agora

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Agora (agora.io)

Skill version: 1.1.0

Build real-time communication applications using Agora SDKs across Web, iOS, Android, and server-side platforms.

技能版本：1.1.0

使用Agora SDK跨Web、iOS、Android及服务端平台构建实时通信应用。

Core Concepts

核心概念

App ID: Project identifier from Agora Console. Required for all SDK calls.
App Certificate: A unique key generated by the Agora Console, unique to each project, for use in creating authentication tokens.
Token: Time-limited auth key generated server-side from App ID + App Certificate. Never expose App Certificate on client. For testing, disable token authentication in Agora Console and pass
```
null
```
as the token.
Channel: Auto-created when first user joins, destroyed when last leaves. Users in same channel can communicate.
UID: Unique user identifier per channel. Pass
```
null
```
/
```
0
```
for auto-assignment. Duplicate UIDs cause undefined behavior.

App ID：来自Agora控制台的项目标识符。所有SDK调用均需使用。
App Certificate：由Agora控制台生成的唯一密钥，每个项目对应一个，用于生成身份验证Token。
Token：通过App ID + App Certificate在服务端生成的限时身份验证密钥。切勿在客户端暴露App Certificate。测试时，可在Agora控制台禁用Token身份验证，将
```
null
```
作为Token传入。
频道：首个用户加入时自动创建，最后一个用户离开时销毁。同一频道内的用户可进行通信。
UID：每个频道内的唯一用户标识符。传入
```
null
```
/
```
0
```
可自动分配。重复的UID会导致未定义行为。

Products

产品模块

Read the README for the product the user needs. Only load what is needed.

请阅读用户所需产品的README文档，仅加载必要内容。

RTC (Video/Voice SDK)

RTC（音视频SDK）

Real-time audio and video. Users join channels, publish local tracks, subscribe to remote tracks.

references/rtc/README.md — Platforms: Web, React, iOS, Android

提供实时音视频能力。用户可加入频道、发布本地音视频轨道、订阅远端音视频轨道。

references/rtc/README.md — 支持平台：Web、React、iOS、Android

RTM (Signaling / Messaging)

RTM（信令/消息）

Text messaging, signaling, presence, and metadata. Independent from RTC — channel namespaces are separate.

references/rtm/README.md — Platforms: Web

提供文本消息、信令、在线状态及元数据能力。独立于RTC——频道命名空间相互分离。

references/rtm/README.md — 支持平台：Web

Conversational AI (Voice AI Agents)

对话式AI（语音AI Agent）

REST API-driven voice AI agents. Create agents that join RTC channels and converse with users via speech. Front-end clients connect via RTC+RTM.

references/conversational-ai/README.md — REST API, agent config, 6 recipe repos (agent-samples, agent-toolkit, agent-client-toolkit-react, agent-ui-kit, server-custom-llm, server-mcp)

基于REST API的语音AI Agent。可创建加入RTC频道并通过语音与用户对话的Agent。前端客户端通过RTC+RTM连接。

references/conversational-ai/README.md — 包含REST API、Agent配置、6个示例仓库（agent-samples、agent-toolkit、agent-client-toolkit-react、agent-ui-kit、server-custom-llm、server-mcp）

Cloud Recording

云端录制

Server-side recording of RTC channel audio/video. REST API only — no client SDK needed.

references/cloud-recording/README.md

服务端录制RTC频道音视频内容。仅需REST API——无需客户端SDK。

references/cloud-recording/README.md

Server-Side

服务端工具

Token generation and server utilities. Required for production authentication.

references/server/README.md — Token generation for Node.js, Python, Go

Token生成及服务端实用工具。生产环境身份验证必备。

references/server/README.md — 支持Node.js、Python、Go的Token生成

Server Gateway SDK

Self-hosted Linux SDK for server-side audio/video stream transmission. Use when a server process needs to send or receive media in an Agora RTC channel (call centers, AI audio processing, network testing).

references/server-gateway/README.md — C++, Java, Go, Python

用于服务端音视频流传输的自托管Linux SDK。适用于服务端进程需在Agora RTC频道中发送或接收媒体的场景（如呼叫中心、AI音频处理、网络测试）。

references/server-gateway/README.md — 支持C++、Java、Go、Python

Testing Guidance

测试指南

Mocking patterns and testing requirements for Agora SDK integration code.

references/testing-guidance/SKILL.md

Agora SDK集成代码的模拟模式及测试要求。

references/testing-guidance/SKILL.md

Routing

请求路由规则

Clear, product-specific request: Route directly to the relevant product README. Do not load

intake/SKILL.md

Examples of clear requests:

"RTC Web video call" →
```
references/rtc/web.md
```
"ConvoAI Python" →
```
references/conversational-ai/README.md
```
"Generate RTC token in Go" →
```
references/server/tokens.md
```

Vague or multi-product request: Route through

intake/SKILL.md

. Intake handles product identification, combination recommendations, and routing.

明确的、产品特定的请求：直接路由至对应产品的README文档。请勿加载

intake/SKILL.md

。

明确请求示例：

"RTC Web视频通话" →
```
references/rtc/web.md
```
"ConvoAI Python" →
```
references/conversational-ai/README.md
```
"使用Go生成RTC Token" →
```
references/server/tokens.md
```

模糊或多产品请求：通过

intake/SKILL.md

进行路由。该入口文件负责产品识别、组合推荐及路由。

Documentation Lookup

文档查询规则

Check bundled references first (Level 1). If they don't cover the detail needed, fetch

https://docs.agora.io/en/llms.txt

, find the relevant URL, and fetch it (Level 2). See references/doc-fetching.md for the full procedure, fallback URLs, and freeze-forever decision table.

Always fetch Level 2 before answering questions about: TTS/ASR/LLM vendor configs, model names, full request/response schemas, error code listings, or release notes. These change frequently — do not answer from training data or memory.

If MCP is unavailable or Level 2 fetch fails: use the fallback URLs in

doc-fetching.md

to reach the official markdown docs directly. Never fabricate API parameters — always tell the user to verify against official docs if live fetch is unavailable.

If a user explicitly asks about the Agora MCP server, see references/mcp-tools.md.

优先查询内置参考文档（一级文档）。若无法覆盖所需细节，请获取

https://docs.agora.io/en/llms.txt

，找到相关URL后获取对应内容（二级文档）。完整流程、备用URL及永久冻结决策表请查看references/doc-fetching.md。

以下内容必须先获取二级文档再作答：TTS/ASR/LLM厂商配置、模型名称、完整请求/响应 schema、错误代码列表或发布说明。这些内容更新频繁——请勿根据训练数据或记忆作答。

若MCP不可用或二级文档获取失败：使用

doc-fetching.md

中的备用URL直接访问官方Markdown文档。切勿编造API参数——若无法实时获取文档，请告知用户以官方文档为准。

若用户明确询问Agora MCP服务器，请查看references/mcp-tools.md。

Web Framework Notes

Web框架注意事项

Next.js / SSR

Agora SDKs are browser-only. See references/rtc/nextjs.md for the required dynamic import patterns —

next/dynamic

with

ssr: false

does not work in Next.js 14+ Server Components without extra steps.

Agora SDK仅支持浏览器环境。如需了解所需的动态导入模式，请查看**references/rtc/nextjs.md**——在Next.js 14+的Server Components中，不带额外配置的

next/dynamic

（设置

ssr: false

）无法正常工作。