JEV LAB
Submit a find
English
English한국어日本語EspañolFrançaisDeutsch简体中文繁體中文PortuguêsBahasa IndonesiaไทยItalianoTiếng ViệtTürkçePolskiРусский

A FIELD GUIDE TO JEV / VOL. 01

SMALL
DECISIONS.
BIG
POSSIBILITIES.

The best of Jev. Real projects, practical guides and ideas from across the internet.

Explore the labGuides
1,195resources16languagesFind something
worth building.
IN THE SPOTLIGHT SOURCE: X
Gregor Zunic@gregpr07

Browser Use + Jev

Gregor Zunic's flight-search demo with a dynamic DOM action space.

Browser Use + Jev Explore this project
Source linked · creator-reported demoView on X

01 / A small decision engine. A whole new way to build.

378 resources / The collection

Reset filters

AI-assisted summaries and translations. Check original sources for context and performance claims.

browser-useGitHub

Jev Ultrafast

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.

Agents & browsersEnglish
Open original
tamaratranGitHub

fast-jev-compaction

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.

Agents & browsersEnglish
Open original
shaharia-labGitHub

jev-cli (shaharia-lab)

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.

Agents & browsersEnglish
Open original
awlevinGitHub

typesafe-computer-use

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

Agents & browsersEnglish
Open original
aniruddh-krovvidiGitHub

switchboard

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

Agents & browsersEnglish
Open original
AkashPriyadarshiiGitHub

jev-git

Sub-second Git pre-commit & pre-push semantic reflex gate powered by TypeSafe AI Jev.

Agents & browsersEnglish
Open original
Mihajlo MicicGitHub

jev-tool-runner

Jev-Tool-Runner is a GitHub project where Jev selects developer tools and Codex generates code based on those selections.

Agents & browsersEnglish
Open original
rashedInt32GitHub

jev-reach

Chrome-devtools-mcp plus one tool: Jev walks the browser to the right spot, then your agent makes a single devtools call there.

Agents & browsersEnglish
Open original
gaborishkaGitHub

jev-canvas

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.

Agents & browsersEnglish
Open original
Konstantinos BotonakisGitHub

codex-context-diet

A Codex plugin that uses Jev to streamline and reduce excessive tool outputs.

Agents & browsersEnglish
Open original
ajensenwaudGitHub

hermes-jev-plugin

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

Agents & browsersEnglish
Open original
ranjan2829GitHub

AskJev

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

Agents & browsersEnglish
Open original
ohmyjiroGitHub

jev-judge

Dependency-free CLI and Codex skill that send local state to Jev for batched typed judgments and return answers without echoing the state.

Agents & browsersEnglish
Open original
blakestone-xGitHub

jev-mcp (blakestone-x)

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

Agents & browsersEnglish
Open original
NyarlathotepppppGitHub

pi-heed

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

Agents & browsersEnglish
Open original
AkashPriyadarshiiGitHub

jev-scout

Zero-hallucination open-source repo and crate scout powered by TypeSafe AI Jev System One scoring.

Agents & browsersEnglish
Open original
vinilanaGitHub

jev-browser (vinilana)

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

Agents & browsersEnglish
Open original
3clyp50GitHub

a0-typesafe-ai

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

Agents & browsersEnglish
Open original
FriedjofGitHub

jev-mobile

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

Agents & browsersEnglish
Open original

Privacy, on your terms.

Essential functionality works without analytics. Optional Google Analytics runs only with consent. We respect Do Not Track and Global Privacy Control. External X and YouTube embeds load only when you ask.