SANE - Smart AI Note Evolution

unlisted

by Adam Chen

Evolve your notes intelligently with AI. When you add/edit notes, SANE finds the 3 most relevant notes and enhances them with smart tags, keywords, links, and summaries.

★ 2 starsUpdated 1mo agoMIT
View on GitHub

SANE — Smart AI Note Evolution

Official Website | Full Documentation

An Obsidian plugin that automatically enhances your notes using AI. When you add or edit a note, SANE finds the most relevant notes in your vault and enriches them with tags, keywords, links, and summaries via YAML frontmatter.

Features

  • Multiple AI providers — OpenAI, Google AI, Grok, Azure OpenAI, and local LLMs (Ollama)
  • Semantic similarity — finds related notes using embeddings, not keyword matching
  • Related notes panel — browse similar notes and likely duplicates from an Obsidian sidebar
  • Flexible triggers — process immediately, after a delay, on a schedule, or manually
  • Targeted scope — limit processing to a specific folder
  • Cost controls — daily budget limits and real-time cost tracking
  • Reversible — all generated fields are prefixed with sane_ and can be removed at any time

Quick Start

  1. Install — search for "SANE" in Obsidian Community Plugins (or install manually from GitHub releases)
  2. Configure — choose an AI provider and add your API key in Settings > SANE
  3. Set scope — specify a target folder to limit which notes are processed (recommended)
  4. Initialize — run "Initialize all notes" to process your existing notes
  5. Write — SANE processes notes automatically as you add or edit them

Example Output

SANE adds frontmatter to the top of processed notes:

sane_tags: ["machine-learning", "neural-networks"]
sane_keywords: ["backpropagation", "training data"]
sane_links: ["[[Introduction to AI]]", "[[Neural Network Basics]]"]
sane_summary: "A guide to understanding neural networks and their applications."
sane_version: "1.0"
sane_created_at: "2025-05-05T11:59:11.000Z"
sane_modified_at: "2025-06-29T04:15:12.000Z"

Your original note content is never modified.

Documentation

Full usage documentation, configuration reference, and local LLM setup guide are available at the project documentation site.

Support

License

MIT

For plugin developers

Search results and similarity scores are powered by semantic analysis of your plugin's README. If your plugin isn't appearing for searches you'd expect, try updating your README to clearly describe your plugin's purpose, features, and use cases.