Content scoring
Score quality, risk or relevance on an ordered scale.
166 rows are filed under this pattern, 165 of them with code. Rows are listed as the catalogue orders them: official first, then rows with code, then by stars.
Filter and search them in the catalogue →
Rows marked “not Jev itself” or “shadow mode” stay listed, but they are not examples of deciding with Jev.
-
Cookbook: Self-consistency with choices
Adds an explicit "uncertain" outcome to moderation decisions and measures label agreement against the share of actions taken automatically.
-
Pattern: Composite scoring
Break one broad judgement into atomic scores and combine them with weights that live in your code, not in the prompt.
-
AutoGPT TypeSafe blocks
Seven production blocks — choice, score, yes/no, ask-many, route, pick-best, filter — with a UTF-8 byte budget, verbatim wire capture and eleven test files.
-
worldmonitor: news threat classification
Two Choice questions over threat level and category, held in shadow mode after a blind evaluation found Jev merely tied the incumbent model.
-
gptcache
Semantic cache for LLM calls. Its Jev evaluator asks, for a cached answer and a new request, nouls on whether the task and context match, the format fits, nothing is missing and the answer is still fresh, and reuses it only if the lowest clears the threshold (0.70 in its example).written by a model
-
jev-chat-jarvis
An Android reply co-pilot that judges intent, timing and risk from on-screen text, while separate models handle OCR and drafting.
-
ai-cookbook: Jev track
A graded course from a first call through each primitive, state shapes and criteria, to ticket triage and a multi-step workflow, mirroring all four official patterns.
-
pg-jev
A real PostgreSQL extension exposing the primitives as SQL functions, so a semantic decision can appear in a WHERE clause over any row type.
-
jev-seo
SEO audit from one homepage URL: it crawls the site, checks 52 rules and Core Web Vitals, and asks Jev choice, score and noul questions about each page (type, search intent, helpfulness, trust, whether it opens with the point). Code acts only on decisive answers (0.80 confidence) and ranks fixes.written by a model
-
jev-review
Pre-screens code review with Jev to surface high-risk changes for a more expensive model or a person, with a local dashboard.
-
狗头军师 Jev Chat
Chat-reply assistant (desktop overlay, Android floating assistant, iOS keyboard) built on Jev Android. From the visible chat or a screenshot it asks Jev the literal question, the other person's intent, a danger level, whether to reply now and the best action, then has Jev pick among drafted replies.written by a model
-
llm2jev
Adapt local language models into Jev-compatible structured decision engines with Choice, Score, and Noul outputs powered by prefill-only binary inference.
-
perch: semantic code linting
Tree-sitter finds and ranks methods, then user-authored YAML rules compile into nouls, with severity read as the rubric's expected value rather than the top band.
-
beebots
Three trading bots race on OKX perpetual futures, paper trading by default: Jev (or Gemini) picks each move as a choice from the legal actions plus a score for conviction, with a deterministic fallback, a plain-code risk layer and a live dashboard.written by a model
-
killmyidea
Scores a startup idea across several dimensions and returns a verdict of kill, fix or ship.
-
jev-review
A local-first MCP plugin for continuous code-quality review by coding agents.
-
jev-forge
Not Jev: a toolkit that synthesizes decision data, trains and calibrates small candidate scorers (JevForge-0.8B) and serves them behind a Jev-compatible API, first for picking the next click or form control on a web page. Its benchmark sends the same held-out choice, noul and score questions to Jev.written by a model
-
neurolink
The pipe layer of an AI nervous system: one interface connecting provider neurons to an application, across three inference types — generate, stream, and decide. Decide returns typed, calibrated judgments (boolean/choice/score) via TypeSafe Jev or the open-weights Laya, not text.
-
supercov
Code quality and coverage judgements for coding agents, in Rust.
