브라우저 및 컴퓨터 사용
이 분류의 18개 항목. 각 항목에 구체적 결정과 열어볼 수 있는 근거 링크가 있습니다.
AndrewPrifer/jimothy
README states: Train small, insanely fast local classifiers from Jev-compatible examples. Run locally in your browser or Node.js.
근거https://github.com/AndrewPrifer/jimothy/blob/master/README.md#L3
라벨readme-claim
Bodila51/muse-jev-playbook
README states: Use TypeSafe AI's Jev as a cheap, fast decision layer inside an AI agent workflow — triage, classify, score, and gate work before expensive steps (browser, deep research, retries, subagents).
근거https://github.com/Bodila51/muse-jev-playbook/blob/main/README.md#L3
라벨readme-claim
browser-use/jev-ultrafast
README states:
근거https://github.com/browser-use/jev-ultrafast/blob/main/jev_ultrafast/model.py#L119
라벨call-site-verified
droidrun/mobile-jev
README states: One goal. A real Android phone. Jev makes the decisions.
근거https://github.com/droidrun/mobile-jev/blob/main/scripts/mobile-agent/policy.mjs#L224
라벨call-site-verified
ethanplusai/jev-chat-for-twitch
README states: Sign up at typesafe.ai and create an API key. The key stays in your browser profile. You pay TypeSafe directly for what you use.
근거https://github.com/ethanplusai/jev-chat-for-twitch/blob/main/README.md#L28
라벨readme-claim
filedcom/playjev
README states: Stagehand, but with Jev. Natural-language browser automation for Playwright, powered by Jev.
근거https://github.com/filedcom/playjev/blob/main/src/core/playjev.ts#L305
라벨call-site-verified
forvela/jev-agent-browser
README states: Give a parent agent a bounded browser task. Jev chooses the next typed action. agent-browser executes it. Ambiguity, repetition, or a stuck state becomes a structured handoff back to the parent.
근거https://github.com/forvela/jev-agent-browser/blob/main/src/decision.js#L1
라벨call-site-verified
idovmamane/dejevu
README states: Jev? Déjà vu. Browser agents that run on instinct, no Jev needed. One look at the page. One call to any open model. One action.
근거https://github.com/idovmamane/dejevu/blob/main/dejevu/policy.py#L209
라벨call-site-verified
jkudish/jev-browser
README states:
근거https://github.com/jkudish/jev-browser/blob/main/src/questions.ts#L4
라벨call-site-verified
Liyucheng1997/332_lab-jev-chat
README states: 采集:一个 App 一个适配器(app/src/main/java/com/jev/probe/capture/ChatAppAdapter.kt),服务按前台包名分发;适配器只负责把当前窗口变成「标题 + 消息列表(谁说的、说了什么)」,下游判断 / 悬浮窗 / 填入全部通用。微信适配器读聊天气泡(com.tencent.mm:id/bkl),按气泡位置判断谁说的;QQ 适配器读正文节点(com.tencent.mobileqq:id
근거https://github.com/Liyucheng1997/332_lab-jev-chat/blob/main/README.md#L50
라벨readme-claim
michaelswissa/jevry
README states: The historical beta.1 study ran three five-turn sessions per implementation, with the same fixture tasks and resolved Claude model. Jevry also used Jev for browser decisions.
근거https://github.com/michaelswissa/jevry/blob/main/desktop/engine.ts#L205
라벨call-site-verified
ndolinschi/swarmrouter
README states: Pick which agent/skill handles a task (research / code / browser / support / writer) + confidence — visual swarm map powered by TypeSafe Jev.
근거https://github.com/ndolinschi/swarmrouter/blob/main/src/app/api/decide/route.ts#L7
라벨call-site-verified
phyous/tsai-civ2
README states: An original Civilization II browser harness for TypeSafe Jev, with live decision
근거https://github.com/phyous/tsai-civ2/blob/main/civ2/session.py#L486
라벨call-site-verified
pst2154/Nemotron_Jev
README states: Ask typed questions about text or JSON and inspect model-derived probability distributions in a browser. One container runs the model, the original Decision Lab explorer, and a TypeSafe-shaped API.
근거https://github.com/pst2154/Nemotron_Jev/blob/master/README.md#L3
라벨readme-claim
rokcso/bluenoise
README states: BlueNoise collects no telemetry or analytics. It does not read cookies, access account credentials, call X APIs, or take account actions such as blocking, muting, following, or posting. Settings and rules are stored thro
근거https://github.com/rokcso/bluenoise/blob/main/README.md#L34
라벨readme-claim
Sac-Y/Jev-cu
README states: 把 Computer Use 的「下一步点哪里」交给 Jev(TypeSafe System One):Jev 从界面文字候选中选元素、动作、完成度与风险,Codex Computer Use 负责读取界面与执行,本地策略门槛拦截敏感操作。只传文字,不传截图。
근거https://github.com/Sac-Y/Jev-cu/blob/main/scripts/jev-decide.mjs#L19
라벨call-site-verified
yikangy873-gif/jev-desktop
README states: Jev Desktop adds a bounded decision loop to Codex Computer Use for browser tabs and native macOS apps.
라벨call-site-verified
Ying-Kai-Liao/jev-browser
README states: jev-browser runs locally. It has no server of its own and collects no telemetry. To decide
근거https://github.com/Ying-Kai-Liao/jev-browser/blob/main/README.md#L362
라벨readme-claim
이어서 볼 페이지
체험, 문서, 사례, 가격이 서로 이어집니다. 이 페이지에서 바로 다음 페이지로 갈 수 있습니다.
이 사이트의 다른 입구
clavue-jev 사용하기
문서
- 소개이 모델이 무엇을 푸는지.
- 빠른 시작한 번의 호출로 실행되는 최소 예시.
- System One이 사이트가 쓴 개념: 상태에 타입이 있는 질문 하나. 모델은 clavue-jev.
- 상태판정에 보내는 텍스트.
- 신뢰도반환의 확실성. 자동 실행 여부를 정할 때 씁니다.
- Choice상호 배타적인 선택지에서 하나를 고름.
- Noul예/아니오 질문으로, '예'의 확률로 반환됩니다.
- Score척도를 따라 점수를 매김.
- 의도 라우팅Choice 한 번으로 요청을 하위로 보냅니다.
- 신뢰도 라우팅신뢰도가 높으면 자동 실행, 낮으면 사람에게.
- 팬아웃하나의 상태에 여러 질문을 동시에.
- 복합 스코어링여러 점수를 하나의 순위로 합칩니다.
- HTTP APISDK 없이 쓰는 요청 형태.
- Python SDKPython에서 판정을 호출합니다.
- JavaScript SDKJavaScript에서 판정을 호출합니다.