Numo
Numo is an early-stage language-learning assistant designed around local-first intelligence. The project explores adaptive study loops, persistent learner state, and multimodal AI workflows where speech and generation can run fully local, while still allowing online providers for faster inference when needed.
About This Project
Building a trustworthy language-learning engine where progress, evidence, and pacing are real and not just simulated UI states.
Designed a persistence-first architecture with runtime orchestration and progressive learning flows, integrating local AI components for speech and generation.
Established a strong foundation for a private, adaptive assistant with local inference options and flexible online fallback for performance.
AI Systems & Desktop Developer
2026
Public
Personal
Technology Stack
Project Story
Building a trustworthy language-learning engine where progress, evidence, and pacing are real and not just simulated UI states.
Designed a persistence-first architecture with runtime orchestration and progressive learning flows, integrating local AI components for speech and generation.
Established a strong foundation for a private, adaptive assistant with local inference options and flexible online fallback for performance.
Insights & Takeaways
Highlights
- Local-first by design with explicit truth-path and persistence focus.
- Supports progressive journey logic instead of one-size-fits-all study flow.
Challenges
- Converging multiple runtime and persistence paths into one reliable source of truth.
- Keeping heavy AI workflows practical on desktop hardware in early-stage iterations.
Lessons Learned
- For learning products, data integrity and progression logic are as critical as model quality.
Related Work
Case Study
Academia Plus
C++ Qt prototype simulating students, teachers, courses and exams in a school management system.
Case Study
Auto Shutdown
Rust + React desktop app to automate PC shutdowns by timer, schedule or idle state.
Case Study
Azkari
Lightweight desktop app that displays Azkar reminders based on time of day — built with Tauri, SolidJS, TypeScript and Rust.
