Lapis0x0/obsidian-yolo

Lapis0x0/obsidian-yolo has 1,390 GitHub stars and 94 forks. GitHot measured +1 stars in 24 hours and +4 in 7 days. Last checked 2026-11-11 21:27 UTC. Last push 2026-11-02.

How these counts are measured

Agent-native AI assistant — chat, write, whiteboard, learning, all in one.

1,390 stars 94 forks +1 in 24h

What you can do

A Complete Agent Experience | Use Codex / Claude Code Inside Obsidian - Turn Vault Knowledge into Lasting Mastery
YOLO Whiteboard | A High-Performance Obsidian Canvas
For now, think of it as an Obsidian Canvas several to dozens of times faster. More features that push the boundaries of AI and human thinking are on the way.
🖥️ CLI Agent (Desktop) - Reuse a supported locally signed-in CLI agent, including Claude Code, Codex, Hermes, Pi, and Grok, right inside Obsidian

Measured star growth

in 24h: +1
in 7 days: +4
in 15 days: Update delayed
in 1 month: Update delayed

Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.

documentation/en/README.md

Original

YOLO documentation

简体中文 · English · Italiano

YOLO is an Obsidian plugin that puts an AI assistant inside your vault: chat with your notes, let it read and write files directly, search your whole knowledge base, complete and rewrite text right in the editor, and extend it with full-blown modules such as Learning and Whiteboard.

Start here

Just installed the plugin? Read these three in order and you'll be up and running:

Getting started — install it, configure a model that actually works, have your first chat
Models and providers — connect OpenAI / Claude / Gemini and friends, sign in with OAuth, and what each "default model" slot is responsible for
Chat — everything the chat surface can do: mentioning notes, the Ask and Agent modes, tool approval, writing changes back into your notes

Everyday use

Sparkle — AI without leaving the editor: the Quick Ask panel, tab completion, selection rewrites, continuation
Knowledge base and search — index your vault so answers are grounded, manage multiple knowledge bases, and use a local embedding model that needs no API key
Tools and permissions — what YOLO can do to your vault, how approval works, and how to confine it to a specific folder

Make it understand you

Memory — let YOLO remember your preferences and long-term context across chats
Agents and subagents — configure dedicated assistants for different situations, and hand big tasks off to subagents
Skills — teach YOLO to do things your way with a single Markdown file

Going further

MCP — plug in external MCP servers, and expose YOLO's vault search to other agents
CLI Agent — drive Claude Code, Codex and others that are already signed in on your desktop machine
Modules — the module system, plus how to use the Learning and Whiteboard modules

Reference

Settings reference — every item on the six settings tabs, one by one
FAQ — error troubleshooting and the questions people ask most

About this documentation

This documentation is written and continuously maintained by Claude, based on what the current code actually does.

The upside is that it covers plenty of details buried deep in the settings that nobody would normally write down; the risk is that machines make mistakes too, especially with negative claims like "feature X doesn't support scenario Y". When the documentation and the interface disagree, the interface wins — and please open an issue to tell us. A wrong doc deserves fixing just as much as a broken feature.

If you finish a section and still don't know what to click, that's worth reporting too.

If you'd like to contribute to development, see CONTRIBUTING.md.