PAL
Currently in version 1 utilizing cloud services. Version 2 is actively being developed to support my main cause: utilizing local, uncensored, and private AI to tackle deep issues that I cannot risk sharing with big corporate APIs. PAL also heavily served as the foundational STT/TTS template for several of my other unannounced AI projects (like Numo).
About This Project
I needed a fast, reliable desktop AI assistant to talk to for answering questions and writing code, but quickly realized the privacy risk of sending sensitive data and deep issues to large corporate APIs.
Developed PAL as a high-speed Tauri/Rust launcher with global shortcuts. While V1 uses APIs, it laid the perfect groundwork for V2, architecting the framework to swap in completely local, private, and uncensored models.
Provided a powerful, customizable desktop assistant while acting as the core architectural template for integrating Speech-to-Text and Text-to-Speech in my future AI endeavors.
AI & Desktop Developer
2024
Public
Personal
Technology Stack
Project Story
I needed a fast, reliable desktop AI assistant to talk to for answering questions and writing code, but quickly realized the privacy risk of sending sensitive data and deep issues to large corporate APIs.
Developed PAL as a high-speed Tauri/Rust launcher with global shortcuts. While V1 uses APIs, it laid the perfect groundwork for V2, architecting the framework to swap in completely local, private, and uncensored models.
Provided a powerful, customizable desktop assistant while acting as the core architectural template for integrating Speech-to-Text and Text-to-Speech in my future AI endeavors.
Insights & Takeaways
Highlights
- Architected as a robust template, successfully powering the STT and TTS engines of my other unannounced projects (e.g., Numo).
- Paved the technical path for a fully private, local, and uncensored desktop intelligence ecosystem (V2).
Challenges
- Seamlessly integrating complex speech pipelines (Whisper and Piper) into a minimalist Rust/Tauri native desktop shell.
- Ensuring the architecture is sufficiently agnostic to swap from cloud models (V1) to heavy local LLMs (V2).
Lessons Learned
- Confirmed the fundamental importance of local, private AI when dealing with sensitive, uncensored questions.
Related Work
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.
Case Study
EBEC
A full-stack, highly creative web platform built for the ENSIA Business & Entrepreneurship Club, complete with an administration and user management system.
