Skip to content

构建生产级AI应用的12条指南包括:将自然语言指令转换为工具调用、优化提示词、有效管理上下文窗口、将工具视为结构化输出、统一执行状态与业务状态、提供简单API控制执行流程、通过工具调用与人类交互、设计控制流程、压缩错误信息、构建小而专注的智能体、满足用户需求的触发方式,以及设计无状态的代理以简化状态管理。What are the principles we can use to build LLM-powered

TypeScript · active 2025-03-31 → 2026-09-22 (UTC)

Complete coverage27,283 / 27,286 hourly files (100%) · 2 absent upstream2023-08-15 → 2026-09-24 (UTC)
Events
13K
Pushes
133
Pull requests
90
Issues
17
Stars
11.8K
Forks
820

Activity over time

Daily event counts in the loaded window

Line chart, 541 days from 2025-03-31 to 2026-09-22. Pushes: 133 total, peak 23 in a day. Pull requests: 90 total, peak 10 in a day. Issues: 17 total, peak 3 in a day. Comments: 70 total, peak 8 in a day. Stars: 11,801 total, peak 799 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 11,801 stars here means stars gained during the window, not the repo's star count.