CodeAlive-AI/mastra-jev-moderation

CodeAlive-AI/mastra-jev-moderation on GitHub

Stars: 3
Forks: 1
Language: TypeScript
License: MIT
Last push: 18 Sep 2026

Read from GitHub on 24 Sep 2026. Counts change daily.

How it uses Jev

// Jev System One API
// ---------------------------------------------------------------------------

export const JEV_ENDPOINT = "https://api.typesafe.ai/v1/systemone";
export const JEV_MODEL = "jev-latest";

/**
 * A yes/no question. The API calls this type `noul`; its answer is a number,
 * P(true). `criteria` describes what counts as `true` and as `false`.
 */
export interface JevBooleanQuestion {
  type: "noul";
  instructions: string;
  criteria: { true: string; false: string };
}

View in jev-moderation.ts

Open on GitHub

Use casesLLM guardrails

Introducing System One Models and Jev (Hacker News launch thread)

The 1,978-point, 513-comment launch thread. The top comment calls the speed comparison misleading, since Jev only returns structured output, and disputes the cannot-hallucinate claim because a valid type can still hold a wrong value. Others note ordinary LLMs can already be forced into structured output.

albelfioOpen

DiscussionIntent and model routing+3

Outlines: structured outputs for LLMs

Guarantees valid structured output during generation by constraining decoding to a grammar or schema. The mechanism HN commenters repeatedly cited as already covering Jev's cannot-produce-a-type-error guarantee on ordinary LLMs. Star count is GitHub's rounded display figure.

dottxt-ai16k starsOpen

AlternativeStructured extraction+2

jev-review

Staged code-review workflow with a local dashboard, where Jev judges code changes or a whole codebase.

devagrawal09582 starsOpen

ProjectSemantic code linting+1

Foreman

Places Jev as a fast supervisor above slower Codex coding agents. Codex workers do the engineering while Foreman independently assesses whether the work is complete, requirements are met, tests suffice, or human input is needed.

thruwire538 starsOpen

ToolConfidence-gated actions+2

y0usaf/pi-jev

Extension making Jev the decision layer for the Pi coding agent: a measured tool-call gate plus a jev_ask tool. Judges whether an action is destructive, exfiltrates data or exceeds scope, then blocks or warns on calibrated thresholds.

y0usafOpen

144 starsGate latency ~300ms

ToolLLM guardrails+2

pi-warden

Guardrails for the Pi agent built on pi-typesafe. Jev judges irreversible and off-task tool calls, detects stuck loops, checks unverified completion claims and flags low-quality output, steering the agent rather than interrupting the user.

DevMortimerOpen

138 starsHolds per 1000 calls 3

ToolLLM guardrails+1

Menu

CodeAlive-AI/mastra-jev-moderation