:</p>
<ul>
<li><a href="https://platform.openai.com/account/api-keys" rel="nofollow ugc">OpenAI API Keys</a></li>
<li><a href="https://azure.microsoft.com/en-us/pricing/purchase-options/azure-account?icid=ai-services" rel="nofollow ugc">Azure API Keys</a></li>
<li><a href="https://developer.nvidia.com/nim" rel="nofollow ugc">NVIDIA API Keys</a></li>
<li><a href="https://www.anthropic.com/" rel="nofollow ugc">Anthropic API Keys</a></li>
<li><a href="https://platform.deepseek.com/sign_in" rel="nofollow ugc">DeepSeek API Keys</a></li>
<li><a href="https://console.mistral.ai/api-keys" rel="nofollow ugc">Mistral API Keys</a></li>
<li><a href="https://aistudio.google.com/api-keys" rel="nofollow ugc">Google API Keys</a></li>
</ul>
</li>
<li>
<p>By entering your API key from the AI provider of your choice and activating the chatbot, you:</p>
<ul>
<li>Consent to sending user queries and related data to the selected AI provider for processing and response generation.</li>
<li>Agree to abide by the provider’s terms of service, pricing, and privacy policy.</li>
<li>Acknowledge that your data, including text submitted by users, may be transferred to and processed by the AI platform in accordance with its privacy policy.</li>
</ul>
</li>
</ul>
<p><strong>NOTE</strong>: You are responsible for any fees associated with the use of the selected AI platform. Be sure to review each provider’s pricing and usage policies before proceeding.</p>
<h3>Disclaimer</h3>
<p>WordPress, OpenAI, ChatGPT, NVIDIA, NIM, Anthropic, Claude, DeepSeek, Mistral, Azure and related trademarks are the property of their respective owners. Kognetiks is an independent entity and is not affiliated with, endorsed by, or sponsored by WordPress Foundation, OpenAI, NVIDIA, Anthropic, DeepSeek, or Mistral.</p>


Kognetiks Chatbot for WordPress


1 star until they implement the ability to use a custom model. This should already be a feature.


Doesn't allow Custom Models

Quiet proof that your website is working. Turn real visitor conversations into clear insight, automatically. No dashboards. No guesswork.

SpamAnvil vs Kognetiks Chatbot for WordPress