PHP download

Download the PHP package chubes4/ai-http-client without Composer

On this page you can find all versions of the php package chubes4/ai-http-client. It is possible to download/install these versions without Composer. Possible dependencies are resolved automatically.

Table of contents
Download chubes4/ai-http-client
More information about chubes4/ai-http-client
Files in chubes4/ai-http-client

Vendor chubes4
Package ai-http-client
Short Description A professional WordPress library for unified AI provider communication. Supports OpenAI, Anthropic, Google Gemini, Grok, and OpenRouter with standardized request/response formats.
License GPL-3.0-or-later
Homepage https://github.com/chubes4/ai-http-client

Keywords wordpress ai http-client artificial-intelligence Gemini grok openai anthropic OpenRouter

FAQ

After the download, you have to make one include require_once('vendor/autoload.php');. After that you have to import the classes with use statements.

Example:

If you use only one package a project is not needed. But if you use more then one package, without a project it is not possible to import the classes with use statements.

In general, it is recommended to use always a project to download your libraries. In an application normally there is more than one library needed.

Some PHP packages are not free to download and because of that hosted in private repositories. In this case some credentials are needed to access such packages. Please use the auth.json textarea to insert credentials, if a package is coming from a private repository. You can look here for more information.

Some hosting areas are not accessible by a terminal or SSH. Then it is not possible to use Composer.
To use Composer is sometimes complicated. Especially for beginners.
Composer needs much resources. Sometimes they are not available on a simple webspace.
If you are using private repositories you don't need to share your credentials. You can set up everything on our site and then you provide a simple download link to your team member.
Simplify your Composer build process. Use our own command line tool to download the vendor folder as binary. This makes your build process faster and you don't need to expose your credentials for private repositories.

Please rate this library. Is it a good library?

Example code of chubes4/ai-http-client

Informations about the package ai-http-client

AI HTTP Client for WordPress

Archived: This package is superseded by WordPress core's wp-ai-client APIs. Data Machine no longer uses this runtime dependency; provider/model/key administration and image generation have moved to wp-ai-client-shaped capabilities. This repository remains available for historical reference only and should not be used for new work.

A professional WordPress library for unified AI provider communication. Supports OpenAI, Anthropic, Google Gemini, Grok, and OpenRouter with standardized request/response formats.

Key Features:

WordPress filter-based architecture with self-contained provider classes
Unified request/response format across all AI providers
Comprehensive caching system with 24-hour model cache TTL
Multi-modal support (text, images, files) via native Files API integration
Streaming and standard request modes with proper error handling
REST API endpoints for configuration and management
Multisite network-wide API key storage support
Comprehensive error handling with WordPress action hooks

Installation

Composer (recommended for standalone use):

Git Subtree (recommended for plugin embedding):

Manual Installation: Download and include in your WordPress plugin or theme

Requirements: PHP 7.4+, WordPress environment

Upgrading from v1.x to v2.0

Breaking Changes: All filter/action hooks renamed from ai_* to chubes_ai_* for WordPress.org compliance.

Automatic Migration

API keys are automatically migrated on first admin page load:

Old option: ai_http_shared_api_keys
New option: chubes_ai_http_shared_api_keys
Old option deleted after 30 days

Hook Migration

Update all references in your code:

See docs/CHANGELOG.md for complete migration details.

Usage

Include Library:

Basic Request:

Advanced Options:

Providers

Comprehensive AI provider support with dynamic model discovery:

OpenAI - GPT models, OpenAI Responses API, streaming, function calling, native Files API integration
Anthropic - Claude models, streaming, function calling, native Files API integration with vision support
Google Gemini - Gemini models, streaming, function calling, native Files API integration with vision support
Grok/X.AI - Grok models, streaming support
OpenRouter - 200+ models via unified API gateway

Architecture

Filter-Based: WordPress-native provider registration via chubes_ai_providers filter
Self-Contained: Each provider handles format conversion internally (standard ↔ provider format)
Unified Interface: All providers accept standard format, return normalized responses
WordPress-Native: Uses wpremote* for HTTP, WordPress transients for caching
Modular Design: Provider files self-register, no central coordination needed
Error Handling: Comprehensive error hook via chubes_ai_library_error action
Performance: 24-hour model caching with granular cache clearing

