SiYuan
Privacy-first personal knowledge management system, listed as integrating Jev for document classification and tag routing.
Overview
SiYuan is a privacy-first, self-hostable personal knowledge management system with block-level editing, available as desktop and mobile apps, Docker, Kubernetes and other hosting options, and licensed AGPLv3. Its README covers installation channels, a CLI, data storage and sync FAQs.
The fetched README does not mention Jev. A directory listing describes native Jev decision-model integration for fast document classification, flashcard intent categorisation and automated tag routing. If present, that would use typed choices to file notes and cards rather than generative summaries. Treat the integration claim as unverified from the README.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Which category or tag should this document get?(inferred) | — |
| Choice | What is the intent of this flashcard?(inferred) | — |
How it works
- Create or import a note
- Ask Jev to classify it and suggest tags
- Route the note or card accordingly
Strengths
- Mature, widely used knowledge base
- Typed classification instead of generated text, per the listing
Caveats
- Jev integration not mentioned in the fetched README
- AGPLv3 licence
At a glance
- Type
- Plugin
- Status
- production
- Language
- TypeScript
- Runtime
- Desktop/mobile app, Docker
- Has code
- yes
- License
- AGPL-3.0
Use cases and integrations
How curated lists describe it
Knowledge management: privacy-first personal knowledge management system featuring native Jev decision model integration for high-speed document classification, flashcard intent categorization, and automated tag routing.
yibie/awesome-jev
Frequently asked questions
Does SiYuan use Jev?
A directory listing says so; the fetched README does not mention it.
What would Jev decide?
Document categories, flashcard intents and tags, per the listing.
Is SiYuan open source?
Yes, under AGPLv3.
Related projects
Go terminal app that files documents using five Jev questions: category, sensitivity, urgency, whether action is needed and action state.
ProjectbetaGoCalibre plugin that asks Jev yes/no questions to suggest genre and subject tags for books, with per-tag thresholds and review.
PluginbetaPythonObsidian plugin that ranks existing vault folders and tags for the active note with Jev and only moves or tags after you confirm.
ProjectbetaTypeScriptLLM-maintained Markdown wiki where a System One classifier decides where documents and questions go, keeping it fast as it grows.
ServicebetaPythonDocker service that classifies the Paperless-ngx inbox with Jev (or local Clef via Ollama), setting confident fields and queueing the rest.
ProjectbetamacOS menu-bar link router that opens each link in the right browser profile, asking Jev when no local rule matches and learning rules.
ProjectbetaSwift