jev

Hands the small judgments in a session to TypeSafe's Jev, a System One model that returns typed answers instead of…

Create, tune and record typed configurable logic graphs with Sapho.

Behavioral drift detection for autonomous AI agents.

Continuous quality review and source-anchored findings powered by Jev.

Install and operate Auto (Jev), a local model router designed for Codex GPT-6 Luna, GPT-6.1 Sol, and GPT-6 Astra.

An iterative, local-first software-quality score loop for AI coding agents, powered by Jev.

Run structured stimulus-task-response polls against simulated respondent cohorts using Jev.

좁은 판단(예/아니오·분류·0~N 점수)을 LLM 대신 jev 에게 넘겨 에이전트의 토큰과 시간을 아끼는 스킬. 타입이 고정된 확률과 캘리브레이션된 확신도를 건당 약 $0.00004, 300~500ms 에 돌려준다.

Authored Fleet Core library: staffing (work shape, role, and lens to model and effort), the tier palette and resolver,…

Uses the Jev model to decide, when you post in a room without naming anyone, which agent answers first and who else…

Third-party skills enhanced with advisory TypeSafe Jev judgments: two-axis code review, prose humanizing (en/zh-TW),…

Asks TypeSafe's Jev which bulky tool results the session still needs, and replaces the rest with a bounded head plus a…

KOSIF Omni — one plugin for Claude and ChatGPT: unified front door, 49 skills, a 1,040-member Genius Council, 65…

Semantic code search and call-graph analysis via the sgrep CLI (Jev / TypeSafe System One). Finds code by meaning,…

A curated collection of Jev skills, example projects, tools and integrations.

Prompt-injection and dangerous-action guard for coding agents, powered by Jev.

An iterative, local-first software-quality score loop for AI coding agents, powered by Jev.

Use Jev directly or through OpenRouter to select past conversation blocks needed for the next topic.

Routes a task to an LLM under quality, cost, and latency constraints.

Independent Qualixar integration for typed Jev decisions, optional local Laya, bounded recipes, and recoverable context…

Install plan-anchor (Jev-backed anchors and gates that keep plans and delivered work aligned) into a repository or a…

Jev-assisted, evidence-backed merge-queue decisions for rebase and full-test requirements.

Portable jev context-economy plugin: the jev decision MCP (jev_health, jev_summarize, jev_find, jev_screen) plus the…

Jev-based test impact assessment for CI and coding agents.

Plan, verify and learn with an evidence-first Skill and bundled local CLI. Optional Jev; no MCP setup required.

High-level GOAL→JSON browser automation via TypeSafe Jev indexed controls. Prefer over screenshot computer-use for…

Suggests at most one skill for a request via Jev (TypeSafe cookbook pattern) before the agent loads anything.

TypeSafe Jev drives a real browser: one goal, an indexed action space, one systemOne decision per step. Exposes the…