Search...Search plugins and themes...
⌘K
Sign in
  • Get started
  • Download
  • Pricing
  • Enterprise
  • Account
  • Obsidian
  • Overview
  • Sync
  • Publish
  • Canvas
  • Mobile
  • Web Clipper
  • CLI
  • Learn
  • Help
  • Developers
  • Changelog
  • About
  • Roadmap
  • Blog
  • Resources
  • System status
  • License overview
  • Terms of service
  • Privacy policy
  • Security
  • Community
  • Plugins
  • Themes
  • Discord
  • Forum / 中文论坛
  • Merch store
  • Brand guidelines
Follow us
DiscordTwitterBlueskyThreadsMastodonYouTubeGitHub
© 2026 Obsidian

Auto Tagger (Jev)

ParthParth106 downloads

Suggests or applies a tag to the current note using TypeSafe's Jev model and your vault's existing tags.

Add to Obsidian
  • Overview
  • Scorecard
  • Updates1

An Obsidian plugin that suggests or applies a tag to the currently open note using TypeSafe's Jev model and the tags that already exist in your vault.

Install it from the Obsidian community store.

How it works

  1. Run Auto-tag current note from the command palette, or click the tag ribbon icon.
  2. The plugin reads the note title and the start of its body, and collects your most-used vault tags.
  3. It asks Jev a single Choice question: which tag best matches this note. The candidate list includes a literal None of these fit well option.
  4. The chosen tag is applied (unless "None of these fit well" won), and a notification shows the tag and the model's confidence so you can build an intuition for your own vault before trusting any threshold.

Applying tags

  • If the note already has frontmatter, the tag is added to its tags list.
  • Otherwise an inline #tag is appended to the end of the note.
  • Tags the note already has are never duplicated.

Settings

  • TypeSafe API key — required. Stored locally in your vault, never logged.
  • Tags to consider — how many of your most-used tags to send (1 to 25, default 15). Sending fewer, higher-signal options improves the model's discrimination.
  • Note body characters — how much of the note to send, taken from the start (default 2000).
  • Dry run — show the suggested tag without changing the note.
  • Developer mode — log the raw Jev response (tag, confidence, and full probability distribution) to the developer console.

Privacy

  • When you run Auto-tag current note, the plugin sends the note title, the first Note body characters of the note, and the candidate tag names to TypeSafe (https://api.typesafe.ai/v1/systemone) using the Jev model. No other vault content is read or transmitted.
  • This happens only when you explicitly trigger the command or ribbon icon. The plugin makes no automatic or background network calls.
  • Your TypeSafe API key is stored locally in the vault's plugin data file and is used only as the bearer credential for that request. It is never logged.
  • The plugin collects no telemetry and sends no data to any service other than TypeSafe.

Development

npm install
npm run dev     # watch build
npm run build   # type-check and production build
npm run lint    # eslint

Copy main.js and manifest.json into <Vault>/.obsidian/plugins/auto-tagger-jev/ and enable the plugin in Settings → Community plugins.

HealthExcellent
ReviewPassed
About
Suggest a tag for the current note using the Jev model and your vault's most-used tags. Read the note title and start of the body, propose a best-fit tag (or "None of these fit well"), apply it to frontmatter or append an inline tag, and show the model's confidence.
AITags
Details
Current version
0.1.0
Last updated
3 weeks ago
Created
3 weeks ago
Updates
1 release
Downloads
106
Compatible with
Obsidian 1.13.0+
Platforms
Desktop, Mobile
License
MIT
Report bugRequest featureReport plugin
Sponsor
GitHub Sponsors
Author
ParthParthparthsidpara
parths.me
GitHubparthsidpara
XParthTw
  1. Community
  2. Plugins
  3. AI
  4. Auto Tagger (Jev)

Related plugins

Tars

Text generation based on tag suggestions, using Claude, OpenAI, Ollama, Kimi, Doubao, Qwen, Zhipu, DeepSeek, QianFan & more.

Copilot

Run AI agents such as Claude Code, Codex, and OpenCode inside your vault. Turn your second brain into a smart assistant that gets knowledge work done.

Claudian

Embeds Claude Code/Codex and other local Agents as AI collaborators in your vault.

Smart Connections

Find related notes and excerpts while writing. Your AI link building copilot displays relevant content in graph + list view. A local embedding model powers semantic search. Zero setup. No API key.

Fast Note Sync

Real-time sync of your vaults across server, mobile, and web; shareable with anyone; supports REST and MCP integrations to build your personal AI knowledge base.

Tag Wrangler

Rename, merge, toggle, and search tags from the tag pane.

ChatGPT MD

A seamless integration of ChatGPT, OpenRouter.ai and local LLMs via Ollama into your notes.

Supercharged Links

Add attributes to internal links with the values of target note's frontmatter attributes.

Karpathy LLM Wiki

Karpathy's LLM Wiki implementation plugin for Obsidian - turns notes and PDFs into a linked, LLM-powered knowledge base with entity pages, concept pages, graph-powered Q&A, and local-first privacy.

Checklist

Consolidate checklists across all files into a single view.