-
jev-semgrep
grep by meaning, now named sys1grep: for every line Jev answers a noul on whether the line matches a meaning, such as network failure, and a threshold decides. Meanings combine with AND, OR and NOT, a regex can prefilter lines, and the meaning and the text can be in different languages.written by a model
-
jev-lint
Linter for what parsers miss: ast-grep picks the code, Jev is asked each rule's one-sentence question about every match, such as whether the comment above claims something untrue of the code, and matches over the cutoff are flagged. 99 rules ship, from 48 questions; judged code goes to the API.written by a model
-
jev-as-a-judge
Tests Jev as an agent-eval judge against GPT-5.6 Luna, GPT-5.6 Terra and Claude Sonnet 4.6: five frozen runs of a weather agent, each judged 100 times for a quality score and a pass-or-fail call. Jev matched the human label on all 500 calls, against 99.8%, 96.4% and 80.0%; one reviewer, five runs.written by a model
-
jevmeter
Scores every sentence of a video and renders the result as a live meter.
-
ha-jev
A Home Assistant integration: typed answers about the house as sensors, noul, choice and score actions for automations, and a conversation agent.
-
SemDecide
Jev as a command-line tool: classify, score and filter straight from a shell, for crawlers, CI and data pipelines.
-
Working-Memory-Jev
Passage: helps educators see where instructional text may ask a learner to hold too many ideas at once, using the real Jev API to trace active groups and changes in demand.
-
jev-dataops
An open-source JEV-powered workbench for streaming data selection, quality evaluation, automatic LoRA training and held-out model evaluation.upstream description
-
jev-code
Jev, TypeSafe's System One classifier, as a tool inside Claude Code, Codex, Pi, and OpenCode: typed classify, check, score, rank, and ask, plus one-command setup.upstream description
-
Jev-Moderation-Bot
A Discord moderation bot: a Choice tiers each message while a Noul carries ban urgency, and an admin pardon is fed back as a safe precedent in later requests.
-
vibecheck
Python library that turns System One calls into plain values: check (yes/no), classify (one option), label (every option that applies) and score, with thresholds, an unsure answer and batching of several questions about the same data. Works against TypeSafe or any compatible server.written by a model
-
JevScout
A coding-agent skill that hunts jobs on real company sites: Chrome sees and acts, Jev scores every link and posting, and the host LLM never picks what to click.
-
JEV-Paper-Radar
Let Jev read every new arXiv paper each morning and surface the few you should read. Plain-English interests, calibrated probabilities, ~$0.06/day, fork and go.upstream description
-
jev-test-filter
Score every test against a git diff with Jev, and emit the filter arguments vitest, node:test, Playwright, cargo test and go test already understandupstream description
-
slop-grader
Jev-powered, rule-based grader for text files. Runs every rule against every line in parallel. No skimming, no missed lines.upstream description
-
plugins
Official curated plugins for Cline CLI and extensionsupstream description
-
snifftest
A prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model.upstream description
-
typed-decision-bert
Unofficial PoC: a BERT-style encoder decision engine behind a typed-decision (noul / choice / score) HTTP API. Not affiliated with TypeSafe.upstream description
-
jev-calibrate
Calibrate Jev questions against your own labels: tune criteria on labelled examples, confirm on a held-out set, get a verdict per question. Unofficial.upstream description
-
jevgpt
A chatbot built on a model that cannot generate text (TypeSafe AI's Jev, driven autoregressively)upstream description
-
yoshi
Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into https://github.com/compozy/compozyupstream description
-
jsort
sort by meaning: order lines along a plain-English dimension, from pairwise comparisons judged by TypeSafe's Jev modelupstream description
-
toolgate
Open auto mode for AI agents — a calibrated tool-call firewall powered by TypeSafe Jev. Ships as a Claude Code hookearlier upstream description
-
smartmoney-cub
Read-only trading journal and review harness: Jev typed judgments, agent integration, and a reproducible finance benchmark. No orders, no advice.upstream description
-
jev-mcp
An MCP server exposing classify, score, check, match and screen to any agent.
-
jev-yaba-wechat
A macOS floating assistant for replying in WeChat: it reads a message's intent and communication risk, GPT drafts several replies, Jev rates the candidates, and one click fills the chosen one in. You still decide what to send.
-
MetaCog
Inference-time metacognition: a small, fast judge scores a bigger model's answers and steers its reasoning; Jev is one of the judges it can use.
