siyuan

What Jev does in siyuan

The project describes itself this way: A self-hosted knowledge workspace whose AI settings added support for TypeSafe System One (Jev) decision models. In the Routing & Cost Optimization category, Jev typically decides the task type or difficulty, which local rules then map to a model or agent.

Verification

Verified. We confirmed this repository through the GitHub API and located the code that calls Jev at a pinned commit: view the Jev code ↗. Upstream code changes over time, so check that the file still exists at the current commit before citing it.

Topics

• agentic-ai
• ai-agent
• knowledge-base
• local-first
• markdown
• mcp
• note-taking
• self-hosted
• siyuan

How Routing & Cost Optimization projects use Jev

Routers that use Jev to classify a task before choosing which model, agent or effort level should handle it. Routing is one of the clearest early wins for Jev because it is cheap, frequent and easy to check.

Related Jev projects in Routing & Cost Optimization

1. agentscopeagentscope-ai/agentscopeAn agent framework with a built-in TypeSafe Jev classifier model for routing and classification steps.★ 32,338
   Python
2. inbox-zeroelie222/inbox-zeroAn open source email assistant whose rule-learning code includes a Jev integration for classifying senders and messages.★ 12,334
   TypeScript
3. openchamberopenchamber/openchamberOpenChamber’s optional automatic model router uses Jev to classify a message before selecting a configured model and reasoning level.★ 10,318
   TypeScript
4. firstmatekunchenguid/firstmateFirstmate can optionally use Jev to match task briefs to dispatch rules before local policy chooses an Agent configuration.★ 7,002
   Shell
5. pacaPaca-AI/pacaAn open source project-management tool with an optional Jev decision integration per project.★ 1,852
   Go
6. atomicbastani-inc/atomicAn optional Jev decision backend in the Atomic coding Agent for bounded structured choices such as routing.★ 814
   TypeScript

See all 16 Routing & Cost Optimization projects →

Where we found it

• yibie/awesome-jev