Open-source document extraction with JSON output and MCP support
thisguyknowsai · x · 2026-07-20
Unstract’s open-source OCR/document-extraction stack turns documents into structured JSON without per-vendor templates, annotation, or model training.
It supports messy inputs such as invoices, contracts, bank statements, scans, handwriting, and images. The output can be deployed as a REST API or ETL pipeline, and it works with OpenAI, Claude, Gemini, Mistral, or local Ollama. It also ships with an MCP server for direct use in AI agents. The repo is AGPL-3.0 licensed and has 6.7k stars.
More from coding & agent
- Devin adds e2b sandboxes for remote agent execution — badphilosopher · 2026-07-22
- Hermes Agent Refactoring Proposal: Decoupling via Event Bus and Monorepo Slicing — Promptmethus · 2026-07-22
- ty now reads Pydantic config keywords and field metadata — charliermarsh · 2026-07-22
- Pensar Launches AI Security Agent to Autonomously Discover and Patch 0-Days — andriy_mulyar · 2026-07-22
- ty adds first-class Pydantic support, including strict and lax field handling — charliermarsh · 2026-07-22
- Google launches Gemini 3.5 Flash Cyber for CodeMender, with limited access for governments — GoogleAI · 2026-07-22