-
x-scanner
Chrome extension that labels every post you scroll past on X with typed Jev judgments and a live cost counterupstream description
-
anydecisionmodel
A Swift package for typed decisions from language models (probabilities, choices, and scores), with support for local MLX models and the TypeSafe Jev API.upstream description
-
hookmeter-jev
⚡ Millisecond-level Viral Hook Telemetry & Co-pilot for Social Media (Chrome Extension + JEV System 1)upstream description
-
jev-feels
Semantic decisions as ordinary Ruby — feels?, decide, score, Rails validations and pattern matching powered by Jev
-
jevframe
Semantic AI for pandas and Polars: classify text, analyze sentiment, and score DataFrame rows with natural-language questions and full probabilities using TypeSafe Jev.upstream description
-
local-jev
A local, offline System One server compatible with TypeSafe's Jev API. It answers typed yes/no, category and score questions with small open models.upstream description
-
jevalyn
The decision layer for your Rails app. A Rails-native wrapper around TypeSafe's Jev System One API: typed, calibrated decisions in your control flow.upstream description
-
jevlogs
Open-source Jev log triage for OpenTelemetry. Score the signal before expensive LLM analysis.upstream description
-
jev-rs
System One judgments (noul/choice/score) from any LLM in one prefill — a Rust, Jev-compatible /v1/systemone engineupstream description
-
jevlint
Configurable semantic linting powered by Jev, with file-level NOUL judgments and a magic-strings plugin.upstream description
-
omp-jev-compaction
Verbatim Jev-scored context reduction for omp, over TypeSafe or OpenRouterupstream description
-
citation-verifier
Check whether each cited paper supports the sentence citing it. Claude proves the quote, TypeSafe's Jev scores it, a human decides.upstream description
-
jevflow
Probabilistic AI decisions as composable backend primitives — typed judgments (noul/score/choice), deterministic thresholds, and explainable workflows. Powered by TypeSafe's Jev, provider-agnostic.upstream description
-
jevmory
Local memory for coding agents: hooks store what sessions actually said as verbatim quotes, and jevmory audit asks Jev, for each line of a MEMORY.md, whether stored evidence supports or contradicts it, marking it keep, stale, wrong or unsupported. Python standard library, SQLite; grading is opt-in.written by a model
-
jevseo
Typed SEO, AEO and GEO judgments powered by Jev, a System One decision model. Code owns the rules, the model owns the meaning.upstream description
-
poorjev
Open-source, local Jev alternative: a System One decision layer with provably calibrated confidence (ECE 0.170→0.071). Typed decisions, runs offline, no API key, no waitlist.upstream description
-
typed-decisions
Jev-shaped typed-decision model (state + Choice/Score/Noul questions -> calibrated probabilities, one pass) on ModernBERT / DeBERTa / LLaDA-MoE, with measured latency, accuracy, calibration and training costupstream description
-
typesafe-jev
Screen a folder of CVs with the TypeSafe Jev decision model: typed judgments, an editable policy, free re-scoring.upstream description
-
heist-one
Observable browser stealth game: Jev makes typed guard judgments while deterministic code owns the world.upstream description
-
jev-local
Local Jev-compatible evaluation server: POST /v1/systemone with typed noul/choice/score, open weights, no waitlistupstream description
-
prompt2jev
Agent skill and CLI that turn natural language, an LLM prompt, or the code that runs one into a TypeSafe Jev decision: typed state, Choice/Score/Noul questions, and a runnable scriptupstream description
-
aside-jev
Aside agents decide with TypeSafe Jev (System One: Choice/Score/Noul). Not a Cua binding — Jev is the model, Aside is the browser runtime.upstream description
-
claude-jev
Claude Code plugin that scores review findings, debug hypotheses and design options with TypeSafe's Jev — calibrated probabilities instead of one more opinion.upstream description
-
jev-as-quant
Typed System-1 decisions (Laya/Jev) as the judgment layer of a quant research stack, with Claude as System 2. Requirements → design → code → experiments.upstream description
-
jev-dsl
Agent-first Haskell DSL for TypeSafe's Jev judgment model: typed packets, inferred types, answers under the same labelsupstream description
-
jev-skill-gate
Cut Claude Code's skill manifest by ~75% with TypeSafe Jev. Scores every installed skill for relevance and hides the rest via skillOverrides — 12,750 → 3,185 tokens on a 217-skill install, for $0.0009 a session.upstream description
-
llama-index-jev
LlamaIndex reranker + router powered by TypeSafe Jev — typed scores/choices, cheaper than LLM-as-judge.
-
luce
Luce: a recipe for calibrated decision models — a sentence about your task in, a small model that answers typed questions with honest probabilities out (init → synth → train → eval → serve)upstream description
-
pytest-jev
Semantic assertions for pytest: test what your LLM app's output means, judged by TypeSafe's Jev.
-
typesafe-local
Inspired by TypeSafe Ai, Ask a local LLM typed questions, get calibrated probabilities instead of text. Structured output without generation or parsing. MLX / Apple Silicon.upstream description
-
dsh-jev-prune
Jev-judged context compaction for DeepSeek Harness: semantic tool-result pruning + deterministic receipt compactionupstream description
-
n8n-nodes-jev-classification
n8n community node for Jev by TypeSafe AI: classify, score and check text with calibrated probabilities. Parallel requests and multi-item batching.upstream description
-
pagegrade
Grade page sections for clarity, writing and on-page SEO. WXT + TypeSafe AI Jev.upstream description
-
system-one-gemma
Open-source Jev-style System One decision model. Gemma 3 270M with a scoring head — fast, calibrated decisions in a single forward pass. No text generation. Inspired by TypeSafe.ai's Jev.upstream description
-
book-aurora
Jev reads a whole novel in seconds. Every passage becomes a row of colour.upstream description
-
jev-judgment
Agent Skill: send closed coding-agent judgments to TypeSafe Jevupstream description
-
jev-ood-calibration
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 ~
-
jevchess
Jev, TypeSafe's System One model, plays chess against any OpenRouter LLM, Stockfish and you. One-page web app with live moves, Jev's move probabilities, saved games and win rates.upstream description
-
jevmetrics
An experimental OpenTelemetry Collector processor that asks Jev how operationally valuable each metric instrument is, from its metadata, then applies deterministic policy to decide what to keep.
-
jevmoji
Type anything. Get related emojis scored 0–3 with Jev.upstream description
-
jevriel
Give your AI JEV wings. A skill and plugin to build with TypeSafe Jev, upgrade LLM-only workflows and measure the result.upstream description
-
limpet
A Stop hook that stops your coding agent from stopping too early. Plain-language rules, judged by jev.upstream description
-
a0-typesafe-ai
TypeSafe AI Jev judgments for Agent Zero, with typed tools and probability cards.upstream description
-
ai-provider-for-jev
Connect WordPress to TypeSafe's Jev System One model for structured decisions (choice, score, noul).upstream description
-
hush
Issue triage that stays quiet when it isn't sure. Calibrated labels, spam and duplicate detection — with abstention.upstream description
-
jev-rl
JEV Reinforcement Learning: four classic games trained with JEV-powered rewards, reproducible experiments and checkpoint replays.upstream description
-
jev-score
Local-first document evaluation workspaces powered by Jevupstream description
-
jev-ui
React components that resolve which component to render, how to order a list, and whether to show an affordance — from calibrated judgments returned by TypeSafe's Jev.upstream description
-
jevshield
Sub-100ms security gate for AI agent tool calls, powered by TypeSafe's Jev (System-1) decision model. Single-request Choice/Noul/Score evaluation, dual-factor blocking matrix, calibrated-confidence routing, fail-closed parsing, zero-config local fallback. LangChain-ready.upstream description
-
leanest
Local-first test selector using Jev judgments to determine which tests are affected by a code changeupstream description
-
qwen-rlcd
Jev-style calibrated decision model (Choice/Score/Noul) on Qwen3.5-0.8Bupstream description
-
typesafe-jev-bridge
Use the TypeSafe Jev decision model (System One) anywhere: zero-dependency OpenAI-compatible bridge for 9Router, Claude Code, Cursor, Cline & any OpenAI SDK. Typed yes/no, choice & score judgments via CLI or HTTP.upstream description
