OXR: Open-Source Doc Parsing Model Trained with an RSI Loop for Agent-Friendly Output
rohanpaul_ai · x · 2026-10-21
The SoMark team open-sourced OXR (Optical Everything Recognition), a document parsing model that converts PDFs and document images into Agent-friendly Markdown or JSON complete with layout coordinates.
Key points:
- Pretrained from scratch, with a recursive self-improvement (RSI) loop during post-training; the team claims SOTA accuracy and speed
- Offers an online demo and a free API
- Repo ships Docker deployment, example config, and tests, with English and Chinese READMEs
- Early-stage project (9 stars, 13 commits)
Worth a look for developers wiring documents into agent workflows.
Related event: Open-Source 1.3B Model OXR Tops Document Parsing Benchmarks(4 posts)→
More from coding & agent
- A simple context hygiene trick for Claude Code: audit CLAUDE.md with claude-md-management — daniel_mac8 · 2026-10-21
- Laude Institute backs WaggleHaus, an open-source query engine for agentic queries over data lakes — lateinteraction · 2026-10-21
- komorama's weekly: the AI Peter Principle—first 90% never faster, second 90% never slower — lennysan · 2026-10-21
- Orchestrating open-source video models with Opus 5.5 cuts costs ~80x vs Seedance — mickeyxfriedman · 2026-10-21
- Multi-agent swarm architectures are being discovered, not designed — shared state emerges as the norm — JensHonack · 2026-10-21
- UC Berkeley open-sources SkyDiscover, an AI framework that discovers algorithms — CShorten30 · 2026-10-21