Skip to content
JevDirectory.org
CommunityRepos & SDKs9 starsVerified 2026-09-22

super-jev

An experimental TypeScript harness that connects evidence to Jev judgments, permitted actions, and verified outcomes, with pluggable data sources and tools, local JSONL traces, and zero runtime dependencies.

Open github.comKevthetech143/super-jev
Category
Repos & SDKs
Published by
Community
Author
Kevthetech143
Added
2026-09-22
Tagscommunitytypescriptagentsguardrailsskills

Highlights

  • One bounded run tracks state, fetches evidence through observe, batches typed questions, validates answers, permits one tool, and verifies the outcome.
  • Runs end as success, stopped, blocked, or error, bounded by maxSteps, timeoutMs, maxRequestBytes, and maxRepeats.
  • The byte budget is a local size guard, not a tokenizer, and retries are not automatic; an action_started without action_completed needs reconciliation.
  • Journals record context, answers, and outcomes; credentials stay out of trace payloads and raw error text is omitted.
  • The suite has 50 tests, and a live jev-1.13.0 response is checked in as a fixture that confirmed the documented score rule and disproved one inferred rule.

Quickstart

ts
import { run, Jev, JsonlJournal } from './src/index.ts';
import { recovery } from './examples/domains.ts';

const result = await run({ domain: recovery(), initial: { restarted: false, healthy: false },
  evaluator: new Jev(), journal: new JsonlJournal('runs/my-run.jsonl'),
  maxSteps: 10, timeoutMs: 30_000, maxRequestBytes: 100_000, maxRepeats: 2 });
console.log(result.status, result.state);

Watch out

MIT-licensed but experimental V0.2.0 and not affiliated with TypeSafe AI; needs Node.js 24+ and TYPESAFE_API_KEY, plugins run in-process as trusted code without sandboxing, and there are no automatic retries.

More like this

jev-harness
9GitHub stars
A TypeScript library that wraps Jev answers in a policy, a confidence gate, shadow mode, reusable recipes, and an offline eval CLI, so structured decisions can drive actions an application ships.
Repos & SDKs#community#typescript#agents
Communityjev-harness
eve
5.3kGitHub stars
A filesystem-first framework for durable AI agents whose auto model router defaults to Jev through Vercel AI Gateway and whose evaluate helper asks typed Choice, Score, and Boolean questions inside tools.
Repos & SDKs#community#typescript#agents
Communityeve
NeuroLink
137GitHub stars
A Juspay TypeScript SDK that treats Jev as a third inference type beside generate and stream: providers declare which kinds they serve, and tryDecide returns typed boolean, choice, or score answers, null when no decision provider is set.
Repos & SDKs#community#typescript#sdk
Communityneurolink
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Six uses that stuck after 60 days

Security decisions that fit Jev

Kostas
Kostas
@Kostastsale
·

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
Read 14 replies

A million judged questions

Inferring Jev's internals from 1,000 calls

iwashi / Yoshimasa Iwase
iwashi / Yoshimasa Iwase
@iwashi86
·

Jevの内部アーキテクチャを推測している技術記事(Jev’s Architecture Unmasked)からメモ。 ・本記事はJevのAPIを約1万回の呼び出して、内部構造を推測したもの ・従来の言語モデルを用いた分類やルーティングでは、トークンを1文字ずつ逐次生成するために膨大な無駄な計算コストが発生していた。 Show more

Reply
Read 2 replies

The open System One roundup

小墨同学
小墨同学
@xiaomovps
·

Jev 发布没几天，开源社区已经开始疯狂复刻了🔥 最值得推荐的五个模型： 1、Laya 421M：原生决策模型，支持 Mac 2、Decider-2B：最像 Jev，基于 Qwen3.5 3、NanoJev 0.6B：专门的 Decision Head 4、Reflex：Qwen3.5 + Direct Logits 5、System-One 4B：专门做概率校准 Show more

小墨同学
小墨同学
@xiaomovps

Jev 刚发布没几天，开源社区就出现了同款🔥 Decider-2B模型，是基于 Qwen3.5-2B 做了特殊调整 它和 Jev 模型是一样的 只做选择 评分和判断 不是文本类的 LLM 模型 但两者还是有几个明显区别： 1、模型 Jev：闭源 System One Model Decider：Qwen3.5-2B，约 1.9B 参数，Apache 2.0 开源 2、价格

Image
Reply
Read 6 replies

The launch post