Note Graph is a Joplin plugin that visualizes your notes as an interactive graph. It connects notes by the links and tags you already use, and by semantic similarity using Joplin's own built-in AI. This way you can see how your notes actually relate to each other, not just how they're filed. An optional second stage, LLM enrichment (Pass B), adds topic labels and one-line explanations for those connections.
- Explicit connections. Notes linked with
[text](:/noteId)or sharing a tag are connected automatically, no setup required. - Semantic connections. With Joplin AI enabled, the plugin embeds your notes and adds edges between notes that are related in content even when nothing links them. Tunable threshold and edge count.
- Optional LLM enrichment (Pass B). Labels each semantic connection with a one-line explanation of why it exists, using Joplin AI chat. Off by default.
- Community detection. Notes cluster into color-coded groups using the Louvain method, with a keyword-based fallback for small or sparse vaults.
- Centrality-scaled nodes. More connected notes render larger, so hubs stand out at a glance.
- Live updates. The graph updates as you edit, create, and delete notes, without a full rebuild, and catches up automatically after a sync.
- Built for large vaults. The plugin reads your whole vault in the background, but only draws what fits: a notebook, including nested ones, plus the notes in other notebooks that connect to it. Search reaches every note, and a note's connections can be widened with a depth slider. Layout runs away from Joplin's UI thread, so a large vault doesn't freeze the app.
- Local and instant. Embeddings, labels, and the last built graph are cached in a local SQLite database, so reopening the panel doesn't mean waiting again. Nothing is sent anywhere except to Joplin's own AI subsystem, and only when semantic analysis or LLM enrichment is on.
- A panel built for exploring, not just looking. Search, a depth slider, a tag filter, focus mode (isolate a note's neighborhood), per-edge-type toggles, zoom, and PNG/SVG/JSON export. It follows Joplin's theme and adapts down to a narrow panel.
- Side panel or popup. Keep the graph beside your notes, or open it in a large popup from the note toolbar when you only need it for a moment.
- Joplin desktop 3.5 or later.
- Joplin 3.7 or later with AI enabled (Configuration screen's AI page), if you want semantic connections or LLM enrichment. Everything else works without it.
- In Joplin, open the Configuration screen and go to the Plugins page.
- Use the search box to look for Note Graph.
- Press Install next to Note Graph.
- Restart Joplin when prompted to complete installation.
Build the plugin from source and install the resulting file:
npm install
npm run distThis produces a .jpl file under publish/. In Joplin, open the
Configuration screen's Plugins page, press the Plugin tools (gear)
button, choose Install from file, and select it. Restart Joplin after
installing an update.
Open it from the Tools menu: Show Note Graph. If your window has no room for a side panel, open the graph in a popup instead: press the graph icon in the note toolbar, or run Note Graph Popup from the Command Palette. Close the popup with its ✕ or Escape. The graph builds from your current notes, tags and links; if AI analysis is enabled in the plugin's settings, semantic edges are added once your notes are embedded. If LLM enrichment is also enabled, relationship labels appear on hover once Pass B finishes labeling them.
The note open in Joplin is highlighted, and the highlight follows as you move between notes. Click a node to open that note, or right-click it for more. Double-click to zoom in on it.
- Top of the panel: choose which notebooks to show, and search every note. Press Enter to open the top result, or Escape to clear the search. The status button on the right says what the plugin is doing; press it for details.
- Toolbar: turn links, similar notes and tags on or off, show only one tag, choose how notes are colored and arranged, focus on the selected note, or export the view.
- On the graph: zoom, and fit the graph to the panel.
- A note's connections: open them from a search result or the right-click menu, and use the depth slider to widen or narrow them.
Available in the Configuration screen's Note Graph section, which also explains how to open the popup:
| Setting | Default | Effect |
|---|---|---|
| Enable AI-based semantic analysis | Off | Adds semantic similarity edges using Joplin AI |
| Similarity threshold | 70% | Only the strongest (100 − value)% of candidate pairs become edges, ranked by how much closer two notes are than each usually is to its nearest notes. Lower values surface more semantic edges |
| Max semantic edges per note | 5 | Caps how many semantic connections each note keeps |
| Enable LLM analysis | Off | Adds Pass B relationship explanations |
| Retry AI embedding | Off | One-shot: re-runs AI-based semantic analysis, reusing cached embeddings |
| Retry AI labels | Off | One-shot: labels up to 200 more connections straight away; the rest are labeled in the background anyway |
Full details, including how the similarity score and Pass B labels are computed, are in docs/settings.md, docs/similarity-engine.md, and docs/llm-enrichment.md.
In-depth documentation lives in docs/: architecture,
the data pipeline, the similarity engine, the graph model, LLM enrichment
(Pass B), incremental updates, caching, development setup, and
troubleshooting.
npm install # also builds the plugin (npm run prepare)
npm test # run the test suite
npm run format # apply the project's Prettier configSee docs/development.md for the full build, test and project-layout reference.