Use local LLMs to organize your files
Hi everyone, Just wanted to share a use case where local LLMs are genuinely helpful for daily workflows: file organization. I've been working on a C++ desktop app called AI File Sorter – it uses local LLMs via `llama.cpp` to help organize messy folders like `Downloads` or `Desktop`. Not sort files into folders solely based on extension or filename patterns, but based on what each file actually is supposed to do or does. Basically: what would normally take me a great deal of time for dragging and sorting can now be done in a few. It's cross-platform (Windows/macOS/Linux), and fully…
What it does
In the maker’s words, at launch
Hi everyone, Just wanted to share a use case where local LLMs are genuinely helpful for daily workflows: file organization. I've been working on a C++ desktop app called AI File Sorter – it uses local LLMs via `llama.cpp` to help organize messy folders like `Downloads` or `Desktop`. Not sort files into folders solely based on extension or filename patterns, but based on what each file actually is supposed to do or does. Basically: what would normally take me a great deal of time for dragging and sorting can now be done in a few. It's cross-platform (Windows/macOS/Linux), and fully open-source. [GitHub repo](https://github.com/hyperfield/ai-file-sorter) [Screenshot 1](https://i.imgur.com/HlEer13.png) - LLM selection and download [Screenshot 2](https://i.imgur.com/KCxk6Io.png) - Select a folder to scan [Screenshot 3](https://i.imgur.com/QTUG5KB.png) - Review, edit and confirm or continue later You can download the installer for Windows in [Releases](https://github.com/hyperfield/ai-file-sorter/releases) or the Standalone ZIP from the [app's website](https://filesorter.app/download/). Installers for Linux and macOS are coming up. You can, however, easily [build the app from source](https://github.com/hyperfield/ai-file-sorter/blob/main/READM...) for Linux or macOS. --- ### How it works 1. You choose which model you want the app to interface with. The app will download the model for you. You can switch models later on. 2. You point the app at a folder, and it feeds a prompt to the model. 3. It then suggests folder categories like `Operating Systems / Linux distributions`, `Programming / Scripts`, `Images / Logos`, etc. You can review and approve before anything is moved, and you can continue the same sorting session later from where you left off. Models tested: - LLaMa 3 (3B) - Mistral (7B) - With CUDA / OpenCL / OpenBLAS support - Other GPU back-ends can also be enabled on `llama.cpp` compile --- ### Try it out * Windows: [SourceForge](https://sourceforge.net/projects/ai-file-sorter/) or [GitHub Releases](https://github.com/hyperfield/ai-file-sorter/releases) * Linux/macOS: build from source (instructions in the [README](https://github.com/hyperfield/ai-file-sorter/blob/main/READM...)) --- I’d love feedback from others using local models, especially around: - Speed and accuracy in categorizing files - Model suggestions that might be more efficient than Mistral/LLaMa - Any totally different way to approach this problem? - Is this local LLM use case actually useful to you or people like you, or should the app shift its focus? Thanks for reading!
Does the same job
all alternatives →
- CACreate and Maintain Filesystem Structures for LLMs [v1.0.11 Out]Jun 2026 · pypi.org · ▲5
More ai this month
the category →
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
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, July 2025
the whole month →
Trickle - Magic Canvas ▲1,064The 1st Agentic Canvas for building apps visually with AI
AI · 2025 · trickle.so
- TB
Life & fun · 2025 · trytender.app
- TY
Today marks ten years, 3653 consecutive days, of running at least one mile every day under the USRSA rules [1]. To celebrate, I built an interactive dashboard that turns a decade of GPX files into charts you can explore. Running has truly changed my life: I've made lifelong friends, explored beautiful places, and more importantly invested into my own health and fitness, which I'm starting to see the positive benefits as I get older. The stack is pretty simple: a NextJS app, with a Postgres database to keep all my running data, and all the stats are pre-computed and cached in Redis, so I…
Dev tools · 2025 · nodaysoff.run
- DA
Made this website as an exercise in vibe-coding and GCP. It was posted about a few times around the internet, on sites like Morning Brew (https://www.morningbrew.com/issues/business-buzzkill), MetaFilter (https://www.metafilter.com/209703/Draw-A-Fish), boingboing.net, etc. I think it's cute! I built a basic CNN trained against penises and swastikas, and then anything that doesn't hit the 63% confidence score gets sent to a mod queue, a vibe-coded fish-tinder…
Dev tools · 2025 · drawafish.com
