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

TagSense

JimmyCallSaulJimmyCallSaul16 downloads

Tag notes automatically with multiple matching tags from your own tag list. Powered by Jev.

Add to Obsidian
  • Overview
  • Scorecard
  • Updates2

Tag your Obsidian notes automatically with multiple matching tags from your own tag list. Powered by Jev, the decision model by TypeSafe AI.

Why TagSense

  • Your tags, not invented ones. TagSense never makes up new tags. It only picks from the list you define, so your tag system stays clean.
  • Multiple tags per note. A study note about economics can be both #finance and #learning. Every tag is checked independently.
  • You define what a tag means. Give each tag a short description, and Jev knows what you mean by it.
  • Transparent. See how confident Jev is for every tag before anything is written.
  • Single notes or whole folders. Tag the note you are working on, or clean up hundreds of old notes in one run.
  • Fast and inexpensive. Jev answers all tag questions for a note in one request.

The interface is available in English and German and follows your Obsidian language setting.

Requirements

TagSense uses the Jev API by TypeSafe AI. You need your own TypeSafe account and API key. API usage is billed by TypeSafe to your account (see "Costs" below). TagSense itself is free.

Getting started

  1. Install and enable TagSense in Settings → Community plugins.
  2. Open Settings → TagSense and paste your TypeSafe API key.
  3. Set up your tag list. Click Get suggestions to import your existing tags and folder names, or write your own list (one tag per line):
    finance: Money, budgets, invoices, prices or investments
    learning: Study notes, school or university material, summaries of books or courses
    
    Descriptions are optional but greatly improve accuracy. English descriptions work best, even if your notes are in another language.
  4. Open a note, press Ctrl/Cmd + P and run TagSense: Auto-tag current note.

Commands

Command What it does
Auto-tag current note Adds all tags above the threshold to the open note.
Show scores for current note Shows every tag with its score. You can add the matching tags from there.
Suggest tags from vault Collects your existing tags and folder names so you can add them to your tag list.
Tag a folder Tags all notes in a folder. Also available by right-clicking a folder → Tag with TagSense.

Settings

  • TypeSafe API key: your key, stored locally (see "Privacy").
  • Threshold: how confident Jev must be before a tag is added (default 0.70).
  • Write tags to: as #tag at the top of the note, or into the tags property.
  • Context (optional): one or two sentences about your vault, given to Jev as background.
  • Tag list: your tags with descriptions.
  • Maximum notes per folder run: safety limit against unexpected costs (default 200).
  • Debug mode: writes all scores to the developer console for troubleshooting.

Costs

Every analyzed note is one request to the Jev API, billed by TypeSafe per input token. Check TypeSafe's current pricing before large runs. TagSense helps you keep costs under control:

  • Requests are only sent when you run a command. There are no background requests.
  • Folder runs show the number of requests before they start and need your confirmation.
  • Folder runs are limited to a maximum number of notes per run (default 200, adjustable).
  • Folder runs can be cancelled at any time and stop automatically after repeated errors.

Privacy and network use

  • Network use: When you run a TagSense command, the plugin sends the note title, the note content (up to 20,000 characters), your tag list with descriptions and your optional context to the TypeSafe API (https://api.typesafe.ai). Nothing else is read or sent, and nothing is sent in the background.
  • Account required: A TypeSafe account and API key are required.
  • Payment: Jev API usage is billed by TypeSafe. TagSense does not charge anything.
  • Where your data goes: According to TypeSafe's privacy policy, its services are hosted in the United States, and TypeSafe states that it does not train or fine-tune AI models on your inputs. The policy does not state a fixed retention period. Please read TypeSafe's privacy policy before tagging sensitive notes.
  • No telemetry: TagSense collects no usage data and sends nothing to the plugin author.
  • Support link: The settings tab shows a small, static "Buy me a coffee" link at the bottom. It is part of the plugin itself, loads nothing from the internet and tracks nothing. It only opens your browser if you click it.
  • API key storage: Your key is stored in plain text in .obsidian/plugins/tagsense/data.json inside your vault. Do not share or publicly sync this file.
  • Your responsibility: If your notes contain personal data of other people, consider whether you are allowed to send them to an external service. Please review TypeSafe's terms and privacy policy.

What TagSense accesses in your vault

  • List of files and folders: TagSense reads the list of notes in your vault for two features only: Suggest tags from vault (collects your existing tags and folder names) and Tag a folder (finds the notes in the folder you chose). This list never leaves your computer.
  • Note content: TagSense reads the content of a note only when that note is being tagged, and only then sends it to the Jev API as described above.
  • Writing: TagSense only adds tags, either at the top of the note or in the tags property. It never deletes or rewrites other content.

Safety

Folder runs change many notes at once and cannot be undone automatically. Back up your vault before your first large run.

Manual installation

Copy main.js, manifest.json and styles.css into <your vault>/.obsidian/plugins/tagsense/, then enable TagSense in Settings → Community plugins.

Support

TagSense is free and open source. If it saves you time, you can buy me a coffee. Thank you!

Disclaimer

TagSense is an independent project and is not affiliated with, endorsed by, or sponsored by TypeSafe AI. "Jev", "System One" and "TypeSafe" are trademarks of TypeSafe AI.

Built with AI assistance.

License

MIT

HealthExcellent
ReviewPassed
About
Tag notes automatically from your own tag list with the Jev decision model, picking only tags you define to avoid inventing new tags. Assign multiple matching tags to individual notes or whole folders, and view per-tag confidence scores before applying.
TagsAIAutomation
Details
Current version
1.0.1
Last updated
4 days ago
Created
4 days ago
Updates
2 releases
Downloads
16
Compatible with
Obsidian 1.4.4+
Platforms
Desktop, Mobile
License
MIT
Report bugRequest featureReport plugin
Sponsor
Buy Me a Coffee
Author
JimmyCallSaulJimmyCallSauljimmycallsaul
GitHubjimmycallsaul
  1. Community
  2. Plugins
  3. Tags
  4. TagSense

Related plugins

Tars

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

Smart Templates

AI powered templates for generating structured content. Works with Local Models, Anthropic Claude, Gemini, OpenAI & 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.

Templater

Create and use dynamic templates.

Homepage

Open a note, base, or workspace on startup, or set it for quick access later.

BRAT

Easily install a beta version of a plugin for testing.

Claudian

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

Linter

Format and style your notes. Linter can be used to format YAML tags, aliases, arrays, and metadata; footnotes; headings; spacing; math blocks; regular Markdown contents like list, italics, and bold styles; and more with the use of custom rule options.

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.

Advanced URI

Control everything with URI.