Skip to content
JevDirectory.org
CommunityTools & Integrations17 starsVerified 2026-09-22

jev-axi

Agent-ergonomic CLI following the AXI conventions that gives coding agents Jev judgments for blocking risky tool calls, screening fetched content for prompt injection, triaging logs, flagging risky diffs, and ranking many items. Routine commands are decided locally at no cost.

Category
Tools & Integrations
Published by
Community
Author
shiftynick
Added
2026-09-22
Tagscommunitytypescriptclicoding-agentguardrailssecurity

Highlights

  • A PreToolUse hook blocks risky Bash calls before they run and decides routine commands locally for free.
  • jev-axi guard screens fetched text for prompt injection and exits 3 so shell pipelines can gate on it.
  • Its own benchmark found file ranking changed cost and reads by less than run-to-run noise on a 390k-line repo.
  • Tracks tokens, latency, model version, and estimated cost per command in a local usage ledger.
  • Commands cover pick, rate, check, rank, filter, find, diff, files, triage, guard, and progress.

Quickstart

bash
npm install -g jev-axi
export TYPESAFE_API_KEY=YOUR_API_KEY
jev-axi setup safety

Watch out

MIT-licensed. Needs Node and a TYPESAFE_API_KEY from config, .env, or the environment; hook warnings never block, and its own benchmark says it is for judgments, not a substitute for reading code.

More like this

132GitHub stars
Pi extension that supervises a coding agent with Jev judgments: it holds risky tool calls, checks writes against project Markdown rules, and feeds most issues back to the agent as a steer instead of interrupting you. The conscience is beta and off by default.
Tools & Integrations#community#typescript#guardrails
Communitypi-warden
22GitHub stars
A Node CLI that sends source, configuration, build, and CI files to Jev and reports suspicious files and lines with probabilities, as a second opinion before running unfamiliar code.
Tools & Integrations#community#typescript#cli
Communityis-malicious
10GitHub stars
A pre-commit hook that answers five Jev questions about the commit message and staged diff together, warning on mismatches and blocking only on a credential-shaped line.
Tools & Integrations#community#python#coding-agent
Communityjev-commit
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Cua's small System One models

A 706K-parameter form filler

cua open sourced a 706k param model that fills a whole form in one 50ms pass the llm agent doing the same form took 23 turns and 39.6 seconds the specialists are going to eat the generalists from the bottom

Cua
Cua
@trycua

1/ Introducing CUA-S1: a family of System One Models, small, specialized, and built for computer use. Today we're open-sourcing CUA-S1-FORMS, the first in the family: github.com/trycua/cua

Image
Reply

Navigating Neo4j with Jev

Jev 这个 waitlist 还是很给力的,昨天申请,今天就能用上。 给已经拿到 API、但还不知道怎么玩的人整理了一份 Awesome Jev,目前我能确认到的 Jev 项目基本都在这里: 1. jev-ultrafast Browser Use 做的高速浏览器 Agent。Jev Show more

Image
思维怪怪
思维怪怪
@0xLogicrw

前 OpenAI 研究员 Diogo Almeida 创办的 TypeSafe AI 推出新模型 Jev。它有点像一个能读懂自然语言的超级分类器,不生成文本,只返回选项、分数和概率,专门给软件做判断。 普通大模型需要一个 token 一个 token 往外生成,Jev 则可以并行给出多个结果。TypeSafe 还用新的 RLCD

Reply

Reranking 33,047 catalog entries

拿 Jev 做搜索重排,我先泼一盆冷水:单独用,它没打赢向量检索 TypeSafe 的 Jev 这阵子很火,一堆项目拿它做重排。我们在 Agent Skills Hub 的 33,047 条目录上认真测了一次,164 条中英文真实查询,9,831 对分级标注,整套只花了 2.6 美元 三个结论 01|单独重排,约等于没赢 Jev 重排 bge-m3 Show more

Jason Zhu
Jason Zhu
@GoSailGlobal

有美团、阿里的老哥嘛? 试试加一路召回、重排(离线、近实时实现),我觉得有奇效 他在文本理解上 跟之前机器学习、llm很不一样 还能自动打标签做特征

Reply

Six uses that stuck after 60 days

Security decisions that fit Jev

This made me rethink where AI actually fits into security engineering. For purely engineering work, forget about ChatGPT or Claude. TypeSafe AI just released Jev, and I think it’s going to change how we build AI into security workflows. Instead of asking an LLM to “investigate Show more

TypeSafe AI
TypeSafe AI
@typesafeai

we are officially out of stealth! join the frontier and get access to Jev on our website (link on profile)

Reply