Best Jev Projects

Trading research agents with optional Jev screening of social posts for company relevance and sentiment.

AI gateway with a TypeSafe guardrail and Jev classifier for policy judgments and complexity-based request routing.

Coding agent with a TypeSafe judgment provider that uses Jev for typed checks, routing, and workflow decisions.

Claude Code configuration toolkit shipping Jev-based model routing, skill suggestion, and tool guardrail modules.

Computer-use platform with a Jev recipe where the model selects one bounded action candidate and the client validates it before execution.

Open-source Claude Cowork alternative whose eval testkit can use Jev as a typed verification judge for agent-produced work.

Generative UI framework with an experimental evaluator that lets Jev choose among application-supplied composition criteria.

Multilingual, non-autoregressive System 1 decision engine. Typed decisions over 100+ languages in a single forward pass — 33 ms — trained with reinforcement learning against strictly proper scoring rules (RLCD), with a router that picks the right checkpoint per request.

Open-source AI Trading OS, agent trading, and vibe trading, with Jev System One integration. Research, build Python strategies, backtest, and paper/live trade across crypto, stocks, and forex. Launch your own multi-tenant trading SaaS with built-in user management, billing, payments, and settlement.

Browser Use's ultrafast agent: Jev picks the operation and DOM element in one request; a small LLM only writes text when typing is needed.

Jev assigns a calibrated relevance score to each of the top 20 locally recalled files and reranks the search results.

Vercel's open agent framework, which ships Jev as the default evaluation model in its experimental evaluate path.

Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.

Open-model semantic-if engine for local Jev-style decisions.

Agent memory search with optional Jev relevance judgments to rerank retrieved passages.

Jev scores whether each retrieved document answers the query and reranks the search results by that relevance.

Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.

Desktop AI assistant with a Jev plugin for typed classification, routing, verification, and scoring.

Project management app using Jev for agent routing, task fields, assignee selection, and automation conditions.

Android conversation copilot where Jev interprets chat context and helps rank candidate replies before the user inserts one.

Trainable family of small Qwen-based Jev-like decision models with typed primitives, datasets, evaluation tools, and local inference.

Desktop automation runtime with a Jev skill that chooses UI operations and targets from accessibility-tree candidates.

Team agent workspace using Jev typed decisions for response routing and model selection.

One AI trade decision every Monad block. Jev on Kuru MON-USDC.

Laravel AI SDK with a TypeSafe provider for Jev Choice, Score, and Noul classification requests.

Open 0.6B Jev replica with parallel decisions, complete probability distributions, training pipeline, weights, dataset, and live demos.

Train a small model that chooses among a changing list of text options, one probability per option in a single pass. Includes Doom, chess, and Wikispeedia demos.

Agent architecture examples that use Jev for fast typed control decisions.

Agent-computer platform with a runnable pull-request review lab where Jev judges whether findings are introduced, supported, and actionable.

Runtime perception layer that gives web and desktop agents Jev-style machine-readable state.

Vercel Labs terminal CLI that can run Jev as the evaluation model for its evaluate command.

Official agent skill for Claude Code, Codex, and compatible agents: primitives, patterns, and how to structure evaluations.

Agent memory library with an optional Jev reranker that judges which retrieved memories are relevant.

Coding-agent runtime using Jev decisions for model routing, context retention, and tool selection.

The OpenRouter provider for the Vercel AI SDK contains support for hundreds of models through the OpenRouter chat and completion APIs.

Conversational-avatar framework with a Jev gate that judges whether a speaker has finished a turn.

Local Jev-compatible System One API that converts typed questions into DiffusionGemma classification prompts and probabilities.

Decision-oriented directory of 152 linked Jev tools and practices, with inclusion criteria, caveats, and source attribution.

Evidence-backed Jev use cases, patterns, prompts, and starter code.

Optional Jev commands find, filter, and verify browser elements, then select bounded actions subject to confidence and write-authority checks.

把 Computer Use 的「下一步点哪里」交给 Jev（TypeSafe System One）：Jev 从界面文字候选中选元素、动作、完成度与风险，Codex Computer Use 负责读取界面与执行，本地策略门槛拦截敏感操作。 Only send text, not screenshots..

Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.

The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.

Windows WeChat reply assistant that uses local OCR and Jev to classify intent before presenting three manual-send replies.

Awesome Jev: a source-backed field guide to TypeSafe's System One model, with SDKs, live demos, agent tools, and independent evaluations.

Open-model Jev-style server that reads next-token logits to return typed choices, rubric scores, and truth judgments.

VexJoy AI Agent with Jev Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop.

When explicitly enabled, Jev selects an astrology technique when keyword routing has no match and extracts settings stated by the user.

Agentic TypeScript workflow framework with a Jev session checker wired into its workflows.

A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions.

Software Factory Foreman: an agent supervisor that uses Jev decisions to keep coding agents on task.

An awesome collection of Jev use cases, workflows, and agent skills.

非自回归System 1决策引擎，专为结构化类型决策场景设计 DeepOpen Multilingual, non-autoregressive System 1 decision engine.

Jev scores agent progress, tool use, focus, exploration, recovery, and token efficiency from Claude Code session logs.

A staged code-review workflow and local dashboard built with TypeSafe Jev.

At each debugger pause, Jev chooses the next debugging action from the stack, locals, nearby source, output, and prior attempts.

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

Hermes plugin and skill suite using Jev for model routing, skill selection, memory filtering, compaction, and GUI actions.

Stock-analysis application that uses Jev for structured market judgments.

Tax-document classifier where Jev selects an IRS form and page kind from extracted PDF text.

A very fast document classifier/splitter using Jev.

Run Laya, the open-source Jev-compatible System-1 decision model, from Node.js / TypeScript via ONNX Runtime.

When enabled for Codex runs, Jev reviews diagnostic tests and incident-resolution submissions from the supplied evidence.

A TypeSafe/Jev agent that plays Super Mario Bros. from structured emulator state.

Build calibrated AI Functions from human feedback using Jev and GEPA.

Scala client module for TypeSafe System One that submits Jev Noul, Choice, and Score questions and returns typed answers.

Jev classifies incoming WeChat or QQ messages by intent and risk before the app presents reply guidance.

Jev-compatible API server built on open models and SGLang, with prefill-only inference and typed decision endpoints.

Search the web with TypeSafe's Jev: source selection, query understanding and relevance ranking. Built with Search1API.

Standalone Android agent for Mobilerun where Jev makes every decision, with a live React studio and an Uber demo.

AgentJev-0.6B - a fast 'System One' decision model for AI Agents: feed it any unstructured state (diffs, traces, logs) and structured questions, get calibrated probability distributions back in one ~50ms forward pass. Zero output-token decoding.

During assurance evaluation, Jev estimates how likely a proposed agent trajectory is to satisfy its bounded objective.

Open source, terminal-first AI coding agent with fully transparent multi-model routing. Local (Ollama, LM Studio, MLX, llama.cpp) or cloud, your keys, one TUI. No black box.

Open probability decisions with Qwen3.5-2B, Qwen3.5-9B and Qwen3.8-27B.

The open, local take on Jev: typed decisions from an LLM, without generating a single token

One offboard CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain (Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM) and a decision LLM for cheaper and faster steps (Jev, Laya, and Kev). Supports Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot, Jetson, or any ROS.

Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev.

The optional Jev prefilter scores transcript segments before the selected material is sent to the summarizer.

A curated, source-backed list of projects built with Jev, TypeSafe AI's System One model for typed decisions.

Route to the cheapest model in claude code for your task using jev-router.

Jev compares items against a ranking prompt across repeated batches so SiftRank can produce a converged relevance order.

5–10x faster browser operations: Jev clicks, Codex thinks and verifies. Built at EZCollegeApp.

Self-hosted, versioned skills library for AI agents with optional Jev recommendations through TypeSafe or an AI gateway.

Tasksource recasts hundreds of classification datasets into Jev-compatible typed questions, answers, and procedural training examples.

Marketing analytics platform whose feature flag routes brand-visibility classifiers off an LLM and onto Jev boolean decisions.

Self-hosted Jev-compatible System One server backed by GLiNER-family models, with batching and typed question support.

Crush Favorability Monitor: Use Jev to analyze the emotions, intentions and reply performance of WeChat chats. Deploy locally, use your own API Key..

An easy way to use jev with your coding agent for tool calling reasoning.

Adaptive reasoning effort for GPT-6 Astra during Codex tasks, powered by Jev to reduce token usage.

Curated Jev demos, projects, SDKs, skills, source links, and an X showcase gallery.

Agent plugin that uses Jev to judge when a coding session should compact its context.

Semantic code linting with Jev.

Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.

Official drop-in TypeSafeClient replacement backed by OpenAI, Anthropic, and compatible LLM APIs, for comparing Jev against chat models.

Supervises coding-agent edits and uses Jev to flag violations of project rules.

Machine-readable bilingual Jev example catalog organized by decision pattern, with call-site vetting, compatibility notes, and CI link checks.

DiffusionGemma NVFP4 structured decisions on a DGX Spark: container recipe No repository-level license file was found during review.

Official TypeScript/JavaScript client with inferred answer types. npm install @typesafe-ai/sdk.

A source-backed Jev project directory with a reusable Jev-only GitHub review workflow.

EmbodiedJev: MuJoCo robot decision workbench with MiniCPM5-2B, Jev and compatible model APIs

OmniStudio exposes Jev Noul, Choice, and Score decisions for triage, scoring, content guards, retrieval reranking, and intent routing.