Multi-Plugin Support

Plugin-isolated configurations via filter-based settings
Centralized API key storage in chubes_ai_http_shared_api_keys option
Multisite network-wide API key storage support
No provider conflicts through self-contained architecture
Independent AI settings per consuming plugin

Core Components

Providers: Self-contained classes with unified interface (OpenAI, Anthropic, Gemini, Grok, OpenRouter)
Request Processing: Complete pipeline via chubes_ai_request filter with error handling
HTTP Layer: Centralized chubes_ai_http filter supporting streaming and standard requests
Caching System: Model caching via AIHttpCache class with WordPress transients
REST API: Configuration and management endpoints via ai_http_client namespace
Error Management: Centralized logging via AIHttpError class

Core Filters

REST API Endpoints

The library provides REST API endpoints for configuration and management:

Available Endpoints:

GET/POST /wp-json/ai-http-client/v1/api-keys/{provider} - Get/set API key for specific provider
GET /wp-json/ai-http-client/v1/models/{provider} - Get available models for a provider
GET /wp-json/ai-http-client/v1/providers - List all available providers

Multi-Plugin Configuration

Shared API Keys Storage:

Provider Configuration:

AI Tools System

Tool Registration:

Tool Discovery and Usage:

Distribution

Packagist: Available via composer require chubes4/ai-http-client
GitHub: https://github.com/chubes4/ai-http-client
Version: 2.0.7 - Professional WordPress library with BaseProvider architecture
License: GNU GPL v3
Dependencies: None (pure WordPress integration)
Multi-plugin: Safe for concurrent use by multiple WordPress plugins

Adding Providers

Version 2.0.0 Features

WordPress.org Compliance:

All filter/action hooks renamed from ai_* to chubes_ai_* prefix
Automatic migration system for API keys and settings
Backward compatibility migration for 30-day rollback window

Core Architecture:

WordPress filter-based provider registration with self-contained classes
Unified request/response format across all providers
Comprehensive caching system with 24-hour model cache TTL
Native Files API integration for multi-modal content (text, images, files)
Streaming and standard request modes with proper error handling
REST API endpoints for configuration and management
Multisite network-wide API key storage support

AI Provider Support:

OpenAI Responses API integration with native Files API support
Anthropic Claude models with dynamic model discovery and native Files API
Google Gemini with native Files API and multi-modal support
Grok/X.AI integration with streaming support
OpenRouter gateway access to 200+ models

WordPress Integration:

Native WordPress HTTP API usage with centralized chubes_ai_http filter
WordPress transients for model caching with granular cache clearing
WordPress options API for settings with multisite support
Comprehensive error handling via chubes_ai_library_error action hook

Production Usage

This library is actively used in production WordPress plugins:

Data Machine - AI-powered content processing pipelines with multi-provider support
WordSurf - AI content editor with streaming responses and function calling
AI Bot for bbPress - Forum AI responses with contextual conversation management

Debug

Debug Logging Covers:

HTTP request/response cycles via chubes_ai_http filter
Provider-specific API interactions
Model caching operations and cache hits/misses
Streaming request handling
Error conditions via chubes_ai_library_error action hook
File upload operations to provider APIs

Contributing

Pull requests welcome for:

Additional AI provider integrations
Performance optimizations and caching improvements
WordPress compatibility enhancements
Template component additions
Documentation improvements

License

GNU GPL v3 - Chris Huber

All versions of ai-http-client with dependencies

PHP Build Version

Package Version

Version v2.0.13 Release 31. Jan 2026
create-project require 0 people chose require and
0 people chose create-project.

Download

Download latest version of ai-http-client from vendor chubes4

Requires php Version >=7.4

Composer command for our command line client (download client) This client runs in each environment. You don't need a specific PHP version etc. The first 20 API calls are free. Standard composer command

The package chubes4/ai-http-client contains the following files

Loading the files please wait ...