Download the PHP package knackline/laravel-olm without Composer
On this page you can find all versions of the php package knackline/laravel-olm. It is possible to download/install these versions without Composer. Possible dependencies are resolved automatically.
FAQ
Example:
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 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.
Informations about the package laravel-olm
Laravel OLM
OLM (On-device Language Models) is a Laravel connector for local / on-device LLM backends: MLX, Ollama, LM Studio, llama.cpp, and vLLM.
Use one API in your Laravel app — switch backends with config.
Features
- Unified chat, completions, embeddings, and streaming
- Driver pattern (
Olm::driver('mlx')) like Laravel filesystem/mail - OpenAI-compatible HTTP for MLX, LM Studio, llama.cpp, and vLLM
- Ollama native model list / pull / show
- Publishable config and facade helper
Requirements
- PHP 8.1+ (8.3+ on Laravel 13)
- Laravel 9.x–13.x
- A running local inference server for the driver you choose
Installation
Publish the config:
Configuration
.env examples:
Backend setup
Ollama
Install Ollama, then:
MLX (Apple Silicon)
Default listen address is typically http://127.0.0.1:8080.
LM Studio
Start the local server in LM Studio (OpenAI-compatible API), usually http://127.0.0.1:1234.
llama.cpp
Run llama-server with an OpenAI-compatible HTTP API, e.g. port 8080.
vLLM
Local development
php artisan olm:serve starts the configured default driver backend (ollama serve, mlx_lm.server, llama-server, or vllm serve). If the backend is already healthy, the command keeps the process alive so it can sit in a concurrent dev stack.
Laravel 13+ (composer run dev / php artisan dev)
When Illuminate\Foundation\DevCommands is available, laravel-olm auto-registers process olm (php artisan olm:serve). Disable with:
Or in your app:
LM Studio is not registered (no CLI start path) — start its server in the LM Studio app.
Override the shell command per driver with serve in config (or OLM_*_SERVE env vars).
Older apps (npx concurrently in composer.json)
Append the OLM process to your existing dev script, for example:
Usage
Facade
Helper
Streaming
Embeddings & completions
Models & Ollama pull
Calling pull / show on drivers that do not support them throws UnsupportedOperationException.
Dependency injection
Roadmap
- Fine-tuning helpers / job stubs
- Richer multimodal (vision / audio) support
- Optional integrations (Laravel AI, Prism, etc.)
Testing
Contributing
See CONTRIBUTING.md.
License
MIT — see LICENSE.
All versions of laravel-olm with dependencies
illuminate/support Version ^9.0|^10.0|^11.0|^12.0|^13.0
illuminate/http Version ^9.0|^10.0|^11.0|^12.0|^13.0
illuminate/console Version ^9.0|^10.0|^11.0|^12.0|^13.0