Self-Hosted Plaform for Secure Execution of Untrusted User/AI Code

RamaLama web site.

Real-time webcam demo with SmolVLM and llama.cpp server

Run RamaLama as part of your Llama Stack

Use the OpenRouter API to automatically write a git commit message

🍻 Default formulae for the missing package manager for macOS (or Linux)

Model swapping for llama.cpp (or any local OpenAPI compatible server)

Composable building blocks to build Llama Apps

aider is AI pair programming in your terminal

Tools using Small Large Language Models

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

https://docs.openwebui.com

Tool to convert Go Templates to Jinja2 Templates

Location for shared common files in github.com/containers repos.

A small self-contained alternative to readline and libedit

Redis is an in-memory database that persists on disk. The data model is key-value, but many different kind of values are supported: Strings, Lists, Sets, Sorted Sets, Hashes, Streams, HyperLogLogs,…

lightweight, standalone C++ inference engine for Google's Gemma models.

Stable Diffusion and Flux in pure C/C++

Podman: A tool for managing OCI containers and pods.

The goal of ramalama is to make working with AI boring.

Port of OpenAI's Whisper model in C/C++

OCI Artifact for ML model & metadata