Browser Use + Jev
Gregor Zunic's flight-search demo with a dynamic DOM action space.
A FIELD GUIDE TO JEV / VOL. 01
The best of Jev. Real projects, practical guides and ideas from across the internet.
Gregor Zunic's flight-search demo with a dynamic DOM action space.
01 / A small decision engine. A whole new way to build.
378 resources / The collection
Reset filtersAI-assisted summaries and translations. Check original sources for context and performance claims.
Tell Claude Code which installed skill a session needs, using Jev (TypeSafe AI) for the decision and skills.sh for discovery.
Hybrid coding harness: System 2 writes, System 1 (Jev) runs reflexes.
An experimental local-first plugin for coding agents that uses Jev to provide quality feedback during development.
A community post discusses Jev as a faster general classifier/decision-maker, questioning its accuracy in complex scenarios and noting potential benefits in limited solution spaces with low latency requirements.
A developer project where Jev filters tool results before model processing, aiming to improve efficiency in agent systems.
Pi coding-agent extension: TypeSafe Jev checks for tool calls, tool outputs and replies (prompt injection, approvals, secret scrubbing, task pinning).
Autonomous Jev pull-request review with typed decisions, calibrated approval gates, and trusted-owner escalation.
Claude Code plugin: trim long Bash output with TypeSafe Jev before the model sees it.
Typed judgment layer for coding agents — gates from PRD to ship. Jev-ready, provider-agnostic.
Jev-browser enables agents to perform web tasks by automatically opening websites and making click decisions based on screen content.
Open auto mode for AI agents — a calibrated tool-call firewall powered by TypeSafe Jev. Ships as a Claude Code hook.
Throw in a pile of company files and get them classified and organized by department, type, sensitivity, date, counterparty and PII, with an index for AI agents. Powered by TypeSafe's Jev on OpenRouter (17¢ per 1,000 files). Zero-dependency Node CLI + Claude skill + Codex agent.
A guide-directed World of Warcraft agent designed to reduce expenses as it runs longer, developed on GitHub.
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.
PiJev: a terminal coding agent with Jev in the loop — Jev ranks the repository's files before the first call, picks skills and triages failures; your coding model writes the code. Built on Pi.
Retriever AI evaluates Jev's performance on real browser tasks, identifying strengths and areas for improvement in integration with larger models.
Agentcard integrates Jev and Kernel to enable secure and efficient online shopping by agents, avoiding token costs and safety issues.
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.
Privacy-first Chrome extension that semantically blocks native ads, sponsored feed cards, and video ads using TypeSafe Jev.
An agent project that enforces policies by judging Claude Code tool calls.
A guide explaining how to integrate Jev with Pydantic AI agents for type-safe operations.
A developer project focused on agent memory, where Jev determines what information is relevant to recall.
A community post describing an offline decision system using Jev to evaluate research branches efficiently.
Type-safe model router. Jev (System One) banks each request to a typed catalog route.