Coding agents can ask Jev to judge small workflow decisions, such as whether build results look healthy.

An on-demand crypto market intelligence and decision-support terminal powered by TypeSafe AI's System One model (Jev).

🔥🔥 Papers, open reproductions and independent evaluations behind System One models and Jev.

Browser use using Typesafe's Jev model.

An educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos.

Anna uses Jev as a fast judgment layer for bounded enterprise-agent recommendations and abstentions.

API server runtime for common AI use cases — supports multiple models and providers. Run locally with Ollama or LM Studio, or in the cloud via OpenRouter, OpenAI, Anthropic, or Google.

Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating).

Open, Jev-compatible System One decision server on DiffusionGemma.

WXT browser extension: Jev-powered page clutter removal with reusable template rules.

Unified AI SDK whose TypeSafe decide API supplies typed judgments for model routing, compaction, tools, and retrieval planning.

Awesome Jev: source-backed open-source ecosystem radar, plain-language project discovery, and automatic GitHub sync.

Claude Code and Codex hooks that ask Jev which parts of long shell output remain relevant before sending them into model context.

Benchmark comparing Jev Choice answers with LLMs on four-option questions about Convex.

Jev selects the next UI operation from the targets and actions exposed by the current desktop state.

Official sync and async Python client. pip install typesafe-sdk.

Control a real browser by voice. Jev (TypeSafe System One) decides intent + target in ~300 ms per spoken word; Playwright acts — often before you finish the sentence.

Smart web search CLI for agents, backed by Jev. Saves a lot of tokens.

grep by meaning, across languages. TypeSafe Jev scores every line against a meaning; combine meanings with AND/OR/NOT. 意味で探す grep。日本語で英語を、英語で日本語を検索できる

Curated index of Jev projects, integrations, and learning resources.

A fast browser-use skill powered by local LLMs via single-token reflexes. Fast, local-first, zero hallucinations.

Proof of concept MCP for Typesafe's new Jev AI model.

A skill for writing and improving programs that call Jev, TypeSafe's System One model.

Go CLI and single-binary MCP server exposing TypeSafe judgments to Claude Desktop, Claude Code, and Codex.

Same as jev-ultrafast but using Laya.

Adapter that turns local language models into Jev-style Choice, Score, and Noul decision engines with typed probabilities.

Bounded TypeSafe Jev workflows for coding agents.

Code-quality and coverage reviewer that uses Jev to judge coding-agent changes.

A small extension that demos the combination of Jev x WebMCP.

Contrastive language model for one-pass typed decisions and option probabilities.

OpenSource Jev.

Jev ranks command-palette entries against a plain-language query so the intended terminal action appears first.

One-pass typed decisions with calibrated probabilities (System One style model), fine-tuned from Qwen3.5-2B.

Desktop browser where Jev selects executable browser actions and a separate text model handles planning.

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.

CLI and MCP server for Forma benefit claims that can use Jev to classify receipt line items into reimbursement categories.

Guardrails for Pi built on pi-typesafe that steer the agent instead of interrupting you: Jev judges irreversible and off-task tool calls, detects stuck loops, checks unverified done claims, flags slop.

Jev model introduction and actual measurement: use Choice / Score / Noul to convert natural language into typed judgments and probabilities for classification, scoring and routing; supports comparison of comment marking, speed and results with models such as DeepSeek, including CSV/Excel import, original speed playback and offline reporting..

Personal-assistant agent built on Vercel's eve with 100 mocked tools, measuring how many steps it takes when Jev picks the tool versus the LLM.

Jev Chat Assistant for Windows - PC version of WeChat intent judgment and DeepSeek suggested reply.

Indexed browser automation where Jev selects a control and Playwright executes it.

Say it, and your Mac does it. A computer-use harness on Jev that reads the screen through Accessibility. Fast, no vision model.

TypeSafe Jev as a decision layer for the Pi coding agent: a measured tool-call gate plus jev_ask for typed, calibrated answers.

A tool calling chat bot built with Jev and no LLM.

A lightweight Jev-powered router for models, tools, and subagents.

Four agent skills use Jev Score and Noul judgments to assess subjective criteria with calibrated probabilities.

Laya vs Jev: local MLX and hosted AI decisions playing T-Rex side by side, with live metrics and replay recording.

A curated list of awesome Jev / TypeSafe System One applications, libraries, and resources.

A small, type-safe client for asking AI questions about your data, powered by TypeSafe Jev.

Intraday trading bot where Jev ranks Nifty 50 candidates and deterministic code controls position sizing and risk.

Left-pad strings with TypeSafe AI's Jev. For reasons.

Talk to your Mac. Local whisper.cpp + one Jev (TypeSafe) call per command + macOS automation.

Awesome list of TypeSafe AI Jev use cases: 74 demos ranked by likes, 150+ GitHub repos, limits, cost and API examples. CC0, sponsored by AY Automate.

Pre-alpha PostgreSQL extension for TypeSafe AI (Jev) categorical classification.

A small open decision model: state + typed questions -> calibrated probabilities. A Jev / System One re-creation on Qwen3.5.

Camera-only autonomous drone in MuJoCo with a small judgment model (TypeSafe Jev) in the loop at 2.5Hz.

When enabled, Jev performs bounded editorial and title checks on stories selected for an Earth changelog edition.

Community directory of projects built on Jev and TypeSafe System One.

Per-turn model & reasoning routing for Codex, driven by Jev (TypeSafe System One): picks the model, thinking depth and speed mode for every turn.

Bounded TypeSafe Jev workflows for coding agents.

Scientific-agent architecture separating fast local judgment, probabilistic evaluation, evidence, and authorization.

Curated Jev resources and runnable examples for typed AI decisions.

Jev triages malware-scan findings and supplies typed Noul, Choice, and Score decisions for WordPress maintenance.

Grok Bot integration where Jev applies usage gates and routes requests before the generative model runs.

Put a live Jev (TypeSafe) meter on any video: every sentence scored, rendered as a 16:9 edit.

Rust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, abstention, and local feedback. Requires a TypeSafe API key.

Solana liquidity agent with optional Jev shadow judgments for deposit choice, toxic flow, and market-regime stress.

WebMCP benchmark comparing browser-agent interfaces, with Jev included as one of the evaluated configurations.

Papers, open reproductions and independent evaluations behind System One models and Jev.

Jev checks retrieved memories for contradictions before an agent uses them in an answer.

Train small, insanely fast local classifiers from Jev-compatible examples. Run locally in your browser or Node.js.

JevBench v1 - a benchmark for Jev-class typed decision models: smart, cheap, fast, reliable, open.

Portable, Jev-guided context compaction for coding agents.

Fish-style zsh history autosuggestions ranked by Jev (TypeSafe).

An input that becomes what you mean: one text box that morphs into the right UI as you type. Powered by TypeSafe Jev, works offline.

TypeSafe Jev action selection inside Codex Computer Use.

Milvus model library with a TypeSafe Jev reranker provider for semantic search.

Jev classifies JMeter agent intent and selects a focused tool pack, with a full-tool fallback when routing is uncertain.

Jev chooses camera moves, emphasis, and timing from a rendered Playwright recording and bounded direction candidates.

When enabled, Jev classifies article topics and relevance for WeChat daily digests.

CLI that uses Jev task classification to choose and launch Cursor, Claude Code, Codex, or OpenCode with an appropriate model and effort level.

Jev evaluates market state from completed candles, live prices, positions, and strategy constraints, then suggests observe, open, or close actions for human approval.

🧹 Fun project: a Chrome extension that asks a tiny AI decision model (TypeSafe Jev) "is this DOM element an ad?" and pops it off the page. BYOK, no backend, not a real ad blocker.

> This package is experimental. Use at your own risk.

Semantic grep CLI where Jev judges which files and exact line ranges match a natural-language code query.

Jev uses one typed Choice question to select each narrative action from the options available at a Detroit: Become Human decision node.

BeamWeaver exposes Jev Choice, Score, and Noul evaluations as provider-neutral decision-model calls in Elixir workflows.

One-pass option scoring with a local Gemma 3 4B on Apple silicon via MLX, inspired by jevlike, with a Doom demo.

Jev / TypeSafe System One 中文精选列表：官方资料、SDK、爆款应用、Agent 工具、开源复现与独立评测，附中文上手指南，每日自动收录 GitHub 热门项目。

Text linter that uses Jev Score judgments to evaluate strings embedded in source code against configurable writing rules.

WeChat plugin that uses Jev to analyze message intent, emotion, and reply posture locally.

Stops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger, zero runtime dependencies.

Give an agent real hands and eyes: undetectable, DOM-independent GUI automation. A $4 USB-HID microcontroller for hands, a vision grounding model for eyes, any LLM for a brain.

Open-weight Jev alternative that returns typed decisions with probabilities in one forward pass.

AI-powered Log Intelligence System - Semantic search, anomaly detection, and root cause analysis for logs using RAG techniques. Built with Rust, Axum, NATS, ClickHouse, and Qdrant.

Use Jev to make art!.

Ruby client for decision models such as Typesafe Jev

Provider-neutral System One runtime for TypeScript and the Pi coding agent.

A Jev powered LinkedIn recruiting agent. Watch it browse relevant profiles, save links, and review evidence against your hiring brief.

