synthadoc
Convert raw documents into a structured, locally-first wiki.
- Type
- Agent Skill
- Open source
- Yes
- GitHub Stars
- ★ 1.0k
- Source
- skill-github
- Repository
- github.com/axoviq-ai/synthadoc
Overview
Synthadoc is an open-source LLM knowledge compilation engine that transforms raw documents such as PDFs, spreadsheets, PPTs, web pages, images, videos, Word files, and AI chat logs into a structured, locally-first wiki. It offers a transparent and highly readable alternative that enables self-management and continuous improvement without relying on any external tools. Suitable for individuals, small teams, and large organizations, ensuring accuracy in knowledge bases as documentation accumulates. Outputs are stored as Markdown files, enabling seamless integration and autonomous management within Obsidian or other wiki-compatible ecosystems.
Capabilities
- ▪Supports multiple document formats
- ▪Automatically builds cross-references
- ▪Detects and flags contradictions
- ▪Marks isolated pages
- ▪Sources cited for every answer
Use cases
Setup
pip install synthadoc
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
What document formats does Synthadoc support?
PDFs, spreadsheets, PPTs, web pages, images, videos, Word files, and AI chat logs.
How do I install Synthadoc?
Install using pip: pip install synthadoc.
Related skills
im-not-ai
A tool for naturalizing AI-generated Korean text, removing translation-like and mechanical expressions.
skill-prompt-generator
AI portrait prompt generation system based on Claude Skill, supporting multiple domains and intelligent learning.
huashu-skills
Huashu's content creation skills collection, covering the complete workflow from topic selection to publication.
yichen-skills
A set of skills for creators, including writing, drafting articles, and managing WeChat digital assets.
qiaomu-anything-to-notebooklm
Multi-source content processor supporting various format conversions.
baoyu-skills
Baoyu Skills Suite enhances the efficiency of AI agents in generating and publishing content for daily work.