OmniParse: Open-Source Tool to Convert 20+ Formats to Markdown
tom_doerr · x · 2026-08-07
OmniParse is an open-source platform that ingests and parses unstructured data—such as documents, multimedia, and web pages—into structured, high-quality Markdown optimized for GenAI applications like RAG and fine-tuning.
Key Features:
- Completely local execution with no external APIs
- Supports 20 file types
- Capabilities include table extraction, image captioning, and audio/video transcription
- Hardware friendly, fitting on a single T4 GPU
- Deployable via Docker with an interactive Gradio UI
More from coding & agent
- Reverse Engineering Super Smash Bros. Melee into C on a Phone via DeepSeek — pvncher · 2026-08-07
- Is Claude Code Enough? Dev Questions Value of New AI Subscription Tools — MaxLenormand · 2026-08-07
- Noether: Open-Source Tool to Automatically Prove Math Properties of JAX Code in Lean — jonkhler · 2026-08-07
- AI Agent Architecture: Lazy-Load Files, Subagents as Tool Calls — yacineMTB · 2026-08-07
- LabyrinthBench: Measuring Agent Context Recall Shows Wiping History Wins — jwdeaver · 2026-08-07
- HermesBox: A 24/7 Jetson-Powered Local MCP Server for Persistent Agents — Trevi4ko69 · 2026-08-07