Back to directory

LLPhant

A PHP framework for building generative AI applications and retrieval-augmented search, compatible with Symfony and Laravel and inspired by LangChain.

LLPhant

LLPhant is a PHP library for building generative AI applications and working with vector databases, designed to be simple while still covering the tools a production app needs. It works with Symfony and Laravel, and supports a growing set of model providers including OpenAI, Anthropic, Mistral, Ollama, LM Studio, Atlas Cloud and other OpenAI-API-compatible services.

It also includes a typed classifier for structured yes-or-no, multiple-choice and rubric-scored questions, which reports its own input and output token usage. LLPhant installs through Composer and requires PHP 8.1 or later; its documentation covers retrieval-augmented generation and autonomous agents alongside the classifier.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.