CLUSTER CONVERTS-JSON-MARKDOWN · 5 ENTRIES · EARLIEST ENTRY 2025-02-19
Document to Markdown/JSON converters
This cluster consists of document parsing tools that convert PDFs, Office files, and scans into structured Markdown and JSON for downstream use. The cluster's dated history is too thin to read a shape from — only three pre-index entries exist, so it predates the index or members are undated. Traction leaders, all with zero stars, include Scholar-Agent, ParseAnything_DQ_P3, and python-mineru, indicating no dominant player yet.
Entry timeline
ENTRY TIMELINE
Each bar is the month a member carries, which is a creation date where the source published one and a crawl date otherwise. Nothing in the index was found before 11 August 2026, and coverage broadened sharply on 14–15 August, so a bar from then on reports how much we found that month, not how much was built; an earlier bar reports how far back a member's own source dated it — not how long we have been watching.
Members by activity
Activity signals, not revenue.
Build origin · 5 unlabelled
Operator · 2 hobby · 1 indie · 2 open source
Two labels per entry, never collapsed into one: how it was built, and who stands behind it. Counted over the 5 listed below. Unlabelled means nothing has decided yet — not that the answer is small.
- 01Scholar-Agent0★1 mo—hobbyBrowser-based tool that converts dissertation manuscripts from Word to LaTeX, checks formatting against university templates, and produces PDFs.
- 02ParseAnything_DQ_P30★13 days—hobbyDocument parser that converts PDFs, Office files, and scans into structured Markdown and JSON with per-block confidence and risk scores.
- 03python-mineru0★3 moliveopen sourceDocument parsing tool that converts PDFs, images, and Office files into Markdown and JSON for downstream use.
- 04Doc-To-API0★2 mo—indieWeb service that converts uploaded documents like PDFs into structured JSON via an AI-inferred schema and a REST API.
- 05python-marker-pdf0★1 yrabandonedliveopen sourceTool that converts PDF documents into Markdown and JSON formats with high accuracy.
Ranked by traction, highest first, and paged 20 at a time — this is a window on the cluster, never the whole of it. Ties are broken by a stable id so a product cannot appear on two pages or fall between them. Browse every cluster.