
FileFind — Ask Anything About Your Files
AI file search that never leaves your machine
What it does
FileFind is a local-first AI agent that lets you search your files using natural language. Instead of remembering filenames or digging through folders, just ask — "which resume is best for a data science role?" or "what contracts mention payment terms?" and FileFind reads, reasons, and finds exactly what you need. Everything runs 100% on your machine. No cloud, no API keys, no data ever sent anywhere. Your files stay yours. Built with Ollama + ChromaDB + Tauri.
Does a similar job
all alternatives →



- ZCzfind – CLI like find but using SQL syntax and also does tar/zip2024 · github.com · ▲122
I wrote this because I needed to search a lot of files, including some archives, for files in a date range but couldn't find any good tools. Also I never liked find's option syntax. I think most people already know SQL (or at least it's easier to learn) and a much better match for this task.

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 · 19d 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, March 2026
the whole month →

Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com


