Jev in production › Model and agent routing
Local proxy for Claude Code and Codex sends each new task to Jev in one request for a capability tier and per-model reasoning effort with confidence; a user-editable policy maps the answers to a model and pins it for the conversation.

Open-source model and reasoning effort routing for coding agents. Automatic model selection for Claude Code and Codex.
Website · Get started · How it works · Customize your policy · Contribute
Switchboard automatically selects a model and reasoning effort for Claude Code and Codex. Jev or experimental self-hosted Laya assesses the task; your routing policy makes the final choice. It runs inside the coding CLI you already use, keeping the selected pair fixed through follow-ups, tool calls, and resume.
For the project's own README, linking back here: