rsnare

dAIrect Chat enables you to embed a Gemini-powered chatbot into any page or post using a shortcode. Designed for simplicity, flexibility, and fast response, it is perfect for customer support, creative interaction, or building your own branded assistant.
<h4>Features include:</h4>
<ul>
<li>Multi-turn memory (stored per user)</li>
<li>Configurable: temperature, topP, max tokens, timeout</li>
<li>Custom system instruction (acts as a personality or role)</li>
<li>Voice input (Chrome only)</li>
<li>Easy shortcode integration: <code>[dairect_chat_widget]</code></li>
<li>Admin test prompt with saved parameter preview</li>
</ul>
<h3>External Services</h3>
This plugin connects to the Google Gemini API to generate conversational responses using AI.
<ul>
<li>Data sent: Chat message contents and optional system instructions.</li>
<li>Sent when: The user sends a message via the widget or admin test prompt.</li>
<li>Service provider: Google LLC 
<a href="https://policies.google.com/terms" rel="nofollow ugc">Terms of Service</a> | <a href="https://policies.google.com/privacy" rel="nofollow ugc">Privacy Policy</a></li>
</ul>
<h3>License</h3>
GPLv2 or later — Fork freely, build professionally.
License URI: https://www.gnu.org/licenses/gpl-2.0.html
MIT — Fork freely, build professionally.

dAIrect Chat

dAIrect Chat is a lightweight Gemini AI chat widget for WordPress with multi-turn memory, voice input, and custom system instructions.

chancerylaneproject

Markdown for Agents and Statistics converts your WordPress content to Markdown and serves it 
to AI agents and language model tools that request it via HTTP content negotiation 
(<code>Accept: text/markdown</code>).
The Chancery Lane Project is a charity that helps organisations reduce emissions using the power of legal documents and processes. We’ve published this plugin as we believe that making content more legible for AI Agents makes a meaningful difference to their energy usage – not only by reducing the amount of tokens required (by up to 90% over HTML) to consume the content, but also minimising the server resources required to render, process and display pages at source.
How it works:
<ol>
<li>Posts and taxonomy archive pages are converted to Markdown and saved as static 
files on disk inside <code>wp-content/uploads/</code>.</li>
<li>When a visitor (or AI agent) requests a page with <code>Accept: text/markdown</code> in 
the HTTP headers, WordPress serves the pre-generated <code>.md</code> file directly — 
no page render required.</li>
<li>A <code><link rel="alternate" type="text/markdown"></code> tag is added to each page’s 
 so agents can discover Markdown versions automatically.</li>
</ol>
Features:
<ul>
<li>Content negotiation (<code>Accept: text/markdown</code>, <code>?output_format=md</code>, or known AI User-Agents)</li>
<li>Taxonomy archive support — category, tag, and custom taxonomy term pages served as Markdown post listings</li>
<li>Automatic Markdown generation on post save; taxonomy archives auto-update when any post in the term changes</li>
<li>AJAX bulk generation with live progress counter — no page timeouts on large sites</li>
<li>Per-post-type field configuration — choose which meta/ACF fields go in frontmatter or body</li>
<li>ACF support with dot notation for nested group fields (e.g. <code>group.subfield</code>)</li>
<li>Content fields option — use ACF fields as the body content instead of post_content</li>
<li>Manifest generation with content hashes and change tracking per post type</li>
<li>Incremental export — only re-export changed documents (<code>--incremental</code>)</li>
<li>Delta file (<code>changes.json</code>) for RAG system sync</li>
<li>Access statistics — logs AI agent requests with a dedicated stats admin page</li>
<li>Optional frontmatter fields — hierarchy (parent/ancestors/children IDs), author display name, root-relative featured image paths</li>
<li>Topics section — appends a <code>## Topics</code> section with linked taxonomy terms to the Markdown body</li>
<li>Export preview — preview generated Markdown inline in the post editor without writing to disk</li>
<li>WP-CLI commands: <code>generate</code>, <code>generate-taxonomies</code>, <code>prune-stats</code>, <code>status</code>, <code>delete</code></li>
<li>Fully unit-tested</li>
</ul>

Markdown for Agents and Statistics

Serve pre-generated Markdown files to AI agents via HTTP content negotiation.

dAIrect Chat vs Markdown for Agents and Statistics