经 AI Skill Hub 精选评估，AI工作流 获评「强烈推荐」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色，AI 评分 8.0 分，适合有一定技术背景的用户使用。
AI工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
AI工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一：npm 全局安装 npm install -g agents-js # 方式二：npx 直接运行（无需安装） npx agents-js --help # 方式三：项目依赖安装 npm install agents-js # 方式四：从源码运行 git clone https://github.com/livekit/agents-js cd agents-js npm install npm start
# 命令行使用
agents-js --help
# 基本用法
agents-js [options] <input>
# Node.js 代码中使用
const agents_js = require('agents-js');
const result = await agents_js.run(options);
console.log(result);
# agents-js 配置说明 # 查看配置选项 agents-js --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量（覆盖配置文件） export AGENTS_JS_CONFIG="/path/to/config.yml"
<picture> <source media="(prefers-color-scheme: dark)" srcset="/.github/banner_dark.png"> <source media="(prefers-color-scheme: light)" srcset="/.github/banner_light.png"> <img style="width:100%;" alt="The LiveKit icon, the name of the repository and some sample code in the background." src="https://raw.githubusercontent.com/livekit/agents-js/main/.github/banner_light.png"> </picture>
The framework includes a variety of plugins that make it easy to process streaming input or generate output. For example, there are plugins for converting text-to-speech or running inference with popular LLMs.
pnpm if you haven't already:npm install -g pnpmTo install the core Agents library as well as plugins, run:
pnpm install @livekit/agentsCurrently, only the following plugins are supported:
| Plugin | Features |
|---|---|
| [@livekit/agents-plugin-openai](https://www.npmjs.com/package/@livekit/agents-plugin-openai) | LLM, TTS, STT |
| [@livekit/agents-plugin-google](https://www.npmjs.com/package/@livekit/agents-plugin-google) | LLM, TTS |
| [@livekit/agents-plugin-deepgram](https://www.npmjs.com/package/@livekit/agents-plugin-deepgram) | STT, TTS |
| [@livekit/agents-plugin-elevenlabs](https://www.npmjs.com/package/@livekit/agents-plugin-elevenlabs) | TTS |
| [@livekit/agents-plugin-cartesia](https://www.npmjs.com/package/@livekit/agents-plugin-cartesia) | TTS |
| [@livekit/agents-plugin-neuphonic](https://www.npmjs.com/package/@livekit/agents-plugin-neuphonic) | TTS |
| [@livekit/agents-plugin-resemble](https://www.npmjs.com/package/@livekit/agents-plugin-resemble) | TTS |
| [@livekit/agents-plugin-rime](https://www.npmjs.com/package/@livekit/agents-plugin-rime) | TTS |
| [@livekit/agents-plugin-inworld](https://www.npmjs.com/package/@livekit/agents-plugin-inworld) | TTS |
| [@livekit/agents-plugin-silero](https://www.npmjs.com/package/@livekit/agents-plugin-silero) | VAD |
| [@livekit/agents-plugin-livekit](https://www.npmjs.com/package/@livekit/agents-plugin-livekit) | EOU |
| [@livekit/agents-plugin-anam](https://www.npmjs.com/package/@livekit/agents-plugin-anam) | Avatar |
| [@livekit/agents-plugin-bey](https://www.npmjs.com/package/@livekit/agents-plugin-bey) | Avatar |
| [@livekit/agents-plugin-lemonslice](https://www.npmjs.com/package/@livekit/agents-plugin-lemonslice) | Avatar |
| [@livekit/agents-plugin-liveavatar](https://www.npmjs.com/package/@livekit/agents-plugin-liveavatar) | Avatar |
| [@livekit/agents-plugin-mistralai](https://www.npmjs.com/package/@livekit/agents-plugin-mistralai) | LLM, STT, TTS |
| [@livekit/agents-plugin-xai](https://www.npmjs.com/package/@livekit/agents-plugin-xai) | LLM, TTS |
| [@livekit/agents-plugin-phonic](https://www.npmjs.com/package/@livekit/agents-plugin-phonic) | Realtime |
| [@livekit/agents-plugin-fishaudio](https://www.npmjs.com/package/@livekit/agents-plugin-fishaudio) | TTS |
| [@livekit/agents-plugin-hume](https://www.npmjs.com/package/@livekit/agents-plugin-hume) | TTS |
Documentation on the framework and how to use it can be found here
Checkout the quickstart guide
To test any changes or plugins:
1. Build the project:
pnpm build
./examples/src/basic_agent.ts as necessary for any plugin changes3. Run the basic agent with debug logging:
node ./examples/src/basic_agent.ts dev --log-level=debug
When you follow the steps above to run your agent, a worker is started that opens an authenticated WebSocket connection to a LiveKit server instance(defined by your LIVEKIT_URL and authenticated with an access token).
No agents are actually running at this point. Instead, the worker is waiting for LiveKit server to give it a job.
When a room is created, the server notifies one of the registered workers about a new job. The notified worker can decide whether or not to accept it. If the worker accepts the job, the worker will instantiate your agent as a participant and have it join the room where it can start subscribing to tracks. A worker can manage multiple agent instances simultaneously.
If a notified worker rejects the job or does not accept within a predetermined timeout period, the server will route the job request to another available worker.
The orchestration system was designed for production use cases. Unlike the typical web server, an agent is a stateful program, so it's important that a worker isn't terminated while active sessions are ongoing.
When calling SIGTERM on a worker, the worker will signal to LiveKit server that it no longer wants additional jobs. It will also auto-reject any new job requests that get through before the server signal is received. The worker will remain alive while it manages any agents connected to rooms.
高质量的AI工作流构建工具
AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议，可商用，需保留版权声明和 NOTICE 文件，含专利授权条款。
AI Skill Hub 点评：AI工作流 的核心功能完整，质量优秀。对于自动化工程师和运维人员来说，这是一个值得纳入个人工具库的选择。建议先在非生产环境试用，再逐步推广。
| 原始名称 | agents-js |
| 原始描述 | 开源AI工作流：Build realtime multimodal AI agents with Node.js。⭐839 · TypeScript |
| Topics | AINode.jsTypeScript |
| GitHub | https://github.com/livekit/agents-js |
| License | Apache-2.0 |
| 语言 | TypeScript |
收录时间：2026-05-25 · 更新时间：2026-05-26 · License：Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型，复制安装指令后粘贴到对应客户端