智能体工具

jev.nvim

Neovim 插件，根据自然语言问题对函数评分，并在 quickfix 中展示结果。

Neovim plugin that scores functions against a natural-language question and lists results in quickfix.

jev-commit

Git 提交信息钩子，检查提交说明与暂存改动是否一致，并检查可能的凭据。

Git commit-message hook that compares the message with the staged diff and checks for possible credentials.

jev-belay

Claude Code 的 Stop 钩子，结合会话证据检查未经验证的完成声明；发生错误时放行。

Claude Code Stop hook that checks transcript evidence for unverified completion claims; errors allow the turn to end.

foreman

使用 Jev 检查编程智能体的工作。

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

jev-review (devagrawal09)

带看板的代码审查流程。

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

jev-router (gargpratyush)

为 Claude Code 和 Codex 的任务选择模型；需要 Node.js 20.12+、Jev 密钥和已登录的对应 CLI。

Per-turn model routing for Claude Code and Codex; requires Node.js 20.12+, a Jev key, and the corresponding CLI.

jev-review (NiazMorshed2007)

通过 MCP 插件进行本地代码审查。

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

jev-mcp (jkudish)

通过 MCP 工具提供 Jev 检查与查找功能。

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

pi-warden

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

typesafe-mcp

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

pi-jev (y0usaf)

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

ask-jev-skill

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

jev-codex-router

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

winnow

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

jev-axi

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

pi-jev-auto-mode

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.

jev-mcp (blakestone-x)

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

pi-jev-router

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

JevLint

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

typesafe-skill-router

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.

jev-agent-skill-router

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

pi-jev (TheoOliveira)

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

typesafe-cli (geilt)

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

diffjury

DiffJury — TypeSafe Jev PR risk router + code review coach

jev-code

Bounded TypeSafe Jev workflows for coding agents.

jevex

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

typesafe-migration-guard

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

typesafe-mod

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.

jev-judgment

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

jev-mcp (rashedInt32)

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

jev-shield

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.

jcm-router

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

pi-quiet-ask

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

ailerix

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

bicameral

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

jev-system-architect

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

jev-mcp (benballintyn)

MCP server giving coding agents typed, calibrated judgments from TypeSafe's Jev model

omp-typesafe

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

ask-jev

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

jev-predict-skill

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

Antigravity-mcp-semantic-search-with-TypeSafeAi

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

jev-guard

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

jev-skillful

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.

jev-router (prismhq)

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

jev-mcp (arunav25)

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

jev-triage

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

omp-jevens-classifier

Jev-powered model-judged permission gate for OMP (TypeSafe System One)

jev-mcp (burnigtm)

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

pi-jev-code

Single-agent Pi coding coprocessor with Jev semantic gates, baseline-to-current diff review, and append-only observability telemetry.

pi-agent-foreman

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

check-risk

A CLI and GitHub Action that assesses code-change risk using deterministic rules and TypeSafe Jev, recommending checks and reviewers before merge.

limpet

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

agent-gate-loop

Reusable GitHub Action: agent fix loop gated by checks, an AI reviewer, and TypeSafe Jev

switchboard

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

frost

A flexible and configurable CLI model router using TypeSafe Jev.

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.

pi-typesafe

Pi coding-agent extension built on the TypeSafe AI System One API (Jev)

jev-review (thiago-ss)

Autonomous Jev pull-request review with typed decisions, calibrated approval gates, and trusted-owner escalation

hermes-jev-router

Experimental Hermes plugin: Jev-assisted model routing plans with budget and capability constraints. API access pending.

zcode-jev

Typed judgment layer for coding agents — gates from PRD to ship. Jev-ready, provider-agnostic.

jev-builder-loop

Grok skill: Jev as a judgment sensor in a builder-agent loop (priors × probabilities → next act)

typesafeai-review

Using Typesafe.AI to generate diff reviews.

typesafe-demo-mcp

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

agent-handoff-gate

Experimental protocol for evidence-aware agent handoffs, with Jev-assisted review before results reach the lead agent.

fabricioctelles/skills

A collection of skills for AI agents (Kiro, Cursor, Windsurf, Claude Code, and others). Each skill is a reusable module that teaches the agent to perform complex tasks with context, structure, and best practices.

dbreunig/building-with-jev-skill

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

superagents-lab/jev-search

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

Dicklesworthstone/skillranker

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.

supercorp-ai/supercov

Code quality and coverage for coding agents

DanRWilloughby/snifftest

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

anpicasso/hermes-jev-approvals

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.

doeixd/jev-pref

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

iamvatsalpatel/tiershift

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.

MongLong0214/jev-gate

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.

ShivamPansuriya/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.

aegsrl7/jevmap

Map a codebase into units and let Jev (TypeSafe AI) hand an AI coding agent the ten files that matter for a task

altryne/jevify

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

buchmark/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.

harrymunro/decision-first

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

poponline63/hermes-jev-north-star

Hermes Agent skill whose north-star gate is judged by Jev (TypeSafe System One): turn an intention into a checkable finish line, generate the run prompt, and let Jev rank what is still unproven.

qkal/Canny

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

rthomas24/jev-realtime-trading

Paper trading agents on a live tape, decided every second by TypeSafe's Jev (System One). Electron desktop app.

24601/Augustus

Agent skill: design judgment-assisted systems with TypeSafe Jev (System One). Maps Choice/Score/Noul onto decision theory, reranking, and routing. Composition algebra, question design, validation gates. MIT.

aaravriyer193/OpenSmoke

Find the AI agent runs that broke because their environment did: missing keys, tools, files, permissions, network, or context. Powered by TypeSafe Jev.

AkashPriyadarshii/jev-superpowers

Systematic software development framework for AI coding agents upgraded with TypeSafe Jev System One typed decisions

AlexBabescu/ActionJev

Structured code review for GitHub and Gitea Actions, powered by TypeSafe Jev and written in Rust.

ArkadyBuryakov/jev-preview

TUI Sandbox for Typesafe Jev API

BrunooMoniz/polymarket-btc-5m-agent

Agente de trading para o mercado BTC Up/Down de 5 minutos da Polymarket: modelo em código, Jev (TypeSafe System One) como portão, ordens maker, calibração e shadows em paper

CodeAlive-AI/mastra-jev-moderation

Input moderation for Mastra agents on TypeSafe Jev — one file

ddfeyes/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 deps, MIT.

dsandrade/jevra

An open-source decision layer connecting coding agents with TypeSafe Jev.

Eliran-Turgeman/reaper

Semantic linter for AI coding agents and CI code review. Detects silent failures, weakened tests, scope creep, unnecessary abstractions, and other semantic code smells.

eyenpi/actionreflex

A pre-execution gate for AI agent actions, powered by TypeSafe's Jev (System One) model.

fabricio852/jevshift

⚡ Token Saver & Fast Decision Layer for OpenAI Codex — powered by Jev

getexcited/stepwarden

Every tool call your agent makes, checked before it runs. A Claude Code plugin that uses TypeSafe AI's Jev to verify each pending tool call against the session plan, then allows it, asks you, or blocks it. Proof of concept

ibrahemid/git-jev-stage

Stage the git hunks that match a sentence. Exact patch, preview first, staging only, decided per hunk by Jev.

ibrahemid/jevprune

Keeps the lines of a command's output that matter for the task. Exact text, full output recoverable, decided per line by Jev.

ivorpad/skillranker

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.

kaustav1996/reflex

A coding agent and personal assistant with System One reflexes (TypeSafe Jev) on top of the Pi coding agent

kevin9327/jev-harness

JevHarness: TypeSafe Jev agent tool-call gate. execute / confirm / reject in code.

knowlet/Decision-Theoretic-Mixture-of-Agents

A fully audited, reproducible decision‑theoretic mixture‑of‑agents framework comparing multiple selector strategies, including OpenJev, with transparent calibration, limitations, and verification artifacts.

manojlds/jev-review

Standalone TypeSafe Jev code-review CLI: typed decisions over a local git diff.

Mentioum/judgement

Agent-friendly Go library and JSON-first CLI for TypeSafe AI's Jev and System One API

milokuo/tagtrim

Tag every line of a command's output, then trim by tag, so your coding agent reads the signal, not the noise. Design stage.

pistachiopranay/jev-synergy-screening

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

rashedInt32/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.

RiskAverseTech/toolgate

Open auto mode for AI agents — a calibrated tool-call firewall powered by TypeSafe Jev. Ships as a Claude Code hook

rustfuture/reflex-control

Rust policy engine using TypeSafe Jev and deterministic checks to route AI agent decisions.

suraj-phanindra/wellposed

Lint your jev requests before they come back confidently wrong.

Thestral12/pr-sieve

Semantic PR gate: .jev.yml rules as TypeSafe Jev questions. Not a review bot.

wotai-dev/typesafe-jev-tools

A Claude Code hook that asks whether the decision you are writing needs a model at all. Includes a measured 149-row comparison of TypeSafe Jev against Claude Haiku 4.5.