Open semantic decision engine implementing Choice, Noul, and Score primitives with a TypeSafe comparison harness.

Claude Code plugin where Jev decides which project rules apply to each prompt and edited file.

Agent plugin and MCP tool where Jev classifies batches of text so agents can read only the relevant items. No repository-level license file was found during review.

An open-source JEV-powered workbench for streaming data selection, quality evaluation, automatic LoRA training and held-out model evaluation.

LIBERO robot-control environment where Jev chooses fine-grained actions using task state and physics previews.

Full-stack agent harness with memories, long-running tasks, multi-agent relay, and a Jev-backed model-routing table.

Chrome extension: vibe-check your X posts with TypeSafe's Jev before you hit Post.

Jev judges whether a cached computer-use workflow is semantically reusable for the current request.

Jev-style parallel constrained decisions for any MLX model on Apple Silicon. Typed, schema-valid JSON in one forward pass.

Open reproduction of TypeSafe Jev: a 150M typed decision engine (noul/choice/score in one non-autoregressive pass, calibrated confidence). 0.697 vs Jev's 0.727, 2.5x better calibrated, 4x faster, free. Trains on a Colab T4 in 30 min.

Type-safe language-model generation and structured decisions.

An LLM + Jev workflow. Boost your vertebrate brain with a spine inside.

An unofficial local visualizer for Jev (TypeSafe): a live view of every call your code makes. Not affiliated with TypeSafe AI.

Solar Mini–based local model for Jev-style typed decisions.

Ableton Live controller where Jev maps a short natural-language request to a bounded music-production action.

Route HTTP requests by meaning. A semantic router for Hono powered by Jev.

Self-hosted API and web interface for Laya decision models with a Jev-compatible API shape.

We only curate source-reviewed JEV-related projects with 100+ GitHub stars — integrations, tools, open models, and experiments. Live gallery: beatapi.io/awesome-jev

Typesafe.ai System One Model Jev navigating a Neo4j graph by using a classifier over neighbouring relationships.

MuJoCo xArm7 study where Jev chooses movement directions and gripper actions from physical feedback.

Jev chooses the next step from bounded options and records that choice in Tocket’s shared project notebook.

Crypto decision dashboard that uses Jev to classify market state and risk.

Real-time Discord moderation bot: Jev evaluates messages and metadata in parallel to catch phishing, spam, and social engineering with a progressive escalation ladder.

Probability-tree and graph runtime for verifiable multi-step Jev decisions.

Open visual decision model that encodes an image once and answers multiple structured questions.

Four decision-quality applications where Jev answers structured questions and deterministic code keeps final authority.

The cli-jev transport routes typed-judgment requests from the skill harness to the Jev CLI and MCP interfaces.

Decision plugin for DeepSeek Harness and iPolloWork that lets OpenCode, Codex, and other agents use Jev to select tools, skills, and task owners and evaluate outputs.

Exchange deposit and withdrawal risk-triage gateway where Jev triages and deterministic code adjudicates.

Two-stage JEV control of a Franka Panda in MuJoCo.

Jev-style structured decisions on DiffusionGemma: the example server from vLLM PR 57250.

ACP and MCP adapter that exposes Jev typed decisions and computer-use actions to Codex, Claude, OpenCode, and other agents.

Call-coaching application where Jev evaluates conversation context to surface structured coaching decisions.

Jev-Mem: System-One Controlled Agentic Memory.

macOS voice and text control where Jev selects UI actions in an observe–act–verify loop.

Skill for Hermes, and other agents, to ask typesafe's jev.

Obsidian plugin for AI chat, workflow automation, and semantic search — supports Gemini, OpenAI, OpenRouter, Grok, Ollama, and CLI backends.

The highly anticipated open-source repository for JEV as Policy enables one-click setup of the simulation environment. Evaluations of Astra + JEV on benchmarks such as RoboTwin will also be released soon.

Isolated Playwright Chromium driven by Jev. A coding agent (or you) runs a.

Training stack for a multimodal Jev-like System One model with vision.

Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev.

StarCraft agent experiment using Jev for fast tactical decisions.

Supersimple way to serve LLMs as a Jev-like endpoint.

This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev.

Astra uses native Jev judgments to inspect agent context and choose evidence-backed runtime actions.

用 TypeSafe Jev 推荐已安装 Skill / Bounded installed-skill recommendations with TypeSafe Jev. Python CLI, Codex skill, bilingual docs and live examples.

Training and inference stack for calibrated Jev-style choice models with dynamic candidate sets.

Live SEO audit for any website from one homepage URL, judged by Jev. PDF, XLSX and Markdown reports.

Turning an LLM model into a Jev like System.

Calibrate Jev questions against your own labels: tune criteria on labelled examples, confirm on a held-out set, get a verdict per question. Unofficial.

A Java SDK for the TypeSafe AI JEV API, & Spring AI TypeSafe integrations.

CC0, awesome-lint-clean Jev list organized by what users can install, with model limitations documented up front.

Systematic-review extraction app where Jev answers structured review forms and points reviewers to quoted source lines.

Unofficial PoC: a BERT-style encoder decision engine behind a typed-decision (noul / choice / score) HTTP API. Not affiliated with TypeSafe.

open-jev is a browser-focused TypeScript library for typed decisions: one piece of text (the state) plus any number of typed questions go in, and one forward pass returns a calibrated probability distribution per question. Nothing is generated, so an answer is always one of the options you provided.

Filter your X.com feed with Jev or any LLM.

Live Jev trader on Hyperliquid.

Open Thai-English System One model with Choice inference, calibration, evaluation scripts, and a Jev comparison suite.

Rank Pi Agent Skills for the current task with TypeSafe Jev.

Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground.

Open model for typed, calibrated decisions in one forward pass.

Semantic code search CLI and MCP server: Jev scores authorized repository excerpts and returns exact file paths and line numbers to coding agents.

The jev.ask runtime global lets sandboxed TypeScript programs request calibrated Jev Noul, Choice, and Score answers.

Jev Explained.

Read-only Gmail triage app where Jev assigns each message a tray, urgency score, and human-authorship judgment.

Multi-agent AI news pipeline powered by GLM-5.3-Flash and Jev.

Random Jev-compatible baseline that emits Noul, Choice, and Score probabilities for mocks, lower-bound comparisons, and router evaluation.

Permutation Invariant Jev.

Is it even? Ask Jev.

A Clash Royale bot with no trained policy: Jev (TypeSafe System One) makes every decision from the live game state.

Classify Git commit diffs and messages with Jev. Bug fixes, security fixes/CWEs, and change types.

Pi extension with a batched Jev evaluation tool, terminal playground, and typed API for other extensions.

A calibrated context sieve for Claude Code: every tool result is judged by a System One model before it enters context.

Document OCR router where Jev judges page by page whether the existing text layer is usable or OCR is required.

Read-only trading journal and review harness: Jev typed judgments, agent integration, and a reproducible finance benchmark. No orders, no advice.

Self-improving agent harness with an optional TypeSafe Jev companion for typed Choice, Score, and Noul judgments.

ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.

🚀🚀 A 0.8B JEV-like multimodal model playing GUI games directly from raw pixels.

Laya (open source, local) vs TypeSafe Jev (API): two AI models race in Snake and fight in a Mortal-Kombat-style arena. Every move is a real model decision.

Open probabilistic Choice, Noul, and Score API powered by constrained open-model log probabilities.

Home Assistant integration for TypeSafe Jev. Ask a question about your house and get a probability, a choice or a score as an entity.

Codebase search powered by Jev from @typesafe-ai.

SwiftPM client for the TypeSafe System One API with typed Noul, Choice, and Score questions.

MCP tools that expose Jev for verification, screening, classification, reranking, review, gating, and scoring.

Mini-Jev: what a Jev-style typed-decision interface looks like on a frozen Qwen3-4B — read the option letter's logits instead of generating JSON. Preregistered experiment, results, teaching bench.

Independent, evidence-based map of when TypeSafe's Jev actually holds up vs. breaks down — real API-call receipts, not a leaderboard. 中文为主的双语 repo。.

A spatial reference explorer for creators. Local Jev query choices, metadata highlights and source-linked collections.

JEV HUB · X 上关于 TypeSafe AI「系统一模型」Jev 的长文与演示视频聚合（保留原链与作者）｜ 谁是专家 出品

Experimental browser agent powered by FX, Jev, and Vercel AI Gateway. Bring your own API key to read pages and automate browser tasks.

Rust System One–compatible API for open decision models such as Laya.

Jev shadcn-block generator.

Agentic GraphRAG pipeline with swappable local Laya or cloud Jev decision models.

A prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model.

SillyTavern extension where Jev scores replies against configured narration rules before adding guidance.

Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.

AI diagnostic agent for ROS 2 robots — evidence-based, tool-calling, safety-gated.

Serve typed-decision (System 1) models — Laya or your own — on NVIDIA GPUs or Apple Silicon, with a Jev-compatible API and coding-agent integrations.

Video editing pipeline where Jev judges transcript segments to select highlights and remove filler.

⚡ Millisecond-level Viral Hook Telemetry & Co-pilot for Social Media (Chrome Extension + JEV System 1).

RikkaHub Plus Huadeng Edition - Android AI chat client & SillyTavern Android tavern compatibility. Connected to API instant chat: prefix cache to save token, semantic memory RAG, Jev intelligent decision-making, QuickJS plug-in, voice call, WeChat QQ Bot; character card, world book Lorebook, default, regular, QR, beautification theme can be imported with one click according to the official semantics of the tavern, without Termux/Node.js.

Describe your startup idea. Jev decides: kill it, fix it or ship it.

A reproduction of Jev that turns any Qwen model into a fast decision model, serving the same /v1/systemone schema (Choice, Score, Noul) with no training and no generated answer text.

Jev-native agent design with top-k proposals, fallback decisions, memory, and replanning.

MCP proxy that uses Jev to screen agent tool calls and tool results.

English full-duplex voice control for macOS with OpenAI Realtime, native Accessibility, and Jev.

Jev for Chrome: drives the tab you are looking at with TypeSafe Jev, a sub-second decision model. Community port of browser-use/jev-ultrafast, not affiliated with TypeSafe.

DuckDB extension: typed Jev answers as real SQL types

Customizable Advisor and Executor workflow for Pi with Jev decision support.

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM.

Community playground with editable Jev use cases, games, dilemmas, challenges, and A/B comparisons.

Jev checks configurable Pi agent rules for risk, output redaction, repeated failures, and missing verification at selected workflow stages.

Local Jev-compatible proxy that learns an application’s typed decisions and serves them with a Laya head.

MCP server that puts TypeSafe Jev on the coding loop in Cursor, Codex, and any MCP client.

Rust linter powered by configurable Jev rules, with a VS Code extension.

📡 全网最全 · The world's most comprehensive tracker of the Jev (TypeSafe AI System One) ecosystem — 220+ documented cases · 108 confidence-graded entries · verified & rescanned every 3 hours · API access guide included

Multi-agent orchestration engine with warm sessions, a durable mailbox, and per-task token accounting.

Super fast Jev like server, model agnostic, working with any OpenAI compatible endpoint.

Jev-powered conversation memory: find past sessions and revisit decisions with original sources. A macOS workspace for OpenAI Codex. Manage AI conversations and agents, explore code with CodeGraph, and work with Git, Ghostty terminals, and Apple Notes in one app.

Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into Compozy.

The optional cnki-jev package uses Jev for first-pass literature screening and escalates complex cases for model or human review.

Unofficial study: Jev-style parallel typed decisions on stock 1.5B-8B models on an Apple Silicon laptop. Benchmarks, research notes, and a Hugging Face Space demo.

Snake auto-played by TypeSafe's Jev model: one System One choice per tick, legal moves and facts generated in code.

Semantic tool routing and typed System One decisions for the Pi coding agent using TypeSafe Jev.

TypeSafe Jev for OTP: reply to Jev from a GenServer and pattern match on its answer.

The experimental Jev path scores completed context payloads so users can review and approve what remains available to the agent.

Local Jev-compatible typed decisions from unstructured state in one forward pass.

Native macOS automation loop where Jev chooses the next GUI action from OCR, accessibility, and OmniParser observations.

Jev (TypeSafe System One) backed auto mode for the Pi coding agent: semantically auto-approves bash, write, and edit tool calls and fails closed when a decision cannot be made.

Typed JSON inference with DiffusionGemma, with Every and Jev benchmark results.

Nerve is a supervisory nervous system for Hermes agents, adding typed System One decisions, ranking, verification, token-aware oversight, and an opt-in tool gate powered by TypeSafe Jev or Open Source Laya.

Drone-swarm simulation using Jev for reflex decisions and collision avoidance.

Tame your AI coding agents with natural language. Generate enforced guardrails (CLAUDE.md, hooks, settings) from a single command.

Run SemIf (Jev-style semantic-if decisions) on a CPU — no GPU. Reads typed option probabilities straight from an open model in one forward pass, plus a web UI.

Six live, side-by-side demos of TypeSafe's Jev — a "System One" model that returns typed, probabilistic decisions (70–500 ms, $0.042 per 1M input tokens, output free) instead of generated text.

Local decision-model runner with a Jev-compatible System One API.

Agent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shell.

Jev-powered search infrastructure for AI agents: zero API keys, MCP-ready, LLM-context aware, with local neural evidence verification.

Don’t know how to answer the message on WeChat? macOS floating chat assistant: identifies message intent and communication risks, GPT generates a variety of words, Jev evaluates candidates, and fills in WeChat with one click. I will help you think about it and send it to you to order..

Evidence-backed index of real-world Jev (TypeSafe AI System One) use cases: repos, patterns, benchmarks, and measured results

Jev-powered decision layer for DeepSeek Harness.

Open decision models for finance with a Jev-compatible typed API and evaluation runners.

⚡ Adaptive multi-model LLM router — 80+ providers, Jev System One single-pass routing (model=jev-auto), pheromone-trail failover, parallel ensemble merge. npm: adaptive-memory-multi-model-router.

Jev vs Gemini 3.8 Flash: labelling 1,000 app reviews, 4.1× faster and 7× cheaper.

Open alternative to Jev: typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with benchmarks.

Self-hosted AI email classifier for Gmail powered by Jev. Create custom labels, organize your inbox, and filter spam with confidence and cost controls.

grep for what code does, not what it's called. Semantic code search powered by TypeSafe Jev.

Practical, tested recipes for TypeSafe's Jev decision model on OpenRouter: support triage, database indexing, file organizing, tagging, taxonomies, dedupe, PII detection, extraction, search re-ranking and a browser agent.

TypeSafe Jev controls original StarCraft shareware through keyboard and mouse with recorded action probabilities.

Measures what your Jev classifier's confidence is really worth, and sets the human hand-off line from what a mistake costs.

YouTube transkriptlerini anlamına göre keşfedin. Türkçe arayüz, Jev analizi, altyazı dışa aktarma ve Vercel kurulum rehberi.

Command-line tool for TypeSafe AI's Jev model. Ask yes/no, multiple-choice and rubric questions about any text and get calibrated probabilities back. Answers become exit codes for shells and CI, JSON for scripts, and MCP tools for AI agents.

Local bilingual probability decisions from context, questions, and candidate answers. Independent research preview inspired by TypeSafe Jev.

The agent loop where decisions don't cost a large language model call. Zero deps, runs offline, no API key needed.

Jev runs in shadow mode to append structured quality evaluations to generated deep-research reports.

Evidence-backed use cases, patterns, and guidance for building with Jev, TypeSafe AI's System One model. Every claim is labeled and sourced.

The invalidation layer for AI memory. Every fact gets a lease; new evidence ends it. Built on TypeSafe Jev.

Jev-powered relevance filtering and reranking for RAG in Python.

TypeSafe structured-output provider for RubyLLM 2.

Score every test against a git diff with Jev, and emit the filter arguments vitest, node:test, Playwright, cargo test and go test already understand.

Chrome extension where Jev scores and labels X posts with typed judgments and a live local cost counter.

Jev-powered plugins for coding agents.

Open-weight Jev-inspired decision model fine-tuned from Qwen3.5 4B.

if you're experimenting with jev it will be easier from here.

Android WeChat module that uses Jev to show emotion probabilities, implied meaning, and communication suggestions.

Jev screens likely defects, arbitrates ambiguous findings, classifies scope, and supports cross-round review memory.

Community TypeSafe AI playground: 110 use cases, games, dilemmas and model challenges, with editable prompts, A/B comparisons and a mobile-friendly UI.

Probabilistic control flow for Ruby and Rails - powered by TypeSafe's Jev.

Reproducible benchmark for measuring Jev reranking quality, latency, and cost in RAG.

Linux, macOS ve Windows için kaynaklı ikinci beyin. Claude Code, Codex ve Antigravity adaptörleri; yerel Markdown kasa, ayrı hafıza incelemesi, isteğe bağlı Mem0/Jev.

MetaCoginition powered by Reflex 4B.

Structured-output library with a TypeSafe Jev driver for Noul, Choice, and Score decisions.

Scans a codebase for covert, deceptive, or data-stealing behavior with Jev, then reports suspicious files and line ranges before the user runs it.

Classify your inbox with Jev (TypeSafe's System One model) — tag, move, flag, and notify, all config-driven.

Pi model router that uses Jev task classification and a measured Pareto frontier over quality, cost, and latency to select an OpenRouter model.

Batched single-token choice inference for open language models, compatible with TypeSafe.

Chrome extension that cleans up your LinkedIn feed: hides engagement bait, self-promo and off-topic posts using Jev, TypeSafe AI's typed classification model — and explains every decision.

Block, steer, and "fuzzy lint" with Jev to make agents follow your rules and conventions. CLI, github action, pi package, and more. Built with Effect.

Run Jev-style typed decisions locally on your Mac with low RAM usage and fast responses.

A browsable directory of what Jev can do — 50 runnable.

The Jev integration routes agent memory queries between compact Markdown notes and searchable raw history.

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.

Typed-judgment admission control at the traffic edge: three-layer prompt-injection and abuse filter for nginx/OpenResty, powered by TypeSafe Jev. Fail-open, cached, hot-reloadable.

Azdaja exposes optional Jev semantic judgments inside a bounded local evaluation surface.

Discord bot demo that lets users converse with Jev-backed typed behavior.

Go SDK and CLI for TypeSafe Jev typed yes/no, Choice, and Score decisions.

Open replica of TypeSafe's Jev: typed calibrated decisions in one forward pass, on Gemma 4 E2B / Gemma 3 270M (Modal).

Browser extension that uses Jev to identify and fold ads and selected topics on social platforms.

Split-screen demo where Jev detects Pix-payment scams and traces the fraud chain.

High-performance System One model with an embeddable C runtime and WebAssembly support.

Semantic "Did you mean?" for any CLI — wraps commands and uses TypeSafe's Jev to match subcommand typos by intent, not edit distance.

Open Jev-style model and training stack for typed decisions and option probabilities.

Awesome Jev — evidence-graded index of TypeSafe System One: SDKs, MCP tools, agents, apps and open models. 20 languages, rebuilt every 2 hours.

Windows WeChat assistant that reads and redacts conversations before Jev classifies them.

Trading bot with the all new TypeSafe AI's first system one model named as Jev.

Claude Code plugin that uses Jev for rule checks, verbatim compaction, and prompt routing.

AI Music (MIDI) generator powered by Jev.

Craft Type-Safe Uncertainty-aware semantic pattern matching, control flow, and smart procedures for Effect DecisionModel and Jev.

Jev-inspired travel decision tutorial with classifier training; the browser demo uses recorded model outputs.

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.

A grill-me style interrogation of your idea, with Jev doing the grilling.

Grep, but the pattern is a description. Filters lines by meaning with TypeSafe's Jev decision model: ~200 ms and a thousandth of a cent per line.

AI-town simulation where Jev selects character actions and responses.

A stronger one-pass scorer over a variable list of text options: hashed n-gram encoder, rival-aware attention, gated head, temperature scaling, benchmarked against jevlike.

TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.

Ask typed questions about text or JSON and inspect model-derived probability distributions in a browser. One container runs the model, the original Decision Lab explorer, and a TypeSafe-shaped API.

Python prototype that plays NES Super Mario Bros. from structured RAM observations, with Jev answering focused movement and jump questions.

System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics.

Official collection of reusable Dagger modules for TypeSafe AI and System One workflows.

Natural-language linter that uses Jev to evaluate code against plain-language rules.

Fifty runnable visual demos comparing Jev typed decisions with an OpenAI structured-output baseline, with fixtures and explicit methodology limits.

Type-safe one-decision-per-token decoding engine for autoregressive LLMs, inspired by Jev.

Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.

Agent-first SEO and GEO CLI suite and MCP server using DuckDuckGo evidence and Jev scoring.

MCP server for TypeSafe Jev: typed classify, score, check, match and screen for any agent, with confidence on every answer.

Command Code mod: nudges the agent to keep going when it stops with work left, judged by Jev.

Swift client for TypeSafe Jev typed judgments instead of generated text.

Using Jev as an evaluator.

Turn programs call Jev for Choice, Score, and Noul decisions and route execution from the typed answers.

Filter any live Twitch chat with Jev: a bring-your-own-key Chrome extension.

Jev-native AI security harness for autonomous research, multi-agent swarms, persistent hunt boards, and long-running agent workflows. CLI-first, open source, and built for authorized security research.

Configurable semantic linting powered by Jev, with file-level NOUL judgments and a magic-strings plugin.

看看 Jev 能做什么：用中英文讲清热门应用、工作原理和各自优缺点。Explore Jev apps with plain-language examples, explanations, and comparisons.

Scientific knowledge system using Jev to nominate reusable knowledge issues for human review.

an open-source, from-first-principles reconstruction of the ideas behind TypeSafe AI's Jev, written in pytorch.

Jev-powered, rule-based grader for text files. Runs every rule against every line in parallel. No skimming, no missed lines.

Jev-assisted file retrieval and request caching for faster Pi workflows.

Typed decisions (choice / score / yes-no) from local Qwen models on Apple Silicon. Probabilities come straight from the logits, no text generation. TypeSafe-compatible HTTP API, runs on MLX.

Command-line tool for TypeSafe's Jev AI model.

Jev judges yes-or-no assertions about an agent transcript, and the test passes when its probability reaches the configured threshold.

Local Jevfire-style candidate scoring with ternary models and a System One API; probabilities are candidate-relative.

Elixir control-flow library that uses Jev Choice through ReqLLM to select branches.

Task-boundary model routing for Pi Coding Agent, powered by TypeSafe Jev. Conservative policies, exact caching, and observable failover.

Jev-shaped classification wrapper over OpenAI-compatible clients that returns probabilities and confidence.

Provider-independent agent SDK that uses typed routing to select a model for each turn.

A claude code plugin for jev.

Jev decision layer for agents: MCP server, embeddable DecisionModel library, and an escalate-only Claude Code plugin (TypeSafe AI's Jev).

Software, by reflex. A sentence becomes a call of a small program, chosen by Jev, TypeSafe AI's classifier, and run only when it is sure enough. Reflexes are recipes anyone can write, share and improve. A CLI you talk to, a package manager for reflexes from git, and a TypeScript SDK.

Language and runtime for agent-graph evolution with Jev-backed decisions.

Configurable semantic linting powered by Jev, with file-level NOUL judgments and a magic-strings plugin.

Browser-agent comparison that benchmarks a one-look open-model policy against the Jev demo.

Interactive experiments from support routing to a 3D driving simulation: structured sensor state in, typed steer, brake, and overtake decisions out.

Semantic AI for pandas and Polars: classify text, analyze sentiment, and score DataFrame rows with natural-language questions and full probabilities using TypeSafe Jev.

Prompt-injection and dangerous-action guard for coding agents (Claude Code, Codex, pi, ACP), powered by Jev.

Jev Capability Resolver: agents query a nested capability tree and receive only the deterministic commands and context relevant to the task.

A lightweight, native Swift 6 bridge integrating TypeSafe AI's Jev System One decision model into Apple's Foundation Models framework.

Rails-native Jev wrapper that turns typed, calibrated decisions into application control flow.

Social research agent for Instagram, TikTok, and LinkedIn: Jev repeatedly chooses the next concrete operation and target, while socai executes it in a local Chrome session.

CC0 Jev ecosystem list that resolves original project sources and covers open models, agents, research, applications, and critiques.

Typed TypeSafe AI clients for Rust, with async and blocking backends and observable retries.

2D autonomous car simulation in the browser, driven by TypeSafe's Jev decision model.

An agent skill to discover TypeSafe Jev opportunities, design typed questions, and learn from recent community experiments.

Chrome extension where Jev labels X posts by content type and judges which posts should be hidden.

CC0 Jev directory with 98 linked repositories grouped across SDKs, agents, applications, data workflows, open models, and resources.

Openvons (open-Jev): 有限選択肢に確率で答える判断層 — テキスト / 画像 / 日本語音声コマンド.

A curated list of projects, integrations, and resources for Jev, TypeSafe AI's System One model.

An experimental JEV-powered framework for forecasting short-term stock price direction from structured market data.

Everyday Stocks Status with Jev.

Claude Code Stop hook that asks four Jev questions when files changed without a passing check, blocking unverified completion claims while failing open on errors.

Stop guessing confidence thresholds: calibrate, threshold, and drift-check typed decision models (TypeSafe Jev) against an LLM teacher.

PoC: TypeSafe Jev as the reviewer for Hermes Agent smart command approvals. 8.7x faster, 4.4x fewer prompts, measured on 153 real commands. Approvals only.

TypeSafe (Jev) skill routing for Hermes Agent: names the one skill worth loading, before the model call. Opt-in, stdlib only, ~$0.001 per routed turn.

Typed, confidence-aware agent skill routing with TypeSafe Jev.

TypeSafe Jev as the pi coding agent's quiet decision layer.

Typed System One decisions, ranking, verification, and an opt-in Hermes tool gate using TypeSafe Jev.

Sorts text along a plain-English criterion using pairwise Jev Noul judgments and a locally fitted Bradley–Terry scale, with uncertainty and reliability reporting.

JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.

在 X 的时间线上，给每条帖子标出它想让你干什么。判断来自 Jev，一个只返回概率、不生成文本的模型。

Semantic decisions as ordinary Ruby — feels?, decide, score, Rails validations and pattern matching powered by Jev

LLM router that picks the cheapest model capable of handling a query, using TypeSafe's Jev for fast classification instead of an LLM call.

Open-source Jev log triage for OpenTelemetry. Score the signal before expensive LLM analysis.

Go SDK for the TypeSafe AI API — typed questions in, probability distributions out.

Experimental language and Rust runtime where semantic questions and decision methods are composable program values, with Jev as a supported provider.

Verbatim Jev-scored context reduction for omp, over TypeSafe or OpenRouter.

Zod validates the shape, Jev validates the meaning: semantic checks on request bodies become calibrated probabilities you threshold in code.

Adds jev(), jev_prob, jev_choice, and jev_score to vanilla PostgreSQL queries through a psql-shaped CLI and Go, TypeScript, and Python SDKs.

CDP browser library using batched Jev Choice questions to select operations and DOM-derived targets.

Automatic model routing for Pi using TypeSafe's Jev through Vercel AI Gateway.

TypeScript browser agent for ego lite: Jev Ultrafast indexed actions, TypeSafe Jev decisions, persistent observe/act CLI. No Chrome or Playwright.

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.

Observable browser stealth game: Jev makes typed guard judgments while deterministic code owns the world.

Browser-agent integration where Jev selects typed actions for research and classification workflows.

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.

Use Jev (TypeSafe's System One model) as a calibrated reranker: one call, up to 30 documents, a probability per document. Apache-2.0.

Agent-first Haskell DSL for TypeSafe's Jev judgment model: typed packets, inferred types, answers under the same labels.

Instinct: describe a case in free text and Jev picks the UI from a fixed catalog without generating a line of code or copy.

Agent skill for finding, designing, and validating useful Jev decision loops before committing them to an application.

Model performance first. Token savings second. A Pi extension with freshness-aware read dedupe, Jev log filtering, and searchable verbatim recall. Keeps existing message history intact.

AskJev — Jev autopilot for any website + guard on irreversible clicks (TypeSafe System One, not Claude).

Self-hosted Stacks data service whose Slack gate and fault-triage paths use Jev decisions.

Typed semantic decisions for Unix pipelines and CI, powered by TypeSafe AI Jev.

Scala SDK for Jev. No effect system bundled.

Small dependency-free CLI for TypeSafe Jev.

AI workspace whose approval review uses Jev to gate workspace actions with typed decisions.

TypeSafe AI Jev judgments for Agent Zero, with typed tools and probability cards.

Open local System One implementation for NVIDIA DGX Spark, with a Qwen3-based model, Jev-compatible API, architecture notes, and evaluation tooling.

Browser agent where Jev selects actions, an LLM reads and plans, and answers cite page evidence.

Connect JEV to MCP clients and compare its judgments against general-purpose LLMs using shared datasets and measurable accuracy.

1v1 Jev quickscope arena — Three.js + TypeSafe System One.

Async LangGraph workflow that gets a typed Jev Choice (invoice or general) and routes each inbound email to the matching handler.

Pi extension: verbatim context compaction with TypeSafe Jev decisions.

LegalForecast-MTD benchmark alpha and official evaluation workflows.

A small, extensible decision-to-action harness for TypeSafe Jev.

Site search that recalls candidates locally, then uses Jev to score and rerank them.

Reproducible early-access evaluation of Jev on Korean understanding and medical text, with runtime and cost evidence.

High-speed recursive AI Elo tournament engine powered by Jev and Swiss matchmaking.

Local Jev-like System One decision layer that returns typed choices and calibrated confidence without a hosted API.

Community .NET SDK for the TypeSafe AI System One API — typed noul, choice, and score questions with structured, confidence-scored answers. Not affiliated with TypeSafe AI.

A small, fast prose linter: ruff-style rule codes for writing, backed by TypeSafe's Jev model.

Pre-commit hook where Jev checks the message against the staged diff and flags debug leftovers, unmentioned work, and added credentials.

OpenJev: an independent Jev-inspired System One decision API based on TypeSafe.ai concepts. Choice, score and noul primitives, local mock server, Python and TypeScript SDKs. Real inference planned; not affiliated with TypeSafe AI. No repository-level license file was found during review.

A word-level language model whose output layer is Jev: n-gram drafter, Noul chunk verification, bits-per-token eval.

Local Jev-like typed-decision runtime using ONNX and quantized models for offline CPU inference.

Hybrid coding harness: System 2 writes, System 1 (Jev) runs reflexes.

Cross-agent software-development skills that add Jev decisions to planning, execution, debugging, and completion gates.

Dependency-free Swift 6 client for Jev Choice, Score, and Noul questions, with strict concurrency, retries, and offline transport tests.

Neon Function proxy for the Neon AI Gateway with TypeSafe Jev routing.

This demo uses Jev from TypeSafe AI to autonomously fly a drone in a random city from point A to point B, avoiding obstacles along the way. A trip costs $0.01.

Daf-jev: composable Python toolkit for TypeSafe's Jev (System One) decision API — question builders, confidence gates, evaluator, calibration, CLI, MCP server, agent skill.

Turn your AGENTS.md preferences into a fast, Jev-powered AI linter.

Voice-driven semantic auto-advance for Slidev, powered by Cloudflare Agents and TypeSafe AI Jev.

MCP router for Codex that uses Jev to select an external tool on demand instead of exposing the agent to every tool schema.

Ruby client for typesafe.ai.

A show-and-tell capability study for Jev, TypeSafe's System One decision model.

A browser-native Doom agent experiment with structured spatial state, composable AI controls, live decision telemetry, and a Chocolate Doom WebAssembly runtime.

Natural-language row filtering for MySQL, powered by TypeSafe Jev.

Helping JEV speak <3.

Specification-driven semantic verification engine that uses Jev to check AI-generated code and specs against explicit requirements.

DiffJury — TypeSafe Jev PR risk router + code review coach.

Reproducible evaluation of Jev calibration on synthetic support tickets and public classification benchmarks.

Catch breaking API behavior hidden in OpenAPI prose with deterministic checks and TypeSafe JEV System One semantic review.

Official tooling for observing and evaluating System One workflows.

Hybrid browser harness: an LLM turns goals into verifiable subgoals, Jev chooses each action and DOM field, Playwright acts.

Ask Jev typed questions from the shell: noul, choice, and score answers as numbers, not prose.

Does a TypeSafe Jev rerank beat embedding search? Graded relevance eval (9,831 pairs, 164 zh/en queries) over the Agent Skills Hub catalog, with the judge-circularity bias measured.

Commit-time review gate where Jev judges plain-language rules against agent-written code.

Agent skill for designing Jev-assisted systems with decision theory, composition patterns, question diagnostics, and validation gates.

Natural-language MCP tool dispatcher powered entirely by TypeSafe's Jev — no general-purpose LLM. Discovers a simple MCP server's tool signatures at runtime and uses Jev's typed primitives (Choice/Noul) to pick the right tool and extract its arguments straight out of the sentence. No repository-level license file was found during review.

A chatbot from typed Jev decisions: hierarchical speculative decoding over System One probabilities.

Recruiting-screening demo that combines deterministic date and eligibility checks with Jev judgments to route resumes for review or rejection.

TypeSafe Jev (System One) decision tools for Hermes Agent: jev_check / jev_route / jev_score / jev_evaluate

High-throughput synthetic & pretraining dataset sifter powered by TypeSafe AI Jev (api.typesafe.ai). Stream, filter, and score Parquet & JSONL datasets at 1,500+ rows/sec using System One typed decisions (Choice, Score, Noul).

Approval gate for Claude Code and Codex: intercepts tool calls, gets a Jev risk judgment, then applies a versioned local allow/deny policy.

Local 596M typed-decision model with its own weights, Choice, Score, and Noul support, and a Jev-compatible System One endpoint.

Decision harness for TypeSafe Jev — confidence gates, shadow mode, recipes, and evals. Claude CLI 48.9s → Jev 1.3s on the same row-filter job.

Open, local reimplementation of a Jev-style decision layer for job postings.

LangChain and deepagents skill router where Jev ranks installed SKILL.md files and decides whether and which skills to load for each turn.

SQL with natural-language predicates, powered by TypeSafe's Jev. Filter, rank, classify and score rows by meaning — batched, cached and cost-guarded.

Experimental Playwright library for natural-language browser automation, using Jev to turn page state and instructions into typed actions.

Go client for TypeSafe's System One API and its model Jev: typed judgments and calibrated probabilities instead of generated text.

CLI and agent skill for TypeSafe System One (Jev): typed Choice, Score, and Noul judgments.

Independent async and blocking Rust SDK for the TypeSafe AI System One API.

Agent Skill: send closed coding-agent judgments to TypeSafe Jev.

Swift SDK for TypeSafe AI.

Scala 3 / ZIO client for the System One API: typed end-to-end, several questions per round-trip via NamedTuple.

Reproducible calibration and selective-risk benchmarks for Jev/TypeSafe decisions in DSPy workflows

A curated projects built with Jev, TypeSafe's System One model.

Minimal agent loop where Jev directs control flow and a LangChain chat model writes argument values and the final response.

Selects source-linked evidence within a token budget using Jev relevance judgments plus local diversity-aware selection.

Community Go client for the TypeSafe System One API with typed question builders, retries, examples, and jev-latest as the default model.

Drives a real browser with Jev making every decision and Vercel's agent-browser performing every action, with a benchmark.

Codex plugin: verbatim Jev-guided context restoration around session compaction. Port of tamaratran/fast-jev-compaction to Codex lifecycle hooks.

Semantic schemas over TypeSafe's Jev — validate the state locally, then project typed answers.

Pokémon Red agent that turns structured game state into Jev decisions and validated moves.

Community TypeSafe AI playground: 110 use cases, games, dilemmas and model challenges, with editable prompts, A/B comparisons and a mobile-friendly UI.

DSH bundle that registers jev_ask for TypeSafe Jev noul, choice, and score answers.

An idiomatic, type-safe Elixir port of the official TypeScript AI SDK (ai / ai-sdk) providing unified LLM integrations, streaming text and structured outputs, tool calling, and agentic workflows. Jev is their current flagship model and is the first System One model.

Runtime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by TypeSafe Jev.

Idiomatic Java SDK for TypeSafe AI Jev System One decision engine.

Framework-agnostic agent evals and guardrails that batch a trace's checks into one request to Jev, Kev, Laya, or a chat-model fallback.

MacOS computer use driven by Jev (TypeSafe System One) as the decision maker.

High-throughput, robust native DuckDB extension for batched and streaming TypeSafe/Jev classification, scoring, and semantic predicates from SQL.

Open-source LLM router that uses TypeSafe's Jev to pick a model, on top of LiteLLM.

A VGI worker exposing TypeSafe System One questions (choice, noul, score) to DuckDB/SQL as LATERAL-joinable table functions

MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.

Reimagined window switcher for macOS using frontier artificial intelligence. Predicted by TypeSafe's Jev model.

