Download GClaude Indexer

GClaude Indexer processes entire folders of business documents into structured Markdown outputs that can be used directly in AI project contexts. Scanned PDFs, Office files and emails are converted into typed records with dates, authors and summaries. The resulting index and timeline provide a machine-readable overview of a document collection without modifying any original file. All processing stays on the local Windows machine unless the optional Claude Code engine is selected.

5.0(1 ratings)
Version: 1.3.0
Size: 7.77 MB
Systems: Windows

The program handles mixed document collections where some files contain embedded text and others require OCR. Pages without text layers are passed through Tesseract automatically, while oversized PDFs are divided into segments that preserve reading order. Classification can be performed by a deterministic rules engine, a local Ollama model or Claude Code. The output includes a review report listing every file that failed processing or produced incomplete metadata, allowing the user to verify the result before relying on it.

The installer configures Python 3.12, Tesseract, Ghostscript and Ollama on first run. No administrator rights are needed for the standard installation. The interface runs in a browser window at localhost and displays live graphs of CPU, RAM and GPU usage during execution. Projects can be shared across computers through a Google Drive folder. The uninstaller offers selective removal of components and never touches generated reports or original documents.

Scan folders recursively to inventory all documents Map entire directory tree before processing starts
Run OCR only on pages without text Speed up conversion by skipping searchable pages
Split large PDFs into logical readable chunks Break oversized files without cutting sentences
Extract text from Office and email formats Pull content from workbooks slides and messages
Classify content into typed structured items Assign type date author and summary automatically
Generate Markdown index with source links Create searchable catalog for documentation systems
Build chronological timeline from dated items Reveal document sequences and project phases
Produce review report listing gaps and failures Check quality before using processed output
Create AI workspace instructions in Markdown Let models answer questions without originals
Classify locally with Ollama open model Keep document text on your own machine