Composable building blocks to build Llama Apps

a script to run docker-compose.yml using podman

RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of …

InstructLab Core package. Use this to chat with a model and execute the InstructLab workflow to train a model using custom taxonomy data.

Atomic Run Tool for installing/running/managing container images.

A container for deploying bootable container images.

Repository for Ansible content that can include playbooks, roles, modules, and plugins for use with the Podman tool

Taxonomy tree that will allow you to create models tuned with your data

selinux-policy for Fedora is a large patch off the mainline

Examples for building and running LLM services and applications locally with Podman

Shortnames project is collecting registry alias names for shortnames to fully specified container image names.

An external provider for Llama Stack allowing for the use of RamaLama for inference.

An experimental RAG framework.

Variant of CentOS core with just a minimal "yum -y install" in C

python bindings for the Kubernetes Container Runtime Interface (CRI) gRPC

Project Atomic's very own GitHub CI service.