songzhuozhu

songzhuozhu / obsidian-llm-wiki

Public

Turn your LLM into a wiki maintainer. Inspired by Karpathy's LLM Wiki. Built for Obsidian, Claude Code & Codex. | 让 LLM 成为你的 wiki 维护者。受 Karpathy 的 LLM Wiki 启发。面向 Obsidian、Claude Code 和 Codex 构建。

16
6
100% credibility
Found Apr 16, 2026 at 16 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
AI Summary

Obsidian workflow template that uses AI to transform raw documents like web clippings into a structured, evolving wiki with sources, entities, concepts, and syntheses.

How It Works

1
💡 Discover Smart Wiki Building

You hear about a clever way to turn web articles and notes into a living, organized personal knowledge collection using AI help.

2
📂 Set Up in Your Note App

Copy the ready folders into your Obsidian collection and rename a couple to match your setup.

3
🔗 Add Web Saving Tool

Get a simple browser clipper that drops web pages right into your incoming materials folder.

4
✂️ Clip Your First Article

Save an interesting webpage, and it appears ready in your raw notes area.

5
🤖 AI Builds Wiki Pages

Tell your AI helper to digest the article, and it creates neat pages for facts, people, ideas, and big-picture summaries.

6
🔍 Review and Approve

Look over the new pages to ensure they capture everything right, then approve to safely store the original.

7
❓ Ask and Grow It

Pose questions to your wiki for smart answers from your collection, and add valuable insights back in.

📚 Own a Thriving Knowledge Base

Celebrate your ever-improving, connected wiki that makes sense of all your saved info over time.

Sign up to see the full architecture

6 more

Sign Up Free

Star Growth

See how this repo grew from 16 to 16 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 obsidian-llm-wiki?

This Obsidian template turns your LLM into a wiki maintainer, inspired by Karpathy's LLM Wiki idea. Drop web clips or docs into a raw folder, and use Claude or Codex agents to ingest them into a structured wiki with sources, entities, concepts, and synthesis pages—complete with review gates before archiving. It shifts you from single-turn LLM queries to a multi-turn LLM workflow where knowledge compounds over time, built around Obsidian Markdown and agent commands like ingest_raw, query_wiki, and lint_wiki.

Why is it gaining traction?

Unlike basic RAG setups that reprocess docs every query, this enforces a living wiki with user-approved updates, relationship links, and health checks for stale claims—making multi-turn LLM evaluation feel reliable. Developers dig the Obsidian-native graph (via plugins like Dataview), batch ingests for related files, and prompts optimized for Claude/Codex, turning raw notes into a browsable knowledge graph without starting over. It's a smart hook for anyone tired of ephemeral LLM chats.

Who should use this?

Obsidian power users clipping articles or transcripts who want LLM help organizing research without losing context. Knowledge workers building personal wikis from web content, or devs prototyping multi-turn LLM benchmarks on real docs. Ideal if you're already using Claude in Obsidian via Claudian and need to turn website clippings into structured notes.

Verdict

Early alpha with 16 stars and 1.0% credibility—docs are solid and bilingual, but expect tweaks for scale. Grab it if you're an Obsidian tinkerer testing LLM-powered PKM; skip for production until more battle-tested.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.