-
ask-jev-ai
A public wall where anyone asks a question in three to fifteen words and Jev, TypeSafe's judgment model, answers yes, no, or it depends in about 100 milliseconds. Every judged ask lands on the wall in realtime, with a running count toward one million, showing cost.upstream description
-
dsh-jev-decide
DSH plugin: register TypeSafe Jev (System One decision model) as an agent tool — jev_decide returns calibrated probabilities (noul/choice/score) for routing/triage/guardrail judgments, no text generation. 把 TypeSafe Jev 决策模型注册为 DSH agent 工具upstream description
-
jev-mode
I kept watching coding agents burn context on decisions that aren't hard - triage 400 tickets, tag 600 files, route to one of six teams. jev-mode moves those verdicts to a typed-judgment model. I A/B'd it: 78% fewer tokens, 16x less work-attributable input, accuracy 96.1% vs 93.7%. Python, no d
-
JevPromptCoach
Claude Code plugin that scores how well you prompt a coding agent, and shows whether your habits are improving. Runs on TypeSafe's Jev model. Zero added latency.upstream description
-
tenbin
MCP server and agent skill for the TypeSafe AI System One API (Jev): decompose a judgment into Choice / Score / Noul questions, lint them, measure on labelled data, and put calibrated thresholds in codeupstream description
-
typesafe-cli
Ask Jev typed questions from the shell: noul, choice, and score answers as numbers, not proseupstream description
-
vgi-typesafe
A VGI worker exposing TypeSafe System One questions (choice, noul, score) to DuckDB/SQL as LATERAL-joinable table functionsupstream description
-
dsh-jev
DSH bundle that registers jev_ask for TypeSafe Jev noul, choice, and score answers.upstream description
-
jev-builder-loop
Grok skill: Jev as a judgment sensor in a builder-agent loop (priors × probabilities → next act)upstream description
-
jev-compaction
Context compaction for Hermes sessions that never summarises: every tool call is scored by TypeSafe's Jev model, stale calls are dropped, everything kept stays verbatim.upstream description
-
jev-flash-router
open-sourced jev-flash-router: an MCP server for TypeSafe's new Jev model. AI coding agents waste hundreds of reasoning tokens just deciding which file to edit, which route to pick, or whether a diff breaks tests. Jev evaluates state and outputs calibrated probabilities. Works with Cursor, Wind
-
jev-mcp-server
MCP server for Jev (TypeSafe System One): the three official question types — choice, score, noul — plus batch classify. Calibrated probabilities, ~0.5s, <$0.001/call.upstream description
-
jev-workbench
Build versioned judgment functions on TypeSafe's Jev once, then call the same published version from your backend over HTTP and from coding agents over MCP. The vendor key stays on your machine.upstream description
-
jev-wrapped
Telegram channel X-ray: Jev judges a year of posts, you get a card. One Cloudflare Worker.upstream description
-
jevbus
A streaming event bus whose routing, subscription and consumption are decided by a probabilistic judge. The reference judge is TypeSafe AI's Jev (System One) model: send it a payload and a set of typed questions, get back calibrated probabilities instead of prose.upstream description
-
jevseek
JMP — Joint Model Participation. A local coding workspace where Jev routes actions and OpenAI, DeepSeek, or local models generate arguments.upstream description
-
pi-typesafe-jev
A pi extension that exposes TypeSafe (Jev, System One) judgments as five pi tools, so a model can make narrow semantic judgments while your code and your users keep control of thresholds, weights, and actions.upstream description
-
tripwire
Judge every LLM response before the user sees it. AI SDK middleware and OpenAI-compatible proxy.upstream description
-
clarity-judge
