I Used Too Much AI, So Now It Names My Files

Description and use

LazyRename uses a local Ollama model to suggest descriptive filenames, providing a preview, collision checks, and undo functionality.

Problem

Renaming many files manually is tedious and error‑prone.

Outcome

The tool reduces manual renaming effort, offering a preview and undo, while ensuring no filename collisions or overwrites.

Workflow

• Scan folder for supported file types
• Read up to 3 PDF pages or 64 KB of text, limit to 4,500 characters
• Send excerpt to installed Ollama model for a short filename suggestion
• Display table of old and suggested names
• Allow user to edit or deselect rows
• Require confirmation before enabling rename button
• Apply renames, preserving original folder and extension
• Log transaction in JSON
• Provide undo for latest batch

Evidence

LazyRename does the reading. It scans a local folder for PDF, TXT, MD, and PY files, then asks an installed Ollama model for a short filename based on each file's contents.

Source

It keeps each file in its original folder and preserves its extension. It also checks Windows filename rules and collisions, writes a JSON transaction log, and offers an undo button for the latest batch.

Source

The model gets a bounded excerpt of the file's contents, with no original filename in the prompt. LazyRename reads up to three PDF pages or 64 KB of a text file and sends no more than 4,500 characters to Ollama.

Source

The transaction log records the moves so Undo can check the paths again before restoring them. If the original name is occupied or a renamed file has changed, Undo stops instead of overwriting it.

Source