Urgent.News

What's breaking now, across thousands of outlets.

Tech

ag-ui: A Chinese Translation of the Agent-User Interaction Protocol

ag-ui-protocol/ag-ui has 20219 stars and is written in TypeScript. The Chinese translation at yangshun2005/ag-ui-cn was published on 2026-11-18 and currently has no stars of its own. That second number is the honest starting point for this piece: the translation is new, and what follows describes what it contains rather than how well it has been received. What the original project actually is…

<ins>AG-UI: A Chinese Translation of the Agent-User Interaction Protocol</ins>

The AG-UI protocol, a lightweight, open-source event-based system, allows AI agents to connect to user-facing applications without relying on the traditional request/response model. The protocol enables agents to stream tokens, call tools mid-response, update shared state, pause for human input, and spawn sub-agents. The protocol is framework-agnostic, meaning any client can render the protocol regardless of the framework used to build the agent.

The Chinese translation of the AG-UI protocol, hosted at yangshun2005/ag-ui-cn, was published on 2026-11-18 and currently has no stars of its own. This document analyzes the translation and its contents.

The translation is a faithful reproduction of the original README, with one additional section: a Chinese quick-start guide. The guide is split into two parts: a quick-start guide at the top and the translated README body below it. The quick-start section aims to help non-English-speaking developers get the project running quickly, while the translated README provides a faithful reproduction of the original content.

The Chinese guide highlights two common setup paths: the CLI scaffold and the protocol example. The CLI scaffold generates a frontend using the chosen agent framework and requires setting an OpenAI API key before starting the dev server. The protocol example, on the other hand, consists of a 30-line agent server and a client that does not require any API key. The guide explicitly notes that these two paths are operationally independent, and commands from one path do not apply to the other.

The translation also addresses minimum version requirements for the server and client. The server requires Python 3.9+, while the client needs Node.js 20 or higher. These version requirements are easy to miss in the original README, which the Chinese guide points out.

The Chinese translation includes a section on common pitfalls, such as forgetting to set the OpenAI API key, missing version requirements, or confusing the two setup paths. Additionally, the guide provides compatibility notes for upgrading to the 1.0 spec, which is now frozen and backward compatible in both directions.

It is essential to note that the Chinese translation is not a fork of the protocol, an SDK, or a set of additional examples. It is purely documentation, and the code samples are reproduced from the original protocol. Bugs in the protocol should be reported upstream at ag-ui-protocol/ag-ui, while translation errors should be addressed in this repository.

In conclusion, the Chinese translation of the AG-UI protocol aims to reduce friction for non-English-speaking developers by providing a quick-start guide, highlighting common pitfalls, and clearly distinguishing between the original content and the Chinese additions.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in Tech

Long context vs RAG: why search when a model reads it all?

For long context vs RAG, start with full-document input when one document fits and you need only a few answers; test retrieval for repeated questions over a large collection.

  • Long context allows processing entire document if within model's 128k-1M token window
  • RAG offers efficiency for large document collections by retrieving key passages
  • RAG risk lies in retrieval accuracy, potentially leading to incorrect answers

🌳 Pine Script into readable Python for Free

Download the converted 449 strategies and 471 indicators via this link I built a free compiler and translated over 1000 popular trading strategies and indicators from TradingView into Python source…

  • Free compiler translates 1,000+ TradingView strategies to Python
  • 384 strategies and 458 indicators achieve bit-for-bit consistency
  • Supports multiple exchanges via CCXT library for candlestick charting

The Design Logic Behind Eight Skills

In the previous post I said that the defenses we bought with real incidents eventually turned into eight concrete SKILLs. This post explains how to use those eight.

More from Wednesday 18 November →