AI-assisted summaries and translations. Check original sources for context and performance claims.
jackbarunz
A developer project for the agents shelf, using MCP tool for Codex instead of listing all options.
github.comjackbarunz/jev-tool-routerVer projeto ↗
Source-linked curation
NullPo-jp
On-device iPhone visual decision tool using MLX and Qwen3-VL direct option logits.
github.comNullPo-jp/PocketJevVer projeto ↗
Source-linked curation
shiftynick
Agent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shell.

Source-linked curation
heiwa4126
TypeSafe の Jev を TypeScript SDK で使ってみる最初の 1 歩.
github.comheiwa4126/jev-bun1Ver projeto ↗
Source-linked curation
GhrezaKh74
A .NET 10 and React 19 application for fast, structured AI-powered ticket triage using TypeSafe Jev.
github.comGhrezaKh74/JevTicktRouterVer projeto ↗
Source-linked curation
lyk
A developer project for the hardware shelf involving two-stage Jev control of a robotic arm in MuJoCo.
github.comlykycy123/RoboJEVVer projeto ↗
Source-linked curation
Okina Audio
A tool controlling Ableton Live with concise commands, leveraging Jev's decision-making capabilities.
github.comokinaaudio/live-jevVer projeto ↗
Source-linked curation
fabricioctelles
Curated catalog of System One / Decision Models — contributions for modelsystem.one.
github.comfabricioctelles/modelsystemVer projeto ↗
Source-linked curation
ndolinschi
TrustGate — indie media T&S gate via TypeSafe Jev.
github.comndolinschi/trustgateVer projeto ↗
Source-linked curation
acharyaanusha
A Magic 8 Ball for pull requests: click the ball and it answers "should I approve this?" with one of the 20 classic phrases, chosen by Jev from the PR's real signals in about 200 ms.
github.comacharyaanusha/magic-jevVer projeto ↗
Source-linked curation
thiago-ss
Autonomous Jev pull-request review with typed decisions, calibrated approval gates, and trusted-owner escalation.
github.comthiago-ss/jev-reviewVer projeto ↗
Source-linked curation
bnsd55
Jev-style parallel constrained decisions for any MLX model on Apple Silicon. Typed, schema-valid JSON in one forward pass.
github.combnsd55/jevmlxVer projeto ↗
Source-linked curation
SoundBlaster
Jev adapter to Mellea.
github.comSoundBlaster/Jev4MelleaVer projeto ↗
Source-linked curation
MahmoudAdelbghany
Jev-powered browser MCP for LLM agents — ~300ms decisions, no LLM tokens in the loop. Benchmark vs Playwright MCP included.
github.comMahmoudAdelbghany/jev-browserVer projeto ↗
Source-linked curation
0x7067
Browser automation with Jev (TypeSafe) as decision model.
github.com0x7067/jev-browseVer projeto ↗
Source-linked curation
TypeSafeAI
Multi-axis writing quality checker powered by TypeSafe AI's Jev model. Separate named checks, each with its own verdict and confidence.

Source-linked curation
keltokhy
Links records under a plain-English match rule using Jev Noul pair judgments, with local candidate blocking and match resolution.
github.comkeltokhy/jlinkVer projeto ↗
Source-linked curation
Yasserbhb
Using the new model JEV to play the game tetris.
github.comYasserbhb/Agent-JEV-TetrisVer projeto ↗
Source-linked curation
minorun365
三大クラウドの機能名を、TypeSafe AI の System One モデル Jev が確率つきで判定するデモ.
github.comminorun365/jev-cloud-quizVer projeto ↗
Source-linked curation
kraayenjon
A curated list of Jev use cases, projects, SDKs, and resources. Jev is TypeSafe AI's System One model for fast, typed decisions in software — Choice, Score, and Noul with calibrated probabilities.

Source-linked curation
Kush Bhuwalka
A developer project for agent classification and selective reading using an agent plugin and MCP tool.

Source-linked curation
mossyfield
A SillyTavern extension that evaluates replies before they are displayed, collected for the creative shelf.
github.commossyfield/ST-jevedVer projeto ↗
Source-linked curation
jiawei686
Hand the browser work off: an MCP server where a decision model drives the page for your agent, so a flow costs one tool call instead of a turn per click. Ref-based element tables, code-checked assertions, zero-model macro replay. Speaks CDP to your Chrome.
github.comjiawei686/jev-ultrafast-mcpVer projeto ↗
Source-linked curation
sorrycc
Snake auto-played by TypeSafe's Jev model: one System One choice per tick, legal moves and facts generated in code.
github.comsorrycc/typesafe-snakeVer projeto ↗
Source-linked curation
goya4140
Jev 1.13 reward-model evaluation across 8 benchmark tracks, with an interactive report and 54-row SOTA comparison.
github.comgoya4140/jev-reward-model-evaluationVer projeto ↗
Source-linked curation
Jökull Sólberg Auðunsson
A research project featuring an English–Icelandic dictionary that uses Jev to rerank results for better accuracy.

