vudsen/ai-disk-cleaner

An AI-powered intelligent disk cleanup assistant; 一款 AI 驱动的智能磁盘清理助手。

What it solves

It simplifies disk cleanup by using an AI assistant to identify and summarize junk files that can be safely removed, reducing the manual effort of hunting for unnecessary data.

How it works

The tool follows a three-step process: first, it uses gdu to scan a specific location and load the file tree into memory. Second, it exposes a file tree reading tool to an LLM, which scans the file tree to find trash files and marks them using an add_trash_file tool. Finally, it combines these AI analysis results and presents them to the user.

Who it’s for

Windows users who want an intelligent way to manage disk space and move files to other drives.

Highlights

  • Intelligent LLM analysis to identify removable junk files.
  • Centralized management of symbolic links for one-click file migration to other drives.

Related

  • Project
    dynamiqs/dynamiqs

    A GPU-accelerated and differentiable Python library for high-performance simulation of quantum systems, designed for large-scale problems and gradient-based parameter estimation.

  • Project
    brycewang-stanford/StatsPAI

    A Python-native toolkit for applied causal inference and econometrics that replaces the need to switch between Stata and R for empirical research workflows.

  • Project
    DocAILab/XRAG

    XRAG is an open‑source Python framework that benchmarks the individual components of Retrieval‑Augmented Generation (RAG) pipelines. It offers modular plug‑ins for retrievers, embeddings, LLMs, and orchestrators, supports traditional IR metrics plus LLM‑based quality scores, provides a CLI (`xrag-cli`) and a Web UI, and can run as a REST service. Install via PyPI, configure with `config.toml`, and use commands like `xrag-cli run`, `xrag-cli webui`, or `xrag-cli api` to evaluate or serve RAG systems.

  • Project
    cavalab/srbench

    A living benchmark for symbolic regression that provides a unified framework and reproducible results to compare modern SR methods across diverse datasets.