A FIELD GUIDE TO JEV / VOL. 01

Pequenas decisões.
Grandes possibilidades.

O melhor de Jev: projetos reais, guias práticos e ideias de toda a internet.

1.195recursos16idiomasFind something
worth building.
IN THE SPOTLIGHT SOURCE: X
Gregor Zunic@gregpr07

Uso no navegador + Jev

Demo de busca de voo de Gregor Zunic com espaço de ação dinâmico do DOM.

Uso no navegador + Jev Ver projeto

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

378 recursos / A coleção

Limpar filtros

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

TRADUZIDO
browser-useGitHub

Jev Ultrafast

Agente ultra-rápido para uso no navegador: Jev seleciona a operação e o elemento DOM em uma única solicitação; um pequeno LLM escreve texto apenas quando necessário.

Agentes e navegadoresEnglish
TRADUZIDO
tamaratranGitHub

fast-jev-compaction

Plugin de código Claude que substitui o resumo de compactação por decisões Jev, avaliando todas as chamadas de ferramentas e resultados em uma única solicitação rápida, descartando ou truncando os obsoletos.

Agentes e navegadoresEnglish
TRADUZIDO
shaharia-labGitHub

jev-cli (shaharia-lab)

Ferramenta de linha de comando para o modelo Jev da TypeSafe AI. Permite fazer perguntas sim/não, múltipla escolha e de rubrica sobre qualquer texto e obter probabilidades calibradas. As respostas funcionam como códigos de saída para shells e CI, JSON para scripts e ferramentas MCP para agentes de IA.

Agentes e navegadoresEnglish
RESUMO EN
awlevinGitHub

typesafe-computer-use

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

Agentes e navegadoresEnglish
RESUMO EN
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.

Agentes e navegadoresEnglish
RESUMO EN
AkashPriyadarshiiGitHub

jev-git

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

Agentes e navegadoresEnglish
RESUMO EN
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.

Agentes e navegadoresEnglish
RESUMO EN
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.

Agentes e navegadoresEnglish
RESUMO EN
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.

Agentes e navegadoresEnglish
RESUMO EN
Konstantinos BotonakisGitHub

codex-context-diet

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

Agentes e navegadoresEnglish
RESUMO EN
ajensenwaudGitHub

hermes-jev-plugin

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

Agentes e navegadoresEnglish
RESUMO EN
ranjan2829GitHub

AskJev

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

Agentes e navegadoresEnglish
RESUMO EN
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.

Agentes e navegadoresEnglish
RESUMO EN
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.

Agentes e navegadoresEnglish
RESUMO EN
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.

Agentes e navegadoresEnglish
RESUMO EN
AkashPriyadarshiiGitHub

jev-scout

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

Agentes e navegadoresEnglish
RESUMO EN
vinilanaGitHub

jev-browser (vinilana)

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

Agentes e navegadoresEnglish
RESUMO EN
3clyp50GitHub

a0-typesafe-ai

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

Agentes e navegadoresEnglish
RESUMO EN
FriedjofGitHub

jev-mobile

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

Agentes e navegadoresEnglish

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.