瀏覽器使用 + Jev
Gregor Zunic 的動態 DOM 操作空間飛行搜尋示範。
A FIELD GUIDE TO JEV / VOL. 01
匯集 Jev 的真實專案、實用指南和來自全網的創意。
Gregor Zunic 的動態 DOM 操作空間飛行搜尋示範。
01 / A small decision engine. A whole new way to build.
714 項資源 / 資源集
重設篩選AI-assisted summaries and translations. Check original sources for context and performance claims.
瀏覽器使用場景中的超快速代理:Jev 在一次請求中選擇操作和 DOM 元素;僅在需要輸入時使用小型 LLM 寫入文字。
Claude Code插件透過Jev決策替換壓縮摘要,單一快速請求中評分所有工具呼叫與結果,過時資料被刪除或截斷,保留資料原樣不變。
官方同步與非同步 Python 客戶端。pip install typesafe-sdk。
Claude Code、Codex 及相容代理的官方代理技能:基本動作、模式及評估結構方式。
支援 OpenAI、Anthropic 及相容 LLM API 的官方 TypeSafeClient 替代品,用於比較 Jev 與聊天模型。
官方 TypeScript/JavaScript 客戶端,具備推斷答案類型功能。npm install @typesafe-ai/sdk。
命令列工具,用於TypeSafe AI的Jev模型,可針對任何文字提出是非、選擇題和評分標準問題,並回傳校準機率。
使用Jev,TypeSafe AI的System One模型所建構的專案精選清單。
TypeScript官方AI SDK的Elixir類型安全埠,提供統一的LLM整合、串流文字、結構化輸出、工具呼叫和代理工作流程。Jev是其目前旗艦模型,也是第一個System One模型。
PadFlow(土地開發SaaS)的類型決策基準測試:模式、匿名標記資料行及用於信心校準模型的執行器。
Fast semantic code search & diff sanity auditor for AI coding assistants (Antigravity, Cursor, Claude Code) powered by TypeSafe System One.
Go SDK for the TypeSafe AI API — typed questions in, probability distributions out.
Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
Guardrail + model router for LLM gateways on TypeSafe's Jev (System One model), with an independent accuracy/calibration/latency evaluation. Stdlib Python.
List of projects that use typesafe's jev.
Benchmarks Jev against other evaluation models in games with explicit states, legal actions, and measurable outcomes.
Hunch is a GitHub tool for code review that applies rules written in plain English to analyze and improve code quality.
Sub-second Git pre-commit & pre-push semantic reflex gate powered by TypeSafe AI Jev.
Dasheng is a GitHub tool combining speech recognition with Jev for real-time word-by-word transcription and marking of spoken content.
Jev-Tool-Runner is a GitHub project where Jev selects developer tools and Codex generates code based on those selections.
Visual-Jev is a GitHub research project that makes decisions based on images rather than text descriptions of visual content.
Screen a folder of CVs with the TypeSafe Jev decision model: typed judgments, an editable policy, free re-scoring.
Chess moves, evaluations, persona opponents, and game classification with TypeSafe AI System One.
Chrome-devtools-mcp plus one tool: Jev walks the browser to the right spot, then your agent makes a single devtools call there.