Active installations100Adoption metric — not a quality score
WordPress.org ratingNo WordPress.org ratings yet
Official packageDirect from WordPress.org
Repository metrics are context, not quality scores. Active installations measure adoption and can strongly reflect a plugin’s age and historical popularity. Ratings, recent updates and “Tested up to” metadata also do not guarantee modern code, error-free operation, security, feature completeness or suitability for a particular site. Why active installs don’t tell the whole story →
WP PlugIndex currently records Ultimate AI Connector for Compatible Endpoints version 2.2.1 as active, updated 1mo ago and tested up to WordPress 7.1.
Overview
About this plugin
This plugin extends the WordPress AI Client to support any AI service or server that uses the standard chat completions API format ( /v1/chat/completions and /v1/models endpoints).
Supported services include:
Ollama – Run open-source models (Llama, Mistral, Gemma, etc.) locally on your own hardware.
LM Studio – Desktop application for local LLM inference with a one-click server.
OpenRouter – Unified API providing access to 100+ models from multiple providers.
vLLM – High-throughput inference server for production deployments.
LocalAI – Drop-in replacement for running models locally.
text-generation-webui – Popular web UI with API server mode.
Any compatible endpoint – Works with any server implementing the standard format.
Requirements:
WordPress 7.0+ – The AI Client SDK is included in core. This plugin works on its own without any additional dependencies.
WordPress 6.9 – Also supported when the Gutenberg plugin (23.0+) is active, which provides the AI Client SDK.
Why it matters:
Other AI-powered plugins that use the WordPress AI Client (such as AI Experiments) can automatically discover and use any model you connect through this plugin. Configure your endpoint once and every AI feature on your site can use it.
How it works:
Install and activate the plugin.
Go to Settings > Connectors and configure the connector with your endpoint URL (e.g. http://localhost:11434/v1 for Ollama).
Optionally provide an API key for services that require authentication.
The plugin registers a provider with the WordPress AI Client and dynamically discovers all available models from your endpoint.
The plugin also handles practical concerns like extended HTTP timeouts for slow local inference and non-standard port support.
WordPress.org metadata
Plugin tags
Topics listed for this plugin in the WordPress.org directory.
local ai
connector
llm
ollama
Compatibility & maintenance
Compatibility & maintenance
Tested with WP 7.1
Marked as tested with the current WordPress 7.1 release.
Current WordPress releaseWordPress 7.1
WordPress.org Tested up to7.1
Minimum requirementsWordPress 6.9 · PHP 7.4
Update activity10 Sept 20261mo ago
“Tested up to” is directory metadata supplied by the plugin author. WP PlugIndex does not turn an older declaration into a claim that the plugin is incompatible.
Changes recorded by WP PlugIndex
Recent tracked changes
Version2.2.0→2.2.1
Version2.1.3→2.2.0
Tracking & source
WP PlugIndex tracks public WordPress.org directory metadata and records selected version, compatibility and availability changes as they are detected.
