jev-cli (Nasrallah-AL)

Jev, TypeSafe's System One classifier, as a tool inside Claude Code, Codex, Pi, and OpenCode: typed classify, check, score, rank, and ask, plus one-command setup.

Filter command output for coding agents using a task description.

Jev decides. The LLM writes one line. Your project never forgets. Jev-powered memory layer for AI coding tools.

Vercel Labs terminal CLI that can run Jev as the evaluation model for its evaluate command.

Command-line tool for TypeSafe AI's Jev model. Ask yes/no, multiple-choice and rubric questions about any text and get calibrated probabilities back. Answers become exit codes for shells and CI, JSON for scripts, and MCP tools for AI agents.

Audit your git diff against YAML coding-standards packs using TypeSafe's Jev model, from a CLI or your AI agent's command/skill.

TypeScript CLI that finds code, docs, logs, and text by natural-language conditions using Jev Noul judgments, with probability thresholds, source lines, and cached results.

Experimental semantic line search with TypeSafe Jev via OpenRouter. Python CLI with no runtime dependencies.

CLI for TypeSafe AI's Jev evaluation model — typed questions in, structured JSON answers out