axoviq-ai

axoviq-ai / synthadoc

Public

Synthadoc is a domain-agnostic LLM knowledge compilation engine. It reads raw source documents and uses an LLM to synthesize them into a persistent structured wiki. Knowledge is compiled at ingest time - not at query time. The compiled wiki lives as plain Markdown files that are readable/editable, self-managed and improved without any tool running.

17
3
100% credibility
Found Apr 16, 2026 at 21 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Synthadoc builds a self-maintaining Markdown wiki from diverse documents using AI agents for synthesis, contradiction detection, and Obsidian integration.

How It Works

1
🔍 Discover Synthadoc

You hear about a smart way to turn your scattered documents into a living knowledge notebook that stays organized and accurate on its own.

2
📦 Set up your notebook

With a few simple steps, you create a personal notebook folder ready for your notes and files.

3
🤖 Connect a thinking helper

Link a free or paid AI service so it can read and organize your information smartly.

4
📄 Feed in your files

Drop PDFs, spreadsheets, images, or web links into your notebook, and watch it automatically create linked pages, spot conflicts, and build connections.

5
💬 Ask questions

Chat with your notebook in plain English to get answers with clear sources and links to related ideas.

6
🔍 Review and improve

See flags for conflicting info or lonely pages, fix them easily, and keep everything fresh.

Your smart notebook thrives

Your knowledge grows smarter over time, browsable offline in your favorite note app, always accurate and connected.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 21 to 17 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is synthadoc?

Synthadoc is a domain-agnostic Python engine that ingests raw documents like PDFs, spreadsheets, and web pages, using an LLM to compile them into a persistent structured wiki at ingest time. The resulting knowledge lives as plain Markdown files in a self-contained folder—readable, editable, and improved without any server running. Unlike query-time retrieval, it builds cross-references and surfaces contradictions upfront.

Why is it gaining traction?

It stands out by pre-compiling knowledge into a browsable wiki graph with wikilinks, orphan detection, and auto-resolutions, beating typical RAG tools on accuracy and offline access. Local-first design with multi-LLM support (Gemini free tier to Ollama), CLI commands, HTTP API, and Obsidian plugin make it dead simple to run. Three-layer caching keeps costs near-zero on repeats.

Who should use this?

Solo researchers building personal wikis from papers and sites; small teams centralizing messy docs into a unified knowledge base; enterprises needing compliant, local-only storage with audit trails for regulated domains like finance or legal.

Verdict

Early v0.1 with 17 stars and 1.0% credibility score means watch for stability, but comprehensive docs, tests, and demos make it worth a spin for Python devs tired of RAG hallucinations. Install a demo wiki and ingest your docs—solid foundation for custom knowledge compilation.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.