Multi-axis writing quality checker powered by TypeSafe AI's Jev model. Separate named checks, each with its own verdict and confidence.upstream description
-
clear-head
Claude Code Stop hook that checks an AI assistant's claims against what it actually read this session, using TypeSafe's Jev as the judgeupstream description
-
decision-first
Agent skill for Claude Code, Codex, Cursor and more: when a step is a bounded judgment (classify, triage, rank, route, filter, verify, gate), the agent tries Jev first, via a bundled script sending noul, choice or score questions, before a regex or LLM prompt, and logs each attempt, adopted or not.written by a model
-
jev-carryforward
What your last session knew, scored against what this one is doing. MCP server: a per-project ledger written as things happen, recalled per task with TypeSafe's Jev evaluation model via Vercel AI Gateway.upstream description
-
jev-model-router
Cost-optimized OpenRouter model router using TypeSafe's Jev, with a live full-catalog scorer instead of a hardcoded model listupstream description
-
pi-jev-permit
A Jev (TypeSafe System One) permission gate for the Pi coding agent: judges every bash / write / edit call before it runsupstream description
-
watfile
Text/PDF - File categorization and sorting with Typesafe AI Jev or local calibrated decision modelupstream description
-
draftpulse
Experimental: live X draft viral scorer powered by TypeSafe Jevupstream description
-
dsh-jev-verify
Jev (TypeSafe System One) decision tools + live verification benchmark for DeepSeek Harness: jev_decision (choice/score/noul) and jev_verify, honest by design.earlier upstream description
-
gpt-vs-jev
Compare GPT generated language with JEV structured Noul decisions on the same input.upstream description
-
instruct-jev
INSTRUCT_JEV - TypeSafe AI Jev / System One instruction corpus (choice/noul/score), compiled by DeckerGUI. 119 rows. Mirrored on HuggingFace.upstream description
-
jev-certify
Finite-sample guarantees for Jev (TypeSafe's System One). Conformal risk control turns calibrated probabilities into certified routing thresholds; prediction-powered inference audits them. 2,412 decisions on CLINC150 for $0.23 — including the shift and prevalence cases where the guarantee break
-
jev-hooks
Compose typed Jev judgments as reactive semantic state in React and backend programsupstream description
-
jev-paper-judge
Feedback on your paper in seconds.upstream description
-
jev-songwriter
A decision model that cannot write a single note writes songs. Code computes, Jev judges, and every call is replayable.upstream description
-
jevaluate
Jevaluate: evaluate before you trust. Field notes, runnable scripts and an agent skill for TypeSafe Jev: gated evals, a browser loop, a product walk with DeepSeek vision, a UI text judge and a first-click tree test. Co-authored with Claude Fable 5.1.upstream description
-
judging-with-typesafe
Скилл для агентов Letta: суждения по критериям через TypeSafe System One (Jev)upstream description
-
padflow-jev-evals
Typed-decision benchmark from PadFlow (land development SaaS): schemas, anonymized labeled rows, and a runner for confidence-calibrated models like TypeSafe Jev.upstream description
-
s1-rs
Typed System One layer for Rust (Choice/Score/Noul).upstream description
-
typesafe-as-a-judge
Unofficial community MCP plugin for Codex and Claude Code using TypeSafe Jev for bounded routing, ranking, extraction, verification, and escalationupstream description
-
typesafe-showcase
Next.js UI showing off TypeSafe's System One model (Jev) — parallel Noul judgments and a Choice-based citation checker, deployable to Vercelupstream description
-
A deep dive into Jev, TypeSafe's System One model
The densest independent explainer: code in JS, Python and the AI SDK, all three answer shapes, the advanced patterns, and an honest list of where the model fails.
