LLPhant

An open-source PHP AI framework connects Symfony and Laravel apps to local models through Ollama and LM Studio, or to cloud model APIs.

LLPhant is a PHP framework for developers adding AI capabilities to Symfony and Laravel applications. It supports local model services and cloud providers, so you can choose where model requests run.

Local model connections: Connect applications to Ollama, llmman or LM Studio, or use OpenAI-compatible services such as LocalAI.
Cloud providers: Use OpenAI, Anthropic, Mistral, Atlas Cloud or Heabsy through the same framework.
Typed classification: The Jev integration supports Noul and Choice questions, plus rubric-based Score questions, and returns input and output token usage with answers.
Prompt injection detection: A Jev classifier can check queries for malicious prompt injections within the QuestionAnswering workflow.

LLPhant is open source under the MIT license and requires PHP 8.1 or later. Local model connections let you use services on your own hardware; cloud connections send requests to the selected provider. Jev classification and its prompt injection detection require access to the Jev API and an API key.

LLM Libraries and SDKs RAG Frameworks and Pipelines LM Studio integration Ollama integration OpenAI-compatible API RAG