superdoc/docx-editor

SuperDoc - Build AI agents that work with DOCX (DOCX Editor, DOCX Agent SDK)

What it solves

SuperDoc provides a way to render and edit DOCX files directly in the browser without converting them to HTML. It solves the problem of maintaining document structure (like pagination, headers, and footers) during editing and ensures that changes are written back to the original XML format.

How it works

It uses an OOXML-backed document model that reads files progressively and renders bounded windows. This allows it to function without a browser DOM and synchronize content and package state through a single collaboration model. It provides a unified Document API available via browser, Node.js, Python, CLI, and an MCP server.

Who it’s for

It is designed for developers building browser-based document editors, as well as those creating AI agents that need to programmatically manipulate DOCX files using high-level operations rather than raw XML.

Highlights

  • DOCX-native editing: Edits are written directly to the XML, preserving pagination, sections, and tables.
  • Agent-ready: Provides a structured API for AI agents to perform document operations.
  • Collaborative: Supports suggestions, comments, track changes, and real-time collaboration via Yjs.
  • Multi-language support: Includes SDKs for Node.js and Python, a CLI, and an MCP server.

Related

  • Project
    officecli/officedex

    An AI-native desktop platform that generates native Word, PowerPoint, and Excel files directly from natural language prompts, eliminating manual formatting.

  • Dispatch
    docx-cli: High-Fidelity Word Document Editing for AI Agents

    docx-cli is a CLI tool that enables AI agents to read, edit, and comment on .docx files using stable locators and in-place XML mutation, reducing token usage by over 50% compared to raw OOXML manipulation.

  • Project
    fluffypony/dothething

    Dothething (dtt) is a locally‑run AI agent that takes a plain‑English task, plans the work, and executes it using LLM‑driven tool calls (search via SearXNG, privacy‑focused browser automation, file/shell actions, email, clipboard, etc.). It supports three modes—Normal (cheap fast models), Advanced (strongest models), and Quick (single‑shot fast model). Installation is a one‑line script that sets up a Python venv, SearXNG, and the Notte/Camoufox browser. The tool tracks token usage and cost via OpenRouter and offers extensive CLI flags for model overrides, session resumption, browser session reuse, orchestration, and notifications.

  • Dispatch
    OfficeCLI: An AI-Native Office Suite for Document Automation

    OfficeCLI is an open-source, single-binary tool that allows AI agents to read, edit, and automate Microsoft Word, Excel, and PowerPoint files without requiring a Microsoft Office installation.

  • Project
    agent0ai/dox

    A lightweight framework using a hierarchy of AGENTS.md files to give AI agents precise project context and prevent blind edits during coding.