landing-ai/ade-cli

The official CLI for Agentic Document Extraction (ADE) by LandingAI — parse documents and extract schema-shaped data from your terminal

What it solves

Agentic Document Extraction (ADE) simplifies the process of turning complex documents—including those with tables, figures, and charts—into structured data. It solves the problem of accurately extracting specific fields from documents while providing clear evidence (page and box coordinates) for where that data was found.

How it works

The tool operates in a two-step process: first, ade parse converts a document into grounded Markdown and elements. Second, ade extract uses a provided schema to pull specific fields from that parsed data. The CLI saves results to a local store (~/.ade), ensuring that identical commands do not consume additional API credits.

Who it’s for

This is designed for developers and AI agents. It provides a stable JSON output for all commands, making it easy to integrate into automated workflows or agentic harnesses.

Highlights

  • Grounded Extraction: Extracts data with page-and-box evidence for every field.
  • Complex Document Support: Handles tables, figures, and charts effectively.
  • Cachable Results: Local storage prevents redundant API calls and credit consumption.
  • Agent-Ready: Includes a --json flag for stable, machine-readable output and a dedicated agent contract (SKILL.md).
  • Visual Verification: Includes a view command to open an HTML viewer showing the source of extracted values.

Related

  • Project
    landing-ai/ade-python

    A Python library for the LandingAI ADE API that parses PDFs and images into structured Markdown and extracts typed fields using Pydantic models.

  • Project
    yusukebe/ax

    A command-line tool designed for AI agents to fetch, discover, and extract structured data from the web, replacing the need for fragile parsing scripts and raw HTML dumps.

  • Project
    virgiliojr94/book-to-skill

    A Python tool that converts PDFs, EPUBs, DOCX, Markdown, etc., into an Agent‑Skill bundle (SKILL.md + per‑chapter markdown files). The skill can be loaded by Copilot CLI, Amp, Claude Code, letting the LLM answer questions from the original book on‑demand while using 24‑51× fewer tokens than feeding the whole book as context.

  • Project
    docling-project/docling

    Docling is a document processing tool that parses diverse formats like PDF, DOCX, and images into structured formats like Markdown or JSON for use in generative AI ecosystems.

  • Project
    docling-project/docling-graph

    A toolkit that transforms unstructured documents into validated Pydantic objects and directed knowledge graphs for high-precision entity relationship extraction.