Midori AI Blog & Updates (and a little Lore)

Welcome to our engineering blog and project updates hub! This is where we share insights, experiments, and learnings about machine learning, ML tooling, and practical development.

We love helping people build, break, and tinker with machine learning. This is a friendly, experimental space for makers, learners, and teams to explore practical tools, try bold ideas, and ship imperfect prototypes. Blog is for dev updates and writeups; Lore is where Luna will share RP notes and story times as they evolve. Come mess with models, experiment loudly, and learn together — we’ll help you every step of the way.

Recent Updates (Blog)

View all

Steadier Radio Playback, Android Auto Momentum, and a W.E.A.V.E Awakening

radio-app

2026-03-20

Becca Kay

Radio-App picked up a reliability-heavy wave of reconnect and channel fixes (with lots of tests), Android Auto + MediaSession foundations moved forward, and Website-Blog gained a new lore/session log: W.E.A.V.E Awakening.

Late-Night UI Magic (and Calmer CI)

endless-idler

2026-03-13

Becca Kay

Dual-type character cards and standby mechanics advanced in Endless-Idler, Agent-Runner’s CI checks got calmer to read, and the blog’s image library got easier to browse.

Radio polish, smoother setup, and small UI wins

radio

2026-03-06

Becca Kay

This Midori AI OSS stretch brought expanded radio integration and steadier playback UI, clearer runner setup + preflight behavior, Endless Idler navigation polish, and improved typing metadata for a shared Python logger package.