ブラウザとコンピュータ操作
このカテゴリの 18 件。各項目に具体的な判断と開ける根拠リンクがあります。
AndrewPrifer/jimothy
README states: Train small, insanely fast local classifiers from Jev-compatible examples. Run locally in your browser or Node.js.
根拠https://github.com/AndrewPrifer/jimothy/blob/master/README.md#L3
ラベルreadme-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).
根拠https://github.com/Bodila51/muse-jev-playbook/blob/main/README.md#L3
ラベルreadme-claim
browser-use/jev-ultrafast
README states:
根拠https://github.com/browser-use/jev-ultrafast/blob/main/jev_ultrafast/model.py#L119
ラベルcall-site-verified
droidrun/mobile-jev
README states: One goal. A real Android phone. Jev makes the decisions.
根拠https://github.com/droidrun/mobile-jev/blob/main/scripts/mobile-agent/policy.mjs#L224
ラベルcall-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.
根拠https://github.com/ethanplusai/jev-chat-for-twitch/blob/main/README.md#L28
ラベルreadme-claim
filedcom/playjev
README states: Stagehand, but with Jev. Natural-language browser automation for Playwright, powered by Jev.
根拠https://github.com/filedcom/playjev/blob/main/src/core/playjev.ts#L305
ラベルcall-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.
根拠https://github.com/forvela/jev-agent-browser/blob/main/src/decision.js#L1
ラベルcall-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.
根拠https://github.com/idovmamane/dejevu/blob/main/dejevu/policy.py#L209
ラベルcall-site-verified
jkudish/jev-browser
README states:
根拠https://github.com/jkudish/jev-browser/blob/main/src/questions.ts#L4
ラベルcall-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
根拠https://github.com/Liyucheng1997/332_lab-jev-chat/blob/main/README.md#L50
ラベルreadme-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.
根拠https://github.com/michaelswissa/jevry/blob/main/desktop/engine.ts#L205
ラベルcall-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.
根拠https://github.com/ndolinschi/swarmrouter/blob/main/src/app/api/decide/route.ts#L7
ラベルcall-site-verified
phyous/tsai-civ2
README states: An original Civilization II browser harness for TypeSafe Jev, with live decision
根拠https://github.com/phyous/tsai-civ2/blob/main/civ2/session.py#L486
ラベルcall-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.
根拠https://github.com/pst2154/Nemotron_Jev/blob/master/README.md#L3
ラベルreadme-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
根拠https://github.com/rokcso/bluenoise/blob/main/README.md#L34
ラベルreadme-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。
根拠https://github.com/Sac-Y/Jev-cu/blob/main/scripts/jev-decide.mjs#L19
ラベルcall-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.
ラベルcall-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
根拠https://github.com/Ying-Kai-Liao/jev-browser/blob/main/README.md#L362
ラベルreadme-claim
このまま次のページへ
試用・ドキュメント・事例・料金はつながっています。このページから次のページへ直接進めます。
このサイトの他の入口
clavue-jev を使う
ドキュメント
- 紹介このモデルが何を解くのか。
- クイックスタート1 回の呼び出しで動く最小例。
- System One当サイトが書いた概念:状態に型付きの質問を 1 つ。モデルは clavue-jev。
- 状態判定に送るテキスト。
- 信頼度返り値の確かさ。自動実行の可否を決めるのに使う。
- Choice排他的な選択肢から 1 つ選ぶ。
- Noulはい/いいえの質問。はいの確率として返る。
- Score尺度に沿って点数を付ける。
- 意図ルーティングChoice 1 回でリクエストを下流へ振り分ける。
- 信頼度ルーティング信頼度が高ければ自動実行、低ければ人へ。
- ファンアウト1 つの状態に複数の質問を同時に投げる。
- 複合スコアリング複数のスコアを 1 つの順位にまとめる。
- HTTP APISDK を入れない場合のリクエスト形状。
- Python SDKPython から判定を呼ぶ。
- JavaScript SDKJavaScript から判定を呼ぶ。