# iyaja/llama-fs

A self-organizing file system with llama 3

Repository: https://github.com/iyaja/llama-fs
Canonical: https://ross.abutalabs.com/products/llama-fs
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2025-08-08T02:27:02+00:00

## Health v2 (maintenance only)
Score: 40/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 35, release rhythm 35, longevity 60
- inputs: {"age_days": 844, "days_push": 391, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5836, forks 385 (observed 2026-08-28T04:09:31.457708+00:00)

## What it is
LlamaFS is a self-organizing file manager that uses the Llama 3 model to automatically rename and organize files based on their content and conventions. It runs in batch mode for one-time directory organization and watch mode as an interactive daemon that learns from your renaming habits, with an incognito mode routing requests through Ollama for privacy.

## Use cases
- automatically organize my messy downloads folder
- rename files based on their content using AI
- watch a directory and auto-organize new files as I add them
- organize files locally without sending data to an API
- summarize and sort images and audio files automatically
- suggest a new folder structure for a directory

## When to choose
- you want AI-assisted automatic file organization and renaming
- you need privacy-conscious local inference via Ollama
- you want a daemon that learns your naming conventions over time
- you handle mixed media types including images and audio

## When to avoid
- you need a fully reliable, production-grade file system tool - LLM suggestions can be wrong
- you cannot run Python 3.10+ or a local LLM backend
- you want minimal resource usage - LLM inference adds overhead
- you need deterministic, rule-based organization rather than model-driven suggestions

## Facets
- artifact type: application
- maturity: active
- function: file-system, llm-inference, agent-framework, gui, caching
- domain: files, developer-tools, artificial-intelligence, large-language-models
- platform: python, cross-platform
- tags: file-organization, ollama, llama-3, self-organizing-filesystem, electron-app, whisper, moondream, privacy-mode, desktop, electron

## Member repositories
- iyaja/llama-fs (main) score 40

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:31.457708+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:52:03.642179+00:00, confidence not recorded.
  - readme: https://github.com/iyaja/llama-fs (fetched 2026-08-28T04:09:31.457708+00:00, sha 3f8ca36e5f14)
- Data as of 2026-08-30T08:39:29.467469+00:00.