GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

  • Sign in
  • ActionsCI/CD and automation
  • CodespacesCloud development environments
  • All Features
  • Documentation
  • Training
  • Certifications
  • Build with Copilot
  • Customize Copilot
  • Integrations
  • Trending repos
  • GitHub Sponsors
  • Developer articles
  • Enterprises

This view

  • Original page
  • New address

GeezerVison is showing github.com — GitHub - bitsandbots/fileforge: AI-powered file organizer using local Ollama inference

BranchesTags
Open more actions menu

Latest commit

 

History

75 Commits
75 Commits

Folders and files

NameName
Last commit message
Last commit date
docs
docs
 
 
frontend
frontend
 
 
scripts
scripts
 
 
src/fileforge
src/fileforge
 
 
templates
templates
 
 
tests
tests
 
 
.gitignore
.gitignore
 
 
AGENTS.md
AGENTS.md
 
 
CHANGELOG.md
CHANGELOG.md
 
 
CLAUDE.md
CLAUDE.md
 
 
LICENSE
LICENSE
 
 
README.md
README.md
 
 
fileforge.toml.example
fileforge.toml.example
 
 
pyproject.toml
pyproject.toml
 
 

Repository files navigation

FileForge

AI-powered file organizer using local Ollama inference — no cloud, no subscriptions.

Python 3.11+ License: MIT Status: Alpha

What it does

  • Scans directories and classifies files using local AI (Ollama) or rule-based heuristics
  • Detects duplicates by content hash and semantic similarity
  • Organizes files into category folders automatically
  • Automates with watch mode and scheduled scans
  • Runs offline — no data leaves your machine

Install

From PyPI (coming soon)

pip install fileforge

From source

git clone https://github.com/bitsandbots/fileforge.git
cd fileforge
bash scripts/install.sh

Requirements: Python 3.11+, Ollama (optional, for AI classification).

Quick start

# Pull required Ollama models
ollama pull qwen3:4b
ollama pull nomic-embed-text

# Scan a directory
fileforge scan ~/Documents

# Preview organization (dry-run)
fileforge organize ~/Downloads --dry-run

# Find duplicates
fileforge dupes ~/Documents

Commands

Command Description
fileforge scan <dirs> Scan and classify files
fileforge organize <dirs> Move files to categorized folders
fileforge dupes <dirs> Find and manage duplicates
fileforge watch <dirs> Monitor for changes
fileforge schedule <dirs> Schedule automated scans
fileforge status Show session info
fileforge server Start the web UI server

Run fileforge --help for full options.

Web UI

FileForge includes a web interface for visualizing scan results:

# Start the server (runs on http://localhost:8082)
fileforge server

# Development mode with auto-reload
fileforge server --reload

Run fileforge server --help for full options.

Background Automation

Watch mode

Monitor directories and scan on changes:

fileforge watch ~/Documents ~/Downloads --phase-2

Scheduled scans

Run daily scans automatically:

# Daily at 2 AM
fileforge schedule ~/Documents --cron "0 2 * * *"

# Or use systemd (Linux) — scan timer + web UI server
bash src/fileforge/systemd/install.sh           # both (default)
bash src/fileforge/systemd/install.sh --scan    # scan timer only
bash src/fileforge/systemd/install.sh --server  # web UI on http://127.0.0.1:8082

Configuration

Copy the example config and edit to suit:

cp fileforge.toml.example fileforge.toml

Create .forgeignore files in any directory to exclude patterns:

*.log
node_modules/
*.tmp

Development

bash scripts/install.sh       # editable install + dev deps
bash scripts/check.sh         # tests + lint + formatting
python -m pytest -q           # run tests

Documentation

  • Blueprint Overview — Single-page HTML reference (open in browser)
  • Overview — Project goals and capabilities
  • Architecture — Design and data flow
  • Setup Guide — Detailed installation and usage
  • Tech Stack — Dependencies and requirements
  • API Reference — Python API + REST endpoints
  • Gap Analysis — Known gaps between docs and code

License

MIT — see LICENSE.


A CoreConduit Consulting Services open-source tool. Issues and contributions welcome.

About

AI-powered file organizer using local Ollama inference

Topics

aiclideduplicationfile-organizationlocal-llmollamapython

Resources

Readme
MIT license
Activity

Stars

5 stars

Watchers

0 watching

Forks

0 forks
Report repository

Releases

Packages

Contributors

Languages

You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.