Libraries tagged by llama.cpp

The package enables the use of the LLama C++ library in PHP, thereby allowing the setup and execution of LLM models in PHP on your local machine.

Go to Download

Local LLMs for Laravel through OpenAI-compatible APIs (Ollama, vLLM, LM Studio, llama.cpp): providers and purpose routes in the database with fallback, versioned prompt templates, structured output validated against a JSON schema, a call log with pruning, token quotas, a process-engine effect and a test fake.

Go to Download

Лёгкий PHP SDK для агентов с вызовом инструментов поверх OpenAI-совместимых API (DeepSeek, OpenAI, OpenRouter, Ollama, llama.cpp)

Go to Download

Laravel package for on-device / local language models (MLX, Ollama, LM Studio, llama.cpp, vLLM)

Go to Download

PHP extension for running GGUF models via llama.cpp

Go to Download

PHP 8.3+ native, in-process LLM inference and embeddings via llama.cpp.

Go to Download

llama.cpp models inside the PHP process through FFI, and OCRonos-Vintage OCR correction on top of it. No HTTP, no Python.

Go to Download

Linux binary library for llama.cpp packaged as composer dependency

Go to Download

llama-cpp adapter for PHP lang chain

Go to Download

Use llama.cpp, run Phi3-mini.

Go to Download

Viceroy: An LLM interactions library with an OpenAI compatible completion endpoint via PHP.

Go to Download

PHP bridge to llama.cpp for local and remote LLM inference — no Python service required.

Go to Download

Deterministic high-precision VRAM, GQA KV-Cache, MoE memory bandwidth, and llama.cpp layer offloading profiler for 2026 AI models and silicon.

Go to Download

Provider-agnostic AI client for Laravel, Slim 4, and standalone PHP. Extends Laravel's HTTP client via macros with support for OpenAI, Anthropic, Gemini, Groq, OpenRouter, Ollama, and llama.cpp. Includes tool calling, skills, agents, multi-agent orchestration, and MCP server/client.

Go to Download

LlamaParse-Client für Laravel

Go to Download