lumi

Lumi is a Desktop App that offers a collection of tools to create, edit and share digital content with your class.

The LUMI AI Guide is designed to assist users in migrating their machine learning applications from smaller-scale computing environments to the LUMI supercomputer.

Routes white keys from midi-input to chosen scale to midi output

Open-source phase-field crystal (PFC) and phase-field solver: MPI + HeFFTe spectral and finite-difference kernels on CPU, CUDA and HIP, from a laptop to LUMI

Control Lumi Keys from the browser

Self-hosted H5P player component. No H5P server, Moodle or WordPress. Plays offline, streams video, supports xAPI, H5P into SCORM and VS Code.

Luma AI

xOS public beta: its own operating system, on its own compiled kernel, with Lumi, a local AI that runs on your machine. The g37 image is withdrawn while it is rebuilt; a ready-made xOS stick is at xseed.ing/xOS/Hardware.

This repository documents how to build and run LAMMPS with the pair_symmetrix interface for MACE-based machine learning interatomic potentials on the LUMI supercomputer using AMD MI250X GPUs.

Calm VS Code coding companion — Plan/Act modes, approval-gated tools, governed parallel subagents (projection + durable receipts), MCP, BroccoliDB memory.

xAPI Cohort team to discuss and work on H5P and xAPI (both hosted and standalone)

🌱 An AI learning OS that grows inside your Cursor. 住在 Cursor 里的学习小团子 · lumi — 35 个 Cursor Skill 拼成的 AI 学习操作系统，从"学什么"到"讲清楚"再到"考出来"。

A short guide to running JAX code on the GPU nodes of LUMI supercomputer.

FakeInventories library for Lumi servers

Lumi (Local Understanding & Model Interface): a beginner-friendly local AI helper for Ollama, Codex and Claude Code

A Telegram bot powered by aiogram integrated with a local LLM (LM Studio). Responds to messages, remembers chat history, and speaks in different moods. Triggered by the name “Lumi”.

This repository documents how to build and run LAMMPS with the native PKG_ML-MACE interface for MACE machine learning force field simulations on the LUMI supercomputer using a single AMD MI250X GPU.

PoC for running quntum jobs from your laptop to Quantum Backends accessible on HPC via FirecREST

Portable, host-neutral architecture steering, policy, orchestration, and agent-context primitives for AI agents.