-
decide-mcp
Configurable decision MCP server with AI SDK, Jev, percentage scores, and bias profile routingupstream description
-
deslop
Score web pages for ads, slop, SEO and second-hand content. An agent skill built on TypeSafe Jev: four probabilities per page, no verdict, the caller sets the thresholds.upstream description
-
github-issue-classification-using-jev
This repository contains a GitHub issue classifier built on Jev, TypeSafe AI's System One model. It labels every new issue with typed values and calibrated confidence in milliseconds, labelling what it is sure about and escalating what it is not. Three guardrail layers guard every write, and a
-
harnessjudge
Web app for agent builders: paste the trace of one agent step and Jev judges it as ok, retry, escalate or stop. Without a TYPESAFE_API_KEY, local heuristics return answers of the same shape, labelled as demo mode.written by a model
-
JEV Trading Command Center
Paper-trading research app with a 3D command center. For a USDT futures symbol it asks Jev the direction for the next 1 to 4 bars (long, short or no trade), a `score` for entry quality and three `noul`s (valid setup, trap risk, acceptable risk); code gates every simulated entry on the answers.written by a model
-
jev-asks-until-sure
A twenty-questions guesser that keeps asking until Jev's calibrated confidence crosses a threshold — or gives up and says soupstream description
-
jev-decision-lab
A local lab for seeing what TypeSafe's Jev judgment model does on realistic business cases: typed answers, probabilities, policy in code, receipts.upstream description
-
jev-gates
Six calibrated gates for Claude Code, judged by TypeSafe Jev: rules, scope, intent, done, claims, and commit honesty. Each one escalates, none ever approves.upstream description
-
jev-llm-router-benchmark
Benchmark-driven Jev router and judge for cost-aware, reliable LLM coding workflowsupstream description
-
jev-orderby-bench
Does ORDER BY over a Jev probability put rows in a defensible order? Independent ranking, calibration and invariant measurements of TypeSafe AI's Jev: passes six pre-registered gates on 360 labeled rows, fails four of six on graded product relevance.upstream description
-
jev-packs
Evidence-gated registry of Jev question packs — curated questions, golden cases and measured evidence for Jev-compatible decision endpointsupstream description
-
jev-seo
Audits a business website for SEO and AI-answer-engine visibility. A deterministic crawler measures each page, then one request sends Jev a batch of narrow typed questions about it, and the answers are surfaced as probabilities in a dashboard.
-
jev-shadcn-lint-eval
A small second eval for shadcn-ui/lint that uses TypeSafe's Jev to judge the linter's own output.upstream description
-
Jev-test
A CLI and REST API that asks Jev how exposed an occupation is to AI-driven layoffs, where it is heading, how much human accountability it needs, and how resilient it is.
-
jev-trace-classifier
Application of TypeSafe Jev (noul judgment primitive) on the collusion.wiki corpus: agent vs human page authorship, head-to-head vs local Qwen3.8-Flash-Nextupstream description
-
jevplay
TypeSafe Jev playground — custom Choice/Score/Noul builder with live distributionsupstream description
-
n8n-nodes-typesafe-ai
n8n community node for the TypeSafe AI System One API — typed yes/no, choice and score questions with calibrated probabilitiesupstream description
-
omp-jevens-classifier
Jev-powered model-judged permission gate for OMP (TypeSafe System One)upstream description
-
s1s
System One Search: navigate and trace code with TypeSafe judgments and repository evidenceupstream description
-
shady-town
Shady Town: social-deduction party game for the living room TV, moderated by TypeSafe Jevupstream description
-
sloppy-jevs-extension
Open-source Chrome extension that filters AI-generated prose and ads with Jevupstream description
-
spendbrake
Agent budget brake — continue / downgrade_model / stop via TypeSafe Jevupstream description
-
transcript-scorecard
ACME live support-call scoring demo with TypeSafe AI, Effect, SQLite, React, Vite, and Turborepoupstream description
-
typesafe-demo-mcp
MCP server exposing TypeSafe System One judgments (noul, choice, score) as agent toolsupstream description
-
typesafe-triage-guard
Three composable judgment pipelines on TypeSafe's Jev: support-ticket triage, observability alert triage, and a deploy-risk gate.upstream description
-
typesafeai-review
Using Typesafe.AI to generate diff reviews.upstream description
-
zcode-jev
Typed judgment layer for coding agents — gates from PRD to ship. Jev-ready, provider-agnostic.upstream description
-
jevai.org community showcase cases
Nine worked community scenarios: intent routing, invoice classification, news filtering, product tagging, moderation, claim verification, CSV validation and more.