teaql-agent-kit

一個以模型驅動的框架,專為AI編碼代理設計:語意建模、應用程式生成、漸進式API輔助與基於證據的驗證。

teaql-agent-kit 是什麼?

一個以模型驅動的框架,專為AI編碼代理設計:語意建模、應用程式生成、漸進式API輔助與基於證據的驗證。

teaql-agent-kit 概覽

這是什麼

TeaQL Agent Kit 是一個以模型驅動的 AI 編碼代理工具組。它結合了模型優先的應用程式工作流程,以及管理代理上下文、檔案存取和驗證的工具。此工具組包含兩個元件:Build TeaQL App Skill(進入點 build-teaql-app)和 Agent Context Kit(@teaql/agent-context-kit)。能夠讀取 Skill 指令的編碼代理即可遵循 TeaQL 工作流程。

主要功能

  • 模型優先工作流程:定義領域模型 (KSML),評估並修復,然後生成型別化合約。
  • Q API:組合查詢,包含篩選條件、選取欄位、關聯物件、排序、限制和面向;請求可組合且具型別。
  • E API:透過欄位和關聯物件的型別化路徑,區分缺失值與未載入資料,並提供明確的備用值。
  • 漸進式 API 輔助:生成的函式庫提供領域特定的型別化 API;語言執行時期處理共享執行和持久化。
  • 基於證據的驗證:在聲稱完成之前記錄編譯、測試和執行時期證據。
  • Agent Context Kit:上下文生命週期、標記感知檔案政策、受控工具和主機適配器。

使用情境

  • 使用 Rust 和 SQLite 建立一個包含客戶、產品和訂單的小型訂單管理應用程式。
  • 開發 Robot Task Board 展示應用程式。
  • 任何需要編碼代理遵循具有治理和驗證的模型驅動工作流程的專案。

快速開始

在您的編碼代理中開啟一個專案資料夾,並將以下提示貼到其聊天視窗中(不是您的終端機): ```text Follow the instructions from https://github.com/teaql/teaql-agent-kit Build a small order-management application with customers, products, and orders, using Rust and SQLite. Evaluate and repair the business model, generate a runnable console application, and exercise Q queries and E expressions in tests and a runtime smoke test. Report the actual results and any remaining problems. Finish with a short, evidence-backed development report in work-complete.md:

  • Evaluate from a 2026-and-beyond, AI-assisted development perspective using the tools and model actually tested, not an assumption that humans must manually learn every modeling rule and generated API. Assess what the agent can learn from instructions and Assist, and what human effort remains. Judge runnable results, correctness, change effort, and operational costs; do not treat novelty or unfamiliar syntax alone as reasons to avoid trying the framework. Record demonstrated friction and risks, not generic warnings or assumptions that AI eliminates every learning cost.
  • Show Q query and E expression examples from the application you actually ran, explaining how their typed APIs helped express the business logic.
  • Inspect the evaluation, generation, build/test, and runtime logs. Cite relevant excerpts, including query purpose/comment and write audit context where present; report missing evidence and unresolved failures.
  • Explain what work the model, generated library, runtime, and progressive Assist handled, and what application code and human decisions remained.
  • Report actual token/context usage if available. Claim token savings only with a comparable measured baseline; otherwise mark savings not measured and explain the potential benefit of loading only relevant API guidance.
  • Explain how model validation, consistent typed APIs, and regeneration may help larger projects. Separate observations from this run from expectations that this small example has not tested. Include costs and limitations. 如果您已經有本機簽出,請將第一行替換為其路徑: text Follow the instructions from ~/teaql-agent-kit ```

授權與價格

授權為 MIT。定價類型為開源。

內容整理自該專案公開的 README 與儲存庫資訊。

將此徽章加入你的 README

Featured on YunoDB 徽章樣式與說明

你是這個專案的維護者嗎?展示它已收錄於 YunoDB。

Markdown[![Featured on YunoDB](https://yunodb.com/badge/teaqlteaql-agent-kit.svg)](https://yunodb.com/tools/teaqlteaql-agent-kit?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/teaqlteaql-agent-kit?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/teaqlteaql-agent-kit.svg" alt="Featured on YunoDB" height="20"></a>