Jev in production › Model and agent routing
MCP connector gives Claude Code, Codex and other agents typed access to Jev for routing and urgency decisions (System One Connector).
Give your AI agent direct access to models like Jev, CLM, Laya, and d1: quick decisions with real probabilities.
evaluate connects Claude Code, Claude Desktop, Codex, Hermes and pi to TypeSafe's Jev model. Your agent asks a question like "is this urgent?" or "which team owns this?" and gets back a number or an option it can use in an if statement.
Not tied to one provider: the same connector also runs other System One models, whether you host them yourself, such as CLM and Laya, or they're hosted for you, such as Liquid AI's d1. See running CLM locally and running d1.
For the project's own README, linking back here: