Jev browser agents and automation

Jev Ultrafast

Browser Use

A browser loop where Jev selects an operation and page element, with a text model handling field input.

Source

Mobile Jev

Droidrun

An Android agent using Jev decisions and Mobilerun, with a live studio, CLI, and execution traces.

Source

TypeSafe Computer Use

awlevin

A macOS control loop that combines OCR and accessibility data with Jev action selection.

Source

Jev Review

devagrawal09

A staged Jev workflow for inspecting Git changes or source files, with a local review dashboard.

Source

Typesafe MCP

itsmostafa

A Go CLI and MCP server that lets coding agents request typed Jev evaluations.

Source

TypeSafe Agent Skills

TypeSafe AIOfficial

An official agent skill for designing TypeSafe workflows and finding the relevant API guidance.

Source

jev-browse

kyrylosyzonenko

A CLI and MCP browser tool pairing Jev decisions with agent-browser actions.

Source

Jev Browser

vinilana

A Playwright browser harness splitting goal planning, typed action decisions, and text generation.

Source

pi-typesafe

twilwa

A Pi extension that adds Jev assessments before tool use and after file changes.

Source

Unclutter

kitze

Hide page clutter with reusable, Jev-classified browser rules.

Source

Jev Browser by Ying-Kai-Liao

Ying-Kai-Liao

Delegate a bounded browser step to Jev through MCP.

Source

Computer Use Jev

paulsmith

Control macOS apps through accessibility targets chosen by Jev.

Source

Jev Ego

romaluev

Bring Jev’s indexed action selection to the ego lite browser.

Source

Almond Fastloop

eriestra

A compact Jev browser loop paired with a timed task benchmark.

Source

Barrunto

elpumberto

Add Jev judgment labels to X posts and Hacker News comments.

Source

Jev Browser by tontoko

tontoko

One Playwright core exposed as a persistent CLI, SDK, and MCP server.

Source

Otto

NobleSpartan6

Explore native desktop control with Jev and an optional planning model.

Source

Psearch

komikat

Search and follow web evidence with Jev-ranked pages and links.

Source

Jev Browser by KesavanKing

KesavanKing

Inspect Jev browser decisions in a local visual control panel.

Source

Jev Browser by MahmoudAdelbghany

MahmoudAdelbghany

Let Jev drive browser steps and escalate uncertainty to the calling agent.

Source

Jev Mobile

Friedjof

Run persistent Android tasks with Jev selecting valid device actions.

Source

Jev Playwright MCP

krw82

Add page checks and action judgment to an existing Playwright MCP setup.

Source

JevTest

CorieW

Explore browser flows with Jev decisions and replayable test evidence.

Source

Sift

tylergibbs1

Reorder Google results using Jev relevance and promotional-content judgments.

Source

Sloppy Jev’s

neddes

Optionally blur text flagged as advertising or AI-like prose.

Source

Jev Turbo

sightmap

Run browser goals through named actions and Jev selections.

Source

Foreman

thruwire

Use Jev to supervise evidence from a coding agent’s work.

Source

Pi Warden

DevMortimer

Evaluate Pi edits and actions against project rules with Jev.

Source

Jev Codex Router

0xNatoshi

Archived Jev Codex Router: per-call model and effort selection for a local Codex setup.

Source

Winnow

GhalebDweikat

Reduce large Claude Code tool results using Jev relevance judgments.

Source

Jev AXI

shiftynick

Expose typed Jev judgments as composable commands for coding agents.

Source

DiffJury

raihankhan-rk

Inspect a pull request’s risk, review depth, and test gaps.

Source

Jev Code

devagrawal09

Delegate file ranking, change checks, and triage to bounded Jev workflows.

Source

Ailerix

tylerjharden

Use a single model route with Jev selecting from a provider catalog.

Source

Bicameral

AbdelStark

Pair a Pi coding model with Jev judgments and explicit action policies.

Source

JCM Router

adarshmishra07

Route Claude Code requests while accounting for prompt-cache tradeoffs.

Source

Jev Shield

caiovicentino

Inspect MCP calls, results, and tool descriptions with Jev.

Source

TypeSafe Migration Guard

opaielsheikh

Review proposed database migrations with typed Jev judgments.

Source

TypeSafe Mod

BeLazy167

Add Jev option scores and optional skill routing to Claude Code.

Source

Jev Guard

leepokai

Evaluate agent tool calls for risk, user intent, and untrusted influence.

Source

OMP TypeSafe

siddicky

Add an advisory Jev reviewer to an OMP coding session.

Source

Agent Gate Loop

Ripwords

Run an issue-to-PR loop with tests, an independent reviewer, and Jev checks.

Source

Check Risk

moezubair

Combine repository policy with semantic change-risk signals.

Source

Limpet

noplan-inc

Check a coding agent’s stopping point against plain-language rules.

Source

Pi Agent Foreman

alexshpunt

Review whether a Pi session openly left required work unfinished.

Source

Pi Jev Code

KamilPostrozny

Add semantic checks and traceable review signals to a single Pi agent.

Source

Switchboard

aniruddh-krovvidi

Combine Jev safety signals and model selection in an LLM gateway.

Source

JevLint

huntedman

Check source files against natural-language coding conventions.

Source

Skillful

bestagentkits

Suggest a relevant installed capability for the current agent prompt.

Source

Jev Router by Prism

prismhq

Route an OpenAI-compatible model ID through a Jev decision.

Source

Pi Jev by y0usaf

y0usaf

Use Jev as a typed decision layer within Pi.

Source

AskJev for Hermes

shantanugoel

Give a Hermes agent a typed Jev tiebreaker.

Source

Jev Review MCP

NiazMorshed2007

Return structured code-quality judgments to a coding agent over MCP.

Source

patdown

tyler-dot-earth

Source description: Block, steer, and "fuzzy lint" with Jev to make agents follow your rules and conventions. CLI, github action, pi package, claude extension, and more. Built with Effect + TypeScript.

Source

jevscape

Skyvern-AI

Source description: RuneBench harness for TypeSafe's Jev: bounded action catalog, tick-mode controller and a live dashboard

Source

jev-sentinel

harshwasan

Source description: Pi coding-agent extension: TypeSafe Jev checks for tool calls, tool outputs and replies (prompt injection, approvals, secret scrubbing, task pinning)

Source

jev-router

dirien

Source description: Pass-through model router for Claude Code and Codex CLI that picks a model tier per human turn with Jev, TypeSafe AI's decision model

Source

pi-jev-router

mejiasd3v

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

Source

jev-commit

valentynkit

Source description: pre-commit hook: one Jev call judges whether your commit message matches the diff, plus debug leftovers, scope creep, and a secret belt

Source

jev-cookbook

paramjeetn

Source description: The complete cookbook for Jev by TypeSafe AI — 120+ use cases, 10 runnable examples, 4 composition patterns, and first-principles theory for the world's first System One AI model.

Source

jevymarket

markusbug

Source description: Polymarket trading bot driven by Jev (TypeSafe AI) via OpenRouter

Source

jev-lint

ckorhonen

Source description: A fuzzy linter for coding agents. It checks the code your agent writes against your team's best practices while the agent is still working, not at code review.

Source

jev-remix-cutter

gnipbao

Source description: Agent Skill and Python CLI for local video remixing, Jev judgments, and originality reports.

Source

Jev_steer_or_queue

Larkspur-Wang

Source description: Let TypeSafe Jev decide whether a message you send mid-turn should steer, queue, or interrupt your coding agent. Claude Code plugin; Codex CLI in testing.

Source

jev-opus

WXK-AI

Source description: Claude Opus 5.5 with the effort level re-decided every step by the TypeSafe Jev reflex — without breaking the prompt cache. CLI + Claude Code plugin.

Source

jev-canvas

gaborishka

Source description: Draw on a tldraw canvas with your voice and a pointing finger. Jev (TypeSafe System One) decides action, target and place in ~350 ms per spoken word.

Source

agent-chaperone

agent-chaperone

Source description: Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.

Source

jev-cli

Nasrallah-AL

Source description: Command-line tool for TypeSafe's Jev AI model

Source

jev-code

rhighs

Source description: Interactive TypeScript coding CLI powered by Jev typed decisions and constrained AST generation.

Source

jevwire

Brainwires

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

Source

hermes-jev-approvals

anpicasso

Source description: 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.

Source

jev-mcp

blakestone-x

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

Source

muse-jev-playbook

Bodila51

Source description: Jev decision layer for Muse: a fast, cheap TypeSafe AI gate before expensive agent work — confidence policy, recipes, reference router, honest measurement.

Source

jev-usecases

kenhuangus

Source description: Production TypeSafe Jev (System One) use-case harnesses with confidence-gated decision logic

Source

jevonian

xinyao27

Source description: One local endpoint. The right model for every turn — enforced in code, not prompts.

Source

jevvy

PanAchy

Source description: Jev-powered plugins for coding agents

Source

omo-jev-plugin

brianhong-dev

Source description: Jev-powered decision support for OmO and senpi agents

Source

claude-jev

0x7067

Source description: Claude Code plugin: Jev for rule checks, verbatim compaction, and prompt routing

Source

jev-harness

TypeSafeAI

Source description: A custom coding harness for TypeSafe AI's Jev: an LLM proposes, Jev answers narrow questions, code decides, every step leaves a receipt.

Source

jev-skill-suggester

win4r

Source description: 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.

Source

pi-jev-auto-mode

jomatsu

Source description: 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.

Source

dsh-jev-interceptor

AskTheWay

Source description: ⚡ Millisecond System-1 judgement for every tool call in DeepSeek Harness — Jev-powered risk classification & evidence-gated auto-approval. Fail-closed by construction. dsh 生态第一个 System-1 决策插件

Source

jev-permission-gate

madisonrickert

Source description: A Claude Code mod that uses TypeSafe's Jev to decide auto mode tool calls. 2x faster than the built-in classifier on the calls it decides.

Source

claude-x-jev

charlesdove977

Source description: Fast, cheap, typed decisions for Claude Code. Jev (TypeSafe's decision model on OpenRouter) sorts, checks, scores, gates and verifies at 0.3s and a fraction of a cent per item. Claude keeps the reading, writing and judgment.

Source

pi-jev-skill-picker

safzanpirani

Source description: Rank Pi Agent Skills for the current task with TypeSafe Jev

Source

slop-grader

lukstei

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

Source

snifftest

DanRWilloughby

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

Source

jev-recruiter

skeptrunedev

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

Source

jevreel

DeepAleph

Source description: A zero-embedding approach to video intelligence, using Jev: contact sheets + typed decisions, as MCP tools and a skill for any coding agent.

Source

jev

BorisLeMeec

Source description: A claude code plugin for jev

Source

is-malicious

luantak

Source description: A codebase scanner that helps you not run malicous code

Source

jev-recall

samdotmak

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

Source

jev-mcp

burnigtm

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

Source

jev-use

shitianfang

Source description: 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

Source

hono-jev-router

yusukebe

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

Source

jev-code

FrancoisChastel

Source description: 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.

Source

jevlint

codegirl-007

Source description: A linter to codify code taste using Jev

Source

Canny

qkal

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

Source

stanley-code

devagrawal09

Source description: Bounded TypeSafe Jev workflows for coding agents.

Source

grok-bot-jev

Bodila51

Source description: Connect TypeSafe Jev to Grok Bot as a cheap decision layer - usage gates, skill template, examples

Source

jevcore

PerryLink

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

Source

jev-dsh-decision

Devin-AXIS

Source description: Jev DSH 决策引擎｜面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness，通过 iPolloWork 支持 OpenCode、Codex Harness。

Source

dsh-jev-plugin

luobosibing2

Source description: Native DeepSeek Harness (DSH) plugin integrating TypeSafe Jev or Decision api like luna as a System One decision layer for agent selection, supervision, corrections, and approvals.

Source

jev-pruner

tamaratran

Source description: Claude Code plugin: trim long Bash output with TypeSafe Jev before the model sees it

Source

supercov

supercorp-ai

Source description: Coverage, security and code quality for coding agents

Source

jgrep

keltokhy

Source description: 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.

Source

jev-mcp

jkudish

Source description: Fast, cheap, typed judgments from TypeSafe's Jev model, as MCP tools.

Source

jev-search

superagents-lab

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

Source

JevRouter

BillionsBobby

Source description: A lightweight Jev-powered router for models, tools, and subagents

Source

system-one-connector

itsmostafa

Source description: System One MCP connector to evaluate anything fast and cheap. Give your AI agent direct access to models like: Jev, D1, CLM and Laya

Source

jev-gateway

vinilana

Source description: An easy way to use jev with your coding agent for tool calling reasoning

Source

fast-jev-compaction

tamaratran

Source description: 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.

Source