尚未偵測到更新。GitHub 發布版本後會顯示在這裡。
個人 GitHub 帳號下公開儲存庫的擁有者可以登入並驗證所有權,自行管理介紹,無需管理員核准。
登入並產生驗證檔案,在 30 分鐘內將其提交至此儲存庫的預設分支。其他分支或分叉儲存庫中的檔案無效。然後在下方檢查檔案,即可無需管理員核准直接管理專案。請保留檔案以維持管理權限。
如需登入,將前往登入頁面。登入後請回到此處,再次點擊所選的驗證按鈕。
在專案資料夾中執行 /nomorevibe verify,即可驗證所有權並自行管理介紹。
一分鐘完成驗證製作者的介紹僅有上面的一句話。 更多詳情請閱讀儲存庫 README。 儲存庫 README ↗
正在載入完整 README。
檢視完整 README ↗Building AI apps shouldn't mean sacrificing code quality.
Your AI code is scattered across files, riddled with inconsistent patterns, and nearly impossible to maintain. Every new feature feels like adding another layer to an already fragile house of cards. You're not alone - developers everywhere are drowning in AI complexity, but software doesn't have to be this way.
primitives.org.ai provides battle-tested building blocks for AI applications. These aren't experimental toys - they're production-grade primitives with full TypeScript support, designed to compose elegantly and scale confidently.
1. Install
npm install ai-functions
2. Import
import { ai } from 'ai-functions'
3. Ship
const sentiment = await ai.is('This product is amazing!', {
positive: 'Expresses satisfaction or enthusiasm',
negative: 'Expresses disappointment or frustration',
neutral: 'Neither positive nor negative'
})
// => 'positive'
const summary = await ai.do('Summarize this article in 3 bullet points', {
article: longArticleText
})
const users = await ai.list('Generate 5 realistic user personas for a fitness app')
| Package | Description |
|---|---|
ai-functions | Type-safe AI function calls with ai.do(), ai.is(), ai.list(), and more |
ai-database | AI-powered database operations with semantic search and CRUD |
ai-workflows | Event-driven workflows and state machine orchestration |
| Package | Description |
|---|---|
digital-workers | Unified interface for AI agents and human workers |
digital-tasks | Task queues with dependencies, priorities, and lifecycle management |
digital-tools | Tool definitions compatible with MCP and function calling |
| Package | Description |
|---|---|
autonomous-agents | Build and orchestrate autonomous AI agents with goals |
human-in-the-loop | Integrate human oversight and approval workflows |
@org.ai/authority | Zero-dependency authority kernel - five-axis tokens, register discipline, and competence-typed gates (docs) |
| Package | Description |
|---|---|
business-as-code | Model business processes, KPIs, and OKRs in code |
services-as-software | Transform services into programmable software interfaces |
# Core package (most users start here)
npm install ai-functions
# Additional packages as needed
npm install ai-database ai-workflows digital-tasks
MIT