Independent Jev 1.13.0 behavior study: report, controlled prompt experiments, raw results, and offline verification.

Source-attributed Jev casebook that separates author-reported results from independently verified behavior and documents limits.

Ask a yes/no question of every function in a codebase. Ranked answers in seconds, for cents. Grep whose pattern is a question, powered by TypeSafe Jev.

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 script

Zero-shot English goals on a sim Franka. Jev chains hardcoded primitives.

Local Jev-compatible evaluation server: POST /v1/systemone with typed noul/choice/score, open weights, no waitlist No repository-level license file was found during review.

YouTube extension that asks Jev for the sponsor probability of each caption segment and paints the result on the seek bar without a crowd database.

LlamaIndex reranker + router powered by TypeSafe Jev — typed scores/choices, cheaper than LLM-as-judge.

Local proxy that picks the Claude model and effort per message using TypeSafe Jev. Routes subagents, leaves your cached main chat alone.

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.

Jev-powered game and decision experiment.

Can a decision model beat dedicated rerankers? TypeSafe Jev vs Cohere Rerank 4 vs ZeroEntropy zerank-2 vs a chat-model baseline: 14 datasets, every raw API response, bootstrap ranges on every gap.

Shadow-mode validation harness for a pre-execution firewall on AI agent tool calls (TypeSafe/Jev). Real run, findings in report.md. No repository-level license file was found during review.

Claude Code mod that routes decisions to TypeSafe's Jev model: ranks installed skills per prompt, and answers the agent's own this-or-that questions when confident.

A chatbot built on a model that cannot generate text (TypeSafe AI's Jev, driven autoregressively).

Browser automation MCP server where Jev chooses the next bounded browser action for a coding agent.

Multi-axis writing quality checker powered by TypeSafe AI's Jev model. Separate named checks, each with its own verdict and confidence.

Shadcn-style reusable components and blocks for using TypeSafe AI.

Unofficial Laravel integration for TypeSafe Jev AI with typed responses, async requests, scoped dependency injection, and testing fakes.

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.

JEV Document Classification enables the rapid and cost-effective classification of text-based documents using AI, leveraging TypeSafe's "System One" model.

Mastra input processor that uses Jev for a typed block decision and moderation category.

Rust SDK for the TypeSafe AI API.

Unofficial go SDK for typesafe AI, with typed answers, retries, and context support.

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. No repository-level license file was found during review.

TypeSafe AI System One task plugin for New API with a native /v1/systemone endpoint, routing, and token billing.

Go client for TypeSafe AI's System One API (Jev), with optional Langfuse instrumentation.

Calibration and confidence-based routing measured on Banking77: 80.2% accuracy at $0.103 per 500 decisions.

Eight minimal working examples of TypeSafe's Jev (a System One model) applied to mechanical and electrical engineering: CAD/CAE/CAM routing, FEM result triage, DFM screening, BOM alignment, hallucination-proof extraction. Zero dependencies.

MCP server for typed decisions with Jev / System One via OpenRouter or TypeSafe

Fast structured Android control loops with TypeSafe Jev and Mobile MCP.

Blind security benchmarks for Jev, TypeSafe's System One model: prompt injection and vulnerable code detection, built on jev-go.

Community Rails integration on the typesafe-sdk gem: configuration, persisted usage and cost telemetry, and opt-in confidence policies.

Screen a folder of CVs with the TypeSafe Jev decision model: typed judgments, an editable policy, free re-scoring.

Agent skill that spots bounded-judgment steps, tries a typed decision model (TypeSafe's Jev) first, and documents every attempt

A polished OpenAI + TypeSafe Jev terminal interface for answers with transparent decision reports.

.NET SDK for the TypeSafe AI platform.

Live verdict page: feeds Jev the day’s Florida Man, odd-news, politics and world headlines and asks all three primitives whether AI should kill us all, refreshed every ten minutes.

Shift every LLM call to the cheapest model that can handle it. Routing decided by TypeSafe Jev in ~180 ms. No training data. Policy in plain YAML. TypeScript and Python.

Jev-routed client for NEAR AI Cloud inference and IronClaw agents.

100 AI NPCs live in a tiny town. Jev chooses the next action; the world writes the story.

Reproducible Jev Ultrafast research-browser eval harness + field note (QC’d cases, suite runner, report generator). Not investment advice.

Backtest Jev (TypeSafe) as a BUY/SELL/HOLD trader on NQ L10 order-book data.

Reproducible experiments on Jev probability calibration, uncertainty, and forecast preservation.

Record-linkage toolkit for Python, CLI, Stata, and R: Jev judges record pairs against a plain-English matching rule and returns auditable probabilities.

PDF reader that uses Jev Noul judgments to highlight lines matching a natural-language question.

Discriminative Monte Carlo Tree Search using TypeSafe Jev System One Primitives and Gemini.

Tell Claude Code which installed skill a session needs, using Jev (TypeSafe AI) for the decision and skills.sh for discovery.

⚡ Ultra-fast, low-cost intelligent task classifier and 3-tier routing engine powered by TypeSafe Jev (System One).

Check whether each cited paper supports the sentence citing it. Claude proves the quote, TypeSafe's Jev scores it, a human decides.

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.

Not every coding task needs your best model. Experimental Jev-powered model routing for Claude Code — V3 prototype runs today, V4 routes at the task boundary.

Evidence-driven frontend QA built on Jev Ultrafast and Browser Harness, with a synthetic todo demo.

Open-source native computer use for macOS and Windows: TypeSafe Jev, local OCR, and selective planning.

Judge every LLM response before the user sees it. AI SDK middleware and OpenAI-compatible proxy.

Automated database migration safety reviewer powered by TypeSafe AI (Jev System One model).

Community Java client for the TypeSafe System One API (unofficial).

CC0 catalog where code entries link to pinned Jev call sites and claims are labeled against a stated verification method.

Pi context pruning that uses Jev to drop or truncate stale tool calls while preserving retained content verbatim.

Two Jev agents compete in click-only browser games through Browser Use.

Recursive Jev choice over a taxonomy. Select from more than 255 options without breaking TypeSafe Jev's choice cap.

System-architecture skill for TypeSafe AI Jev/System One — find fuzzy semantic judgment and turn it into small Choice/Score/Noul primitives.

Jev (TypeSafe) exploratory thread: claim audit, live demos, and runnable code.

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.

Jev-powered semantic browser use.

A live tone labeler for Bluesky posts and drafts, using TypeSafe's Jev API.

One grounded Jev/Playwright core: typed SDK, persistent CLI, and MCP server with native browser operations and deterministic assertions.

Type-safe model router. Jev (System One) banks each request to a typed catalog route.

Portable System-1 decision layer for agent harnesses with host-owned routing, receipts, replay, and fail-open integrations.

Pokemon Red on PyBoy where Jev chooses legal actions only at branches and each battle turn logs a Brier-scored faint prediction.

Neovim plugin that has Jev score each function against a plain-language question and ranks results in quickfix.

Privacy-first Chrome extension that semantically blocks native ads, sponsored feed cards, and video ads using TypeSafe Jev.

Experimental multi-horizon BTC signal generator using TypeSafe Jev probabilities and Binance market data.

Benchmarks and a playground for TypeSafe's Jev (System One) model: chess, and who-is-the-player-talking-to for speech-to-text game NPCs.

Challenge the Jev's intelligence in Rubik Cube puzzles.

Local-first document evaluation workspaces powered by Jev

Async Python client for TypeSafe Jev. Typed questions in, probabilities and choices out, no prose to parse.

Pydantic AI capabilities made stronger with Jev: small runnable demos, one file each.

Sub-second pre-commit and pre-push semantic gate that screens staged diffs with Jev.

Grounded GitHub and crates.io discovery CLI and MCP server that uses Jev to score architectural fit, licensing, and maintenance.

Unofficial Go client for TypeSafe's System One API and its model, Jev.

Jev (TypeSafe) vs Claude Haiku 4.5 on 2 000 phishing emails: accuracy, calibration, latency, cost. Reproducible benchmark.

Metis: automatic GitHub issue triage powered by TypeSafe AI Jev. A reusable GitHub Action.

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.

PHP & Laravel SDK for TypeSafe AI's JEV Model series.

Unofficial PHP client for TypeSafe System One with typed Choice, Score, and Noul requests and synchronous or concurrent transport.

An eval-first MCP server for TypeSafe's Jev, a System One model that returns typed judgments (noul, choice, score) with probabilities instead of generated text.

Скилл для агентов Letta: суждения по критериям через TypeSafe System One (Jev).

Uses typeful jev, zero sync to pull and sync large repositories for issue triage.

Workbench that converts Chat Completions requests into editable Jev State and Questions, compares text generation with typed judgments, and exposes reusable proxy routes.

Go SDK for TypeSafe AI API https://docs.typesafe.ai/api.

Reproducible Jev research manuscript, evidence, and paper package.

Predict another skill's next closed decision with TypeSafe Jev — without running that skill.

A playground for TypeSafeAI's Jev Model.

A Chrome extension that brings TypeSafe's Jev to X.com to analyze posts as you browse.

Almond-fastloop: Almond's browser computer-use rig (Chrome DevTools + TypeSafe Jev), and the Browser Use Olympics benchmark it is measured on.

SRT translation app whose Jev Noul checks flag subtitle pairs that need human review without rewriting them.

Claude Code plugin that has Jev compare each pending tool call with the session plan before allowing, escalating, or blocking it.

