BigHugger
GH Repository · axoviq-ai

synthadoc

Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.

stars
1,214
30-day movement
+21/day
Related entries
60
Connections
1
pythonskill-packPythonsynthetic-dataagent-skillscli-toolobsidian-pluginagentic-aipkmsyntheticdomain-adaptationlocal-llmenterprise-solutionsenterpriseknowledge-graphobsidian-mdpersonal-knowledge-managementrag-alternative

Synthadoc is an open-source LLM knowledge compilation engine that converts raw documents into structured, local-first wikis. It is positioned as a transparent, human-readable alternative to traditional RAG, packaged as a Python CLI tool and skill pack with an Obsidian plugin.

You want document knowledge compiled into readable, self-managed wiki output instead of opaque retrieval pipelines.

Use it to

  • Compile raw documents into structured local wikis
  • Replace RAG with human-readable knowledge output
  • Integrate compiled knowledge into Obsidian
  • Adapt LLMs to a domain via synthetic knowledge
  • Run knowledge compilation locally with local LLMs

For Developers and teams building local, self-managed LLM knowledge bases

Role
skill-pack
Language
Python
Licence
AGPL-3.0
Forks
124
Open issues
4
Last push
2026-09-16
Latest release
v0.1.0 · 2026-04-15
topicsknowledge-compilationrag-alternativelocal-llmobsidianknowledge-graphcli-tool