Source-linked curation
madeye
Jev-assisted file retrieval and request caching for faster Pi workflows.

Source-linked curation
aniruddh-krovvidi
Guardrail + model router for LLM gateways on TypeSafe's Jev (System One model), with an independent accuracy/calibration/latency evaluation. Stdlib Python.
github.comaniruddh-krovvidi/switchboardVer projeto ↗
Source-linked curation
MUKi
A GitHub project implements a web search tool where Jev selects sources for plain-language queries.
github.commukiwu/jev-search-mcpVer projeto ↗
Source-linked curation
vnmoorthy
SIEGE: 200 people vs one agent. A typed action gate (TypeSafe System One) that learns from every breach, evaluated by W&B Weave, hardened by a defender loop. Built at CoreWeave Hacks: Agent Loops 2026.
github.comvnmoorthy/siegeVer projeto ↗
Source-linked curation
harshil1712
Voice-driven semantic auto-advance for Slidev, powered by Cloudflare Agents and TypeSafe AI Jev.
github.comharshil1712/slidepilotVer projeto ↗
Source-linked curation
Seb4Ez
A developer tool for decision runtime with zero-token caching and a calibrator, collected for the tools shelf.
github.comseb4ez/jevguardVer projeto ↗
Source-linked curation
terryds
Browser-only playground for Jev (TypeSafe AI's decision model) via Vercel AI Gateway.
github.comterryds/jevplaygroundVer projeto ↗
Source-linked curation
wuyoscar
An awesome collection of Jev use cases, workflows, and agent skills.
github.comwuyoscar/jev-skillVer projeto ↗
Source-linked curation
cephalization
Uses typeful jev, zero sync to pull and sync large repositories for issue triage.
github.comcephalization/jev-triageVer projeto ↗
Source-linked curation
caiovicentino
Semantic MCP firewall powered by Jev — screens every tool call, tool result, and tool description with calibrated System One verification. 94% block recall, 0 false positives, ~$0.00002/check.
github.comcaiovicentino/jev-shieldVer projeto ↗
Source-linked curation
nican2018
Evaluating TypeSafe's Jev as a fast monitor and action gate for agent sabotage in SHADE-Arena, compared with Gemini 2.5 Flash/Pro.
github.comnican2018/shade-arena-jev-monitorVer projeto ↗
Source-linked curation
model-clis
A command-line interface for Jev that provides answers and exit codes based on input questions.

Source-linked curation
Joel Lewis
A chess coach combining Stockfish's analysis with Jev's judgment for real-time decision support.
github.comJoelLewis/game-coachVer projeto ↗
Source-linked curation
brainstormity
Real-time Discord moderation bot: Jev evaluates messages and metadata in parallel to catch phishing, spam, and social engineering with a progressive escalation ladder.

Source-linked curation
heyjunpenn
A verified, community-maintained catalog of 485 open-source projects built with Jev.
github.comheyjunpenn/awesome-jevVer projeto ↗
Source-linked curation
dnakhoa
Position paper: the Hidden-Markov and fuzzy primitives missing from TypeSafe AI's Jev and System-One decision models. Two lemmas, one principle (Deferred Crispification), one architecture (BSF-S1).
github.comdnakhoa/jev-deferred-crispificationVer projeto ↗
Source-linked curation
ShuhanSun
Catch breaking API behavior hidden in OpenAPI prose with deterministic checks and TypeSafe JEV System One semantic review.
github.comShuhanSun/jev-oas-sentinelVer projeto ↗
Source-linked curation
copyleftdev
Never confidently wrong: a TLA+-verified consensus kernel around TypeSafe's Jev, run through 1,680 chaos-tested pharmacy decisions with zero wrong verdicts. Film, code, and every captured call.
github.comcopyleftdev/jev-labsVer projeto ↗
Source-linked curation
frostney
Every code file in a pull request, judged against Uncle Bob's Clean Code by TypeSafe's Jev, then reviewed by Luna. Built on eve and Next.js.
github.comfrostney/clean-code-reviewVer projeto ↗
Source-linked curation
SiliconLabAI
An open-source project aiming to develop a Jev-class decision model for research purposes.
github.comSiliconLabAI/OpenJevVer projeto ↗
Source-linked curation
ajensenwaud
TypeSafe Jev (System One) decision tools for Hermes Agent: jev_check / jev_route / jev_score / jev_evaluate.
github.comajensenwaud/hermes-jev-pluginVer projeto ↗
Source-linked curation
Stumble
Community Go SDK for TypeSafe AI Jev / System One.
github.comStumble/jev-goVer projeto ↗
Source-linked curation
vibe-with-me-tools
Helper n8n community node for Jev by TypeSafe. Classify, route, and score text with questions you define, and get a probability for every answer so unsure items can go to review.
github.comvibe-with-me-tools/n8n-nodes-jevVer projeto ↗
Source-linked curation
Menny1337
TypeScript experiments, evaluations, and latency benchmarks for TypeSafe's Jev model.
github.comMenny1337/jev-labVer projeto ↗
Source-linked curation
Tony Powell
A GitHub project converting agent skills into Oxlint plugins that involve Jev.