A .NET 10 and React 19 application for fast, structured AI-powered ticket triage using TypeSafe Jev.

Fast semantic code search & diff sanity auditor for AI coding assistants (Antigravity, Cursor, Claude Code) powered by TypeSafe System One.

A Jev-inspired decision interface for existing LLMs. Explicit choices, scores, calibration, and review thresholds.

SO-101 robot-arm workbench where Jev selects bounded joint actions under a spend budget.

Unofficial Go SDK for TypeSafe AI's Jev API.

Independent DiffusionGemma and SGLang typed-decision server for text and images, with a drawing playground and public evaluation artifacts.

I tortured Jev into being a RISC-V CPU.

Pi extension suite for Jev-powered context compaction and model routing.

Desktop GUI for agentic coding that routes tasks across local agents and accounts, with Jev picking the best agent per task, running basic code-review checks, and supplying context.

Home Assistant Assist conversation agent powered by TypeSafe's Jev (System One) model.

MCP-first toolkit for TypeSafe/Jev — the System One decision model. One stdio server (jev mcp) serves any MCP-capable harness, backed by one local event log and Prometheus impact metrics you can scrape into your own Grafana.

Unofficial typed async Rust client for the TypeSafe System One API.

CLI for TypeSafe AI's Jev evaluation model — typed questions in, structured JSON answers out.

Semantic code review with Jev, plain-English rules, and installable agent skills.

An observable raw-character chat experiment powered entirely by TypeSafe Jev Choice.

Browser extension that grades page sections for clarity, writing quality, and on-page SEO with Jev.

Parallel web search for terminals and agents, with local Chromium and Jev-guided exploration.

Jev-shaped typed-decision models with measured latency, accuracy, calibration, and training cost.

Let Jev (TypeSafeAI) solve 2048.

A small Next.js app for experimenting with TypeSafe AI's Jev model (System One).

LangChain and Flask agent where Jev chooses among knowledge, calculator, weather, and chat routes, with a local-rule fallback.

Type-safe Java 21 client for the TypeSafe AI Jev (System One) decision API

Security-alert triage filter where Jev or a local model returns typed dispositions while policy routing remains in code.

A playground for experiments around Jev, TypeSafe's System One model.

Agent tool/MCP call gate — allow / ask_human / deny via TypeSafe Jev.

A Stop hook that stops your coding agent from stopping too early. Plain-language rules, judged by jev.

Comment-moderation playground: paste a comment, Jev decides what to do with it.

Put your code comments on trial. Powered by Jev.

Utilizing Jev, the RLCD-type model provided by TypeSafe AI, to independently and cheaply judge agentic coding sessions.

Jev (TypeSafe AI) PoC through Game of Thrones.

TypeSafe Jev plays original Civilization II in a browser, with live action probabilities. Experimental full-game harness.

Jev (TypeSafe System One) × ASReview SYNERGY abstract screening demo — Choice/Noul vs gold labels.

Unofficial MCP server for Jev (Typesafe AI)

Typed decisions from a System One model. An uncertain answer is a different type from a confident one — and the compiler makes you handle it.

MCP server that uses Jev to route coding-agent decisions such as file selection, task paths, and test-impact checks.

Ten runnable agent-decision examples covering memory, retries, context selection, and handoffs, with offline fixtures and optional live Jev calls.

Drop-in /v1/systemone shadow proxy that forwards requests to Jev and local decision models, recording agreement, calibration, latency, cost, and policy-level differences.

Projects built on Jev (TypeSafe AI's System One model), curated by Jev itself.

Low-latency audio censorship POC using Jev typed decisions and ffmpeg.

Jev-style calibrated decision model (Choice/Score/Noul) on Qwen3.5-0.8B.

AI benchmark on Japan's 2026 Common Test: Jev vs luna-none vs luna-low (static dashboard).

Claude Code plugin: asks TypeSafe Jev which installed skill fits each prompt and logs the answer (shadow-first). A working reference for the skill-suggestion cookbook on Claude Code — the README records why it is unlikely to help a strong model as a router.

TypeSafe AI (Jev) adversarial reviewer and typesafe_ask tool for the omp coding agent.

Unofficial list of insanely useful TypeSafe AI Jev / System One projects

Python library that maps Jev Choice, Score, and Noul questions onto classification, ranking, extraction, verification, and DataFrame workflows.

TypeScript library that maps Jev Choice, Score, and Noul questions onto classification, ranking, extraction, verification, and array workflows.

Portable Jev router for cost-aware Codex subagent model and reasoning selection.

Compare GPT generated language with JEV structured Noul decisions on the same input.

Tracks real products and experiments people are shipping with Jev.

Benchmarking Jev (Typesafe.ai) against a strong LLM on the Who&When Pro agent-failure-attribution benchmark (text subset).

Benchmarking TypeSafe's Jev decision model as a cost-efficient LLM router on RouterArena.

JEV picks which stream idea becomes the live MVP. TypeSafe System One decision board.

Typesafe AI SDK in Elixir using Req.

弈瞬：双 Jev 五子棋九宫格输入实验台，逐手查看模型决策，支持真实对局回放与实时对战。

Jev (TypeSafe System One) decision tools + live verification benchmark for DeepSeek Harness: jev_decision (choice/score/noul) and jev_verify, honest by design.

Local model-routing proxy where Jev selects the model route and reasoning depth, and also judges which tool history can be compacted.

Probabilistic decisions for Python. Use Jev or bring your own provider; crawl with Playwright.

Chrome extension for systematic-review screening where Jev returns per-criterion match probabilities and an inclusion judgment.

Pi extension that classifies tasks with Jev and routes each run to an explicitly configured model.

Experiments with openjev, an open Jev-style option-logit runner, on local models.

Idiomatic Go SDK for the TypeSafe AI API.

Typed-decision benchmark from PadFlow (land development SaaS): schemas, anonymized labeled rows, and a runner for confidence-calibrated models like TypeSafe Jev.

Claude Code and Codex browser skill that asks Jev to choose the next browser action.

A cyberpunk border encounter powered by TypeSafe Jev. Bluff the guard. Inspect the receipts.

Guardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT.

Commit-reveal rock-paper-scissors game where Jev scores player behavior, predicts the next move, and chooses its own move before the player acts.

Typed System One layer for Rust (Choice/Score/Noul).

Latency-first Rust SDK for TypeSafe System One.

Pong benchmark where every ball step is a model decision, comparing Jev with LLMs through Vercel AI Gateway.

Connector for integrating TypeSafe Jev decisions into application workflows.

Bounded browser and desktop automation where Jev picks one next step while code owns perception, execution, and verification.

Send Pi agents back to work when they stop before the job is done.

An evaluation of typesafe AI chess. As it turns out, the AI isn't doing really well even though chess is not a particularly open-ended game. Still, it's only a prototype and this probably wasn't optimzied for games.

Semantic assertions for pytest: test what your LLM app's output means, judged by TypeSafe's Jev.

Guardrail + model router for LLM gateways on TypeSafe's Jev (System One model), with an independent accuracy/calibration/latency evaluation. Stdlib Python.

Editable Game of Life ruleset bench where Jev evaluates legal cells and chooses each intervention while code advances and verifies the board.

Local multi-upstream router for the Jev protocol with a Rust backend and React interface.

A compiler for human language. Paste text, get diagnostics. Measured by TypeSafe Jev.

River shooter game in Python, inspired by Atari's River Raid, played by a TypeSafe AI pilot.

A local MCP server that uses TypeSafe Jev to confidence-gate an AI agent’s next step, routing uncertain decisions to proceed, deeper review, or human input.

Detect semantic stagnation in AI agent loops

CV diagnostics and job alignment with TypeSafe Jev, React and FastAPI.

MCP server exposing TypeSafe System One judgments (noul, choice, score) as agent tools.

Zero-shot spam filtering with TypeSafe Jev Noul questions, compared with TF-IDF baselines.

A small second eval for shadcn-ui/lint that uses TypeSafe's Jev to judge the linter's own output.

Push-to-talk voice orb for autonomous browser control using Jev and Metal Whisper.

ACME live support-call scoring demo with TypeSafe AI, Effect, SQLite, React, Vite, and Turborepo.

Demos to test the effectiveness of TypeSafe's "Jev" System One Model.

NPCs of River Oaks Houston, Texas using Jev to power NPCs.

Typesafe/Jev public X demo.

Typesafe/Jev public X demo.

Typesafe/Jev public X demo.

Twelve members. Zero qualifications. A playful TypeSafe AI council with animated votes, inspectable decisions, and shareable verdicts.

MCP server for typed Jev Choice, Noul, and Score judgments with probabilities and confidence.

Rust port of TypeSafe system-one-adapter (LLM-backed system_one evaluations).

Emoji autocomplete at the speed of typing. TypeSafe AI Jev on a Whop-hosted TanStack Start app.

Bounded exploratory browser testing with Jev, deterministic assertions, and replayable evidence.

System One Search: navigate and trace code with TypeSafe judgments and repository evidence.

Configurable decision MCP server with AI SDK, Jev, percentage scores, and bias-profile routing.

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).

N8n community node for the TypeSafe AI System One API — typed yes/no, choice and score questions with calibrated probabilities.

Evidence-gated registry of Jev question packs — curated questions, golden cases and measured evidence for Jev-compatible decision endpoints

TypeScript application exploring TypeSafe Jev as a System One decision layer.