Your notes.
A living wiki.
Write in Obsidian. Every note connects to a network that keeps growing.
Nothing you read should go to waste.
Lose it, or grow it?
Save an article. Forget where. Search later. Nothing.
Drop it in sources/. Ideas found, pages built, summary ready. In seconds.
Link two notes by hand. One changes. The other stays old. The link dies.
Links stay alive. When new information contradicts the old, every related page stays current.
A year of notes. Just files. Every project starts over. Same reading. Same conclusions.
A year builds a wiki. Every new question draws on everything you've collected. Your knowledge grows.
From note to wiki
One note. A world of connections.
What changes
Not features. A new relationship with everything you read.
It just happens
Drop it in sources/. AI reads, extracts, builds. No folders. No tags. No work.
↓ (auto)
wiki/entities/...
wiki/concepts/...
Living links
Every page joins your Obsidian graph. Open Graph View — and watch your knowledge grow.
auto-linked
graph grows
Just talk
Ask like you would a friend. Your wiki answers with sources you can see and trust.
→ X + Y cited
→ saved as wiki page
Stays current
New files? Auto-ingested. Contradictions? Found. Health? Checked. On your terms.
lint: weekly
health check: startup
(default: OFF)
One click fixes everything
Causality-ordered batch fix: aliases → duplicates → dead links → orphans → empty pages. Five phases run in sequence with parallel processing.
3 duplicates · 2 dead links
→ Smart Fix All
one click, all resolved
Fine to coarse. You decide.
Control extraction depth per source. Standard for daily use, Fine for research, Coarse for quick overviews.
Fine deep extraction
Standard balanced
Coarse quick overview
Ready in minutes
Obsidian is all you need.
Install
In Obsidian: Settings → Community plugins → Browse, search Karpathy LLM Wiki, click Install then Enable.
Open Plugin PageConfigure
Settings → Karpathy LLM Wiki. Pick your LLM, enter key, test, save.
Use
Cmd+P (or Ctrl+P). Type Ingest to add sources. Type Query to ask.
Common questions
Everything you need to know to get started.
What does this plugin actually do?
Drop any note into your Obsidian vault. The AI extracts people, concepts, and theories, then auto-generates interlinked wiki pages with bidirectional links. Ask "what did I write about X?" — the answer comes from your own notes, not the internet.
What are the minimum requirements?
Obsidian v1.6.6+ (desktop: Windows, macOS, Linux) and an LLM provider API key. Supported: DeepSeek, Gemini, Claude, GPT, Kimi, GLM, OpenRouter, or custom. No API key needed for Ollama (local models).
Which model should I choose? How much will it cost?
Long-context models (1M tokens) recommended — they process your entire wiki in one pass. A single ingest costs $0.05–$0.50. All costs go to the LLM provider; the plugin itself is free and open source.
Can I use local models via Ollama?
Yes. Install Ollama, pull a model (e.g. qwen3.5), select Ollama (Local). No API key needed. Cloud providers recommended for ingestion (larger context); local models work well for query.
How do I get help or report bugs?
Use GitHub Issues for bug reports, GitHub Discussions for questions. Also find the plugin on the Obsidian Community Plugin page and leave a review.
Every plugin, amplified
Not an island. Every tool you love, now better.
Graph View
See links
Wiki gives your graph meaning. Hub pages, clusters, orphans. Exploration, not decoration.
Web Clipper
Save articles
Drop in sources/. AI extracts, links, updates. One clip becomes 10+ wiki pages.
Dataview
Query data
AI adds structure. Tags, dates, categories. Empty tables become living dashboards.
Git
Track versions
Watch your knowledge evolve. Every commit tells the story of how you grew.
Marp
Make slides
Ask: "Summarize my research for a 10-minute talk." Wiki builds slides from your knowledge.
Canvas
Visual canvas
AI builds concept maps, timelines, decision trees from your knowledge. No more blank canvas.
Built in the open
Open source. Your data stays yours.
Pure Obsidian
No extra apps. Lives entirely in your Obsidian.
Privacy First
No storage. No backend. No data collection. Your notes stay in your Obsidian—only sent to your LLM during ingest or query. Local models keep everything offline.
Long-context models (256K+) recommended. Your whole wiki in one call, complete understanding.
Works with any provider. No lock-in.