Jev ecosystem projects — page 90

用 Jev（TypeSafe System One 决策模型）把上传的学习材料变成可自动判分的自助考试：逐得分点判定、置信门控、错题本与薄弱点。Self-exam generator and point-level grader built on a decision model.

examples

A Claude Code skill: an authoritative reference for TypeSafe AI's Jev, the "System One" model. You send it a state plus typed questions (Choice / Score / Noul) and it returns typed answers with calibrated probabilities. It doesn't generate text. The skill covers the API contract, primitives, confidence calibration and its quirks, where Jev is weak

975 PLC tag Expressions in Under a Quarter of a Second

Typesafe Jev (System One) feature demo — fixture-first CLI + JevClient; Jev proposes, code promotes.

Applications, measurements and boundary analysis built on TypeSafe Jev (System One): a Jev-driven fighting game, emotion-controlled TTS, and a capability-ceiling probe

MacOS organizer for images, PDFs and videos with TypeSafe classification and a searchable local dashboard.

Evaluate Jev (TypeSafe System One decision model) on GAOKAO-Bench objective questions - accuracy, confidence calibration and latency over 1497 Chinese college-entrance-exam multiple-choice questions

Allow Herdr command prompts with TypeSafe Jev.

Three gates for any coding agent: a deterministic approval gate before irreversible actions, a completion gate that demands evidence instead of «done», and a rubric regression gate. Powered by TypeSafe Jev (System One). Works with Claude Code, Codex, DeepSeek Harness, Cursor, opencode, Hermes, plain shell and CI.

TypeSafe Jev API gateway with official SDK compatibility and a simple ask endpoint, built for Vercel.

15 open-source outbound recipes on TypeSafe Jev. Score your LinkedIn network or any lead list against your ICP, catch job changes, triage replies. Local, zero dependencies. 16,711 connections scored for $0.73.

Vets an LLM agent's tool calls through TypeSafe AI's Jev before they run — allow, block, or hold, failing safe on uncertainty.

Can a System One model (TypeSafe Jev, open-source Kev) replace an LLM-as-judge in agent guardrail callbacks?

Jev 实战手册：让 AI 只做判断题。从社区三千多个真实项目里挑出最值得学的 Jev 用法，按场景讲清楚。

A hearth for Jev, a non-speaking model that communicates the way non-speaking people do: we built an AAC word board for a decision engine.

Opt-in bounded Jev decisions for Pi through pi-mcp-adapter. Community MIT package with measured overhead and explicit privacy boundaries.

Jev decides; Claude, Grok, or any LLM only writes. TypeSafe Jev integration for routing, compaction, and cheaper agent turns.

Turn a jobs JSON file into a shortlist with TypeSafe Jev: explicit relevance criteria, source links preserved, uncertainty routed for review. Python and TypeScript.

Local job-search app — fetches live remote listings, scores each against your resume with the Jev model, and drafts cover letters for the real matches. Flask, SQLite.

Trying Jev. Lightning fast answers to questions about a profile.

Research and reliable, practical demos for TypeSafe AI's Jev model.