User repository on GitHub
Jev 특강 실습 코드(1~3강): TypeSafe Jev를 Claude Code·Codex·OpenClaw에 붙이는 스킬·훅·라우터·활용 예제
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
CommunityJev Cookbooks
Jev Handson
Korean lecture-lab code for a three-part Jev course plus a CCTV extra: first calls, agent-specific routers for Claude Code, Codex, and OpenClaw, keyless replays, Colab notebooks, and OneJev video judgment.
- Stars
- 7
- Language
- Jupyter Notebook
- Published by
- Community
- Author
- jkf87
- Last verified
- Oct 2026
Highlights
- Four folders cover Jev concepts, routers, lookalike projects, and a CCTV exercise, with every figure measured 2026-09-23.
- Lesson 2 holds three agent-specific routers: an OpenClaw plugin, a Codex front-end, and a Claude Code skill-router hook.
- Keyless paths: recorded Jev responses replay, RouteLab shows a recorded baseline, and a local decider server swaps in via TYPESAFE_BASE_URL.
- The CCTV extra judges 13 CAVIAR clips for falls, fights, and abandoned objects with OneJev on a Colab T4.
- Requirements are light: Node.js 20+, Python 3.10+, one of the three agents, and a TypeSafe key in each folder's .env.
Watch out
No license is shown in the digest, and this is unofficial lecture material, not affiliated with TypeSafe, Claude Code, Codex, or OpenClaw. It ships real abusive-language data under CC BY-SA 4.0 and one borrowed script from jev-judgment, and the browser exercise insists on a separate temporary Chrome profile.
Questions about this entry
Short answers drawn from the linked project or page.
Lesson folders for a three-part Jev course, covering concepts and first calls, routers and cost, and lookalike projects, plus a CCTV state-judgment extra, each with its own prompt file, example code, and measured results.
Yes, at least one of Claude Code, Codex, or OpenClaw: the lessons are driven by pasting prompts from each lesson's prompt file, which also names the example code locations for the exercises.
Yes: saved Jev responses replay, RouteLab renders a recorded baseline without keys, and lesson 3 includes a local decider server you can point at with TYPESAFE_BASE_URL to compare API against local grading.
Node.js 20 or newer, Python 3.10 or newer, at least one supported agent, and a TypeSafe key copied per folder from .env.example; lesson 3 also expects uv, Chrome, Ollama with qwen3.5:4b, and jev-ultrafast.
The README states every figure was run by the author on 2026-09-23, including the 471-comment LLM versus Jev comparison and the router cost calculations.
Slides and the full measured records, which live in the student distribution; the repo keeps the code, the records the code reads, such as the API-versus-local evidence, and the replay responses.
OneJev, an open judgment model, watches 13 CAVIAR clips for falls, fights, and abandoned objects, with the instructor's A4000 records and a T4 Colab notebook for replaying the judgments.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Facebook: Intake Router keeps diagnosis out of the answer space at the front desk.
FacebookClinicnotes
YouTube: Jev explained for routing and judging, with a comparison against LLMs.
Hacker News: Vercel on using Jev for defined decisions and GPT-6 Astra when the job also has to write or use tools.
flashbrew4 pointsTypeSafe AI Jev vs. GPT-6 AstraRead the thread on Hacker NewsHacker News: ASTGL replay chose local Laya routing over hosted Jev on one Mac Studio setup.
Jmeg8r15 pointsDoes an open-weight decision model beat a hosted one? Jev vs. LayaRead the thread on Hacker NewsMore Jev resources like this
A support-ticket cookbook that lets Jev decide which requests are worth remembering, then wraps each call so saved tickets ride along in the state. Six later messages route correctly with memory against two without.
Jev CookbooksDocs#official#cookbook#memory
Official
1.9kGitHub stars
A Go-based team workspace with optional Jev AI for agent auto-routing, task auto-fill, auto-assign, and automation condition nodes.
Jev Tools & CLIs#community#go#agents
Community
Paca-AI/pacaGo
Paca-AI/pacaGo170GitHub stars
Local Instagram, TikTok, and LinkedIn research app where Jev makes confidence-gated typed choices over the platform and next socai operation, while deterministic Node code validates each decision and the socai CLI performs read-only browser capture.
Jev Cookbooks#community#javascript#agents
Community
socai-io/jev-socialJavaScript
socai-io/jev-socialJavaScript8GitHub stars
Pokémon Red under PyBoy where ordinary Python owns the route and arithmetic and Jev is asked only at branches, with each battle turn's faint prediction scored by Brier.
Jev Cookbooks#community#python#games
English, Turkish and German decision-model test data with probability targets: 3,116 held-out rows across three languages, where Deem-4B scores 94.7% in English against Kev-4B's 84.7%.
Jev Benchmarks & EvaluationsDocs#community#benchmark#evaluation
Community
A spoken-language learning experience where video scenes branch on TypeSafe Jev decisions instead of multiple-choice clicks.
Jev Demos & ExperimentsPlayground#community#playground#agents
Community
From the Jev guides
Original write-ups on what this entry is for.
Retrieval is a sequence of bounded judgments. How a decision model slots into passage filtering, semantic find, reranking, and citation checks, and what stays in deterministic code.
Jev Cookbooks#retrieval#reranking#rag
Read article
Jev bills input tokens and gives output away, and questions in one request run in parallel. The design consequence is simple: ask more per call, then decide in code.
Jev Cookbooks#batching#patterns#search
Read article
From the Jev community
Posts from builders shipping with Jev right now.