Chloe
Permission-aware AI assistant for Windows PC control.
What it does
Chloe is a lightweight, permission-aware AI assistant for Windows that can interact with your desktop, files, apps, browser, terminal, and more. Instead of allowing an AI model to control your computer directly, Chloe uses structured actions, safety checks, and permission gates to keep automation controlled. Built as an open-source project for exploring safer, practical personal AI assistants.
Contribute to raviicodess/Chloe- development by creating an account on GitHub.
A lightweight, permission-aware personal AI assistant for Windows. Chloe is an online-LLM-driven desktop assistant that can operate your computer — windows, keyboard, mouse, files, processes, terminal, browser, code projects and git — but only through a programmatic safety gate. The LLM never controls the machine directly: every action is classified, permission-checked, bounded, verified and audited. Designed for low-end hardware (tested on a 4 GB RAM laptop). The core (text chat + agent + memory) is UI-free and provider-agnostic; the desktop shell is plainfrom github.com
Does the same job
all alternatives →
More dev tools this month
the category →
Open-source GTM skills for technical founders
Dev tools · 29d ago · gtmcofounder.com
OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 2d ago · opentrailpaper.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com