jev-watchdog

glebmish/jev-watchdog
Jev application

Event-driven trajectory watchdog for coding agents: per-event LLM judgments (Jev, Claude, GPT) accumulated into quarantine decisions

PythonDocumented

jev-wiki-watch

hfmsio/jev-wiki-watch
Jev application

Live Wikipedia vandalism watch judged by Jev, TypeSafe AI's typed-decision model. Two files, no packages.

HTMLDocumented

jev-windows

Yzywil/jev-windows
Jev application

Supervised Windows UI Automation with TypeSafe Jev: bounded choices, local policy, verified outcomes.

PythonDocumented

jev-workbench

Chunky83/jev-workbench
Research

Jev Workbench: a C++ desktop workspace with Python diagnostics and structured TypeSafe evaluations

PythonDocumented

jev-x-tags

Muzych/jev-x-tags
Jev application

Tag X/Twitter accounts with TypeSafe Jev and hide posts by tag (Chrome MV3 / WXT).

TypeScriptDocumented

jev-youtube-filter

pomykalakyle/jev-youtube-filter
Integration

Semantic YouTube recommendation filtering powered by Jev

JavaScriptDocumented

jev48

edgelabs-ai/jev48
Local alternative

Open, auditable reproduction of TypeSafe Jev: a 2B probabilistic decision model benchmarked across six public suites with weights, code, and receipts.

PythonDocumented

jev_practice

ryuchan00/jev_practice
Jev application

Jev (TypeSafe System One) と LLM に同じゲームを打たせて、レイテンシ・コスト・判断の質を比べる練習台

PythonDocumented

jev_rag

aijnek/jev_rag
Research

RAGのretrievalにTypeSafe APIを使うアイデアの実装

HTMLCode reference

jev_tool_calling_experiment

javierBrenesAI/jev_tool_calling_experiment
Research

Use Jev model from TypeSafe to evaluate if there is an improvement in latency and cost in the agentic loop for tool decisioning.

PythonDocumented

jevdash

Sunwood-ai-labs/jevdash
Research

100% clean-room, copyright-free 2D platformer benchmarking TypeSafe Jev AI in real-time control (60 FPS)

PythonDocumented

jevengineeringgate

RavenRepo/jevengineeringgate
Jev application

Calibrated decision layer and risk gate for AI coding agents. Routes yes/no, routing and scoring judgments to the Jev System One model at ~$0.0000123 per decision, then enforces the result deterministically through Claude Code PreToolUse hooks. Fitted thresholds, not guessed.

JavaScriptDocumented

JevEye

Adityakhalkar/JevEye
Jev application

Ask Jev about an image. A CNN reports what it sees with a calibrated confidence or an abstention; Jev judges what it means.

TypeScriptDocumented

jevfanity

TickerDev/jevfanity
Jev application

Monorepo for jevfanity, a profanity detector using Jev by TypeSafe AI

TypeScriptDocumented

jevguard-mcp

seb4ez/jevguard-mcp
Jev application

Official Model Context Protocol (MCP) server for JevGuard and TypeSafe AI

PythonDocumented

JevGuard-NSFA

knowlet/JevGuard-NSFA
Jev application

Experimental System One implementation of the SingGuard-NSFA agent-security taxonom.

PythonDocumented

jevia-harness

sleepy0x13/jevia-harness
Jev application

把判断和写作分开的本地 agent:Jev 负责所有能用类型表达的判断,语言模型只写该写的。零第三方依赖。A local agent harness that puts a System One model in front of the LLM.

PythonDocumented

jevify

gulagala001/jevify
Local alternative

Jev-style Choice, Score and Noul decisions from ordinary models. An optional DSH plugin.

JavaScriptDocumented

jevknows

wmtang2/jevknows
Jev application

A malicious instruction protection skill and prehook for zcode

PythonDocumented

jevlergy

daisuke7/jevlergy
Research

Evaluating TypeSafe's System One model Jev through camera-based food allergen estimation (Flutter, iOS/Android)

PythonDocumented

jevmap

rishvaiyer/jevmap
Integration

Evidence-backed Jev opportunity mapping for public GitHub repositories

TypeScriptDocumented