Source-linked curation
AbdelStark
Curated list of official resources and community projects for TypeSafe, System One models, and Jev, with a GitHub Pages site.

Source-linked curation
y0usaf
A word-level language model whose output layer is Jev: n-gram drafter, Noul chunk verification, bits-per-token eval.
github.comy0usaf/jev-lmVer projeto ↗
Source-linked curation
KamilPostrozny
Single-agent Pi coding coprocessor with Jev semantic gates, baseline-to-current diff review, and append-only observability telemetry.
github.comKamilPostrozny/pi-jev-codeVer projeto ↗
Source-linked curation
bestagentkits
Per-prompt capability router for coding agents: resolves installed skills, MCP servers, agents and commands against your prompt via TypeSafe Jev, and measures whether the injection actually helps.
github.combestagentkits/jev-skillfulVer projeto ↗
Source-linked curation
rbalch
Using Typesafe.AI to generate diff reviews.
github.comrbalch/typesafeai-reviewVer projeto ↗
Source-linked curation
kylemclaren
Semantic SQL for Postgres, powered by Jev.
github.comkylemclaren/jevqlVer projeto ↗
Source-linked curation
tryaksh
A small reproducible MuJoCo pilot comparing Jev, Claude Haiku, and reactive rules for pick-and-place.
github.comtryaksh/jev-pick-and-place-studyVer projeto ↗
Source-linked curation
rmalde
Jev controls an Astra planner playing Minecraft in a developer project.
github.comrmalde/minecraft-agentVer projeto ↗
Source-linked curation
AkashPriyadarshii
Systematic software development framework for AI coding agents upgraded with TypeSafe Jev System One typed decisions.

Source-linked curation
PromptGTM
A developer project for lead scoring in Clay using Jev.
github.compromptgtm-shared/clay-jev-people-rankerVer projeto ↗
Source-linked curation
AboveColin
Async Python client for TypeSafe Jev. Typed questions in, probabilities and choices out, no prose to parse.
github.comAboveColin/jevclientVer projeto ↗
Source-linked curation
iefnaf
Pi extension suite powered by Jev: selective context compaction and model routing.
github.comiefnaf/pi-jevVer projeto ↗
Source-linked curation
Koushik890
Real-time firewall for AI coding agents: a PreToolUse hook checks every Claude Code / Codex tool call with deterministic shell-aware rules, and unmatched actions go to Jev for a calibrated allow/ask/block that fails closed.
github.comKoushik890/jev-firewallVer projeto ↗
Source-linked curation
Ably Labs
Game where Jev competes against LLMs in Pong.

Source-linked curation
cablehead
Nushell module for the TypeSafe System One API: typed decisions with calibrated probabilities.
github.comcablehead/jev.nuVer projeto ↗
Source-linked curation
johnhughes3
LegalForecast-MTD benchmark alpha and official evaluation workflows.
github.comjohnhughes3/LegalForecastBenchVer projeto ↗
Source-linked curation
1 clicks / 7d
anandi1989
Evidence-backed index of real-world Jev (TypeSafe AI System One) use cases: repos, patterns, benchmarks, and measured results.
github.comanandi1989/awesome-jev-usecasesVer projeto ↗
Source-linked curation
guillemus
Unofficial Go SDK for TypeSafe AI's Jev API.
github.comguillemus/jev-goVer projeto ↗
Source-linked curation
drowzeys
Validated enhancement pack for MiniMax Code CLI on arm64 DGX Spark + local GLM-5.3-EXL3: TUI scrollbar + context-meter patches, compaction repair for local vLLM, Jev Ultrafast + Playwright MCP browser integration, real usage ledger.
github.comdrowzeys/keys-MiniMax-Code-CLI-Browser-Scroll-Context-Enhancement-Pack-with-Jev-Ultrafast-IntegrationVer projeto ↗
Source-linked curation
smasato
Jev (TypeSafe) 性能評価プロジェクト — 日本郵便 KEN_ALL をマスタに、AI SDK 経由の Jev が住所のあいまい一致にどこまで使えるかを検証.
github.comsmasato/jev-jp-addressVer projeto ↗
Source-linked curation
JanOstrowka
Home Assistant Assist conversation agent powered by TypeSafe's Jev (System One) model.
github.comJanOstrowka/typesafe-assistVer projeto ↗
Source-linked curation