CcardotrejosDemos & playgrounds

jev-ad-preflight

Typesafe/Jev public X demo

Explore repository

How it uses Jev

jev-ad-preflight Typesafe/Jev public X demo

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to jev-ad-preflight

Browse all
jev-demo project preview

jev-demo

Demos & playgrounds
TypeSafe Jev（System One 决策模型）零依赖网页体验台：浏览器操作 / 意图识别 / Agent 上下文裁剪三大预设场景，发送状态与类型化问题，拿到带校准概率的结构化答案
PMade byPenglongHuang1
jev_fsd project preview

jev_fsd

Demos & playgrounds
JEV AI Model Demo with FSD
BMade byBrendanH182
codex-jev-preflight project preview

codex-jev-preflight

Agent tooling
Fail-open Codex UserPromptSubmit hook that injects TypeSafe Jev pre-task routing metadata.
WMade bywellkilo1
jev-demos project preview

jev-demos

Demos & playgrounds
Demos to test the effectiveness of TypeSafe's "Jev" System One Model
BMade byBud-ro0
what-is-jev project preview

what-is-jev

Benchmarks & research
Independent, source-linked research on TypeSafe AI's Jev (System One), with 947 rubric-scored public repositories, recurring patterns, datasets, and bilingual documentation.
GMade byg0runmezadam1
typesafe-demo-mcp project preview

typesafe-demo-mcp

Agent tooling
MCP server exposing TypeSafe System One judgments (noul, choice, score) as agent tools
BMade bybestagentkits0
Jev-Research-Index project preview

Jev-Research-Index

Benchmarks & research
Jev Research Index is a bilingual catalogue of papers, software projects, interviews, public analyses, demonstrations, and social-media material related to Jev, the TypeSafe AI System One typed probabilistic decision model.
AMade byAgenticAPP-Web1
rover-claude-jev-demo project preview
Image 1 of 3

rover-claude-jev-demo

Jev for robotics
Just a weekend project with Claude as system two, and Jev as system One.
DMade byDevonance2
jev-ood-calibration project preview

jev-ood-calibration

Benchmarks & research
Independent calibration test of TypeSafe's Jev on a task it cannot have seen: 900 rule-generated support tickets (choice / score / boolean) plus 3 public benchmarks via Vercel AI Gateway. Raw responses, ECE with noise floor, temperature refit, per-type sign of miscalibration. Reproducible for ~$0.06.
SMade byscienthoon6