{"id":44112357,"url":"https://github.com/chicogong/conversational-ai-agent","last_synced_at":"2026-02-08T16:34:21.774Z","repository":{"id":292301676,"uuid":"978697162","full_name":"chicogong/conversational-ai-agent","owner":"chicogong","description":"TRTC-based Conversational AI Agent Platform - real-time voice/video AI interactions","archived":false,"fork":false,"pushed_at":"2025-12-23T12:30:46.000Z","size":15686,"stargazers_count":0,"open_issues_count":10,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-12-25T01:52:27.849Z","etag":null,"topics":["a2a","ai-agent","asr","conversational-ai","express","golang","llm","mcp","nodejs","openai","python","real-time","tencent-cloud","trtc","tts","typescript","vad","voice-assistant","voice-chat","voiceprint"],"latest_commit_sha":null,"homepage":null,"language":"HTML","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/chicogong.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-05-06T11:31:59.000Z","updated_at":"2025-12-24T12:05:28.000Z","dependencies_parsed_at":null,"dependency_job_id":"b7c84e93-8647-45bf-a797-6660c099ee63","html_url":"https://github.com/chicogong/conversational-ai-agent","commit_stats":null,"previous_names":["chicogong/conversational-ai-agent"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/chicogong/conversational-ai-agent","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chicogong%2Fconversational-ai-agent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chicogong%2Fconversational-ai-agent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chicogong%2Fconversational-ai-agent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chicogong%2Fconversational-ai-agent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/chicogong","download_url":"https://codeload.github.com/chicogong/conversational-ai-agent/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chicogong%2Fconversational-ai-agent/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29236900,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-08T14:18:14.570Z","status":"ssl_error","status_checked_at":"2026-02-08T14:18:14.071Z","response_time":57,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["a2a","ai-agent","asr","conversational-ai","express","golang","llm","mcp","nodejs","openai","python","real-time","tencent-cloud","trtc","tts","typescript","vad","voice-assistant","voice-chat","voiceprint"],"created_at":"2026-02-08T16:34:20.755Z","updated_at":"2026-02-08T16:34:21.761Z","avatar_url":"https://github.com/chicogong.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🚀 Conversationsal AI Agent\n\n\u003cdiv align=\"center\"\u003e\n\n[![Conversationsal AI Agent](https://img.shields.io/badge/Conversationsal_AI_Agent-2.0.0-blue.svg)](https://cloud.tencent.com/product/trtc)\n[![AI Agent](https://img.shields.io/badge/AI_Agent-2.0.0-blue.svg)](https://cloud.tencent.com/document/product/647/110584)\n[![Node.js](https://img.shields.io/badge/Node.js-18.0.0-green.svg)](https://nodejs.org/)\n[![License](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](CONTRIBUTING.md)\n\n\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"docs/images/logo.png\" alt=\"logo\" width=\"200\"/\u003e\n\u003c/div\u003e\n\n## ✨ 产品简介\n\nConversationsal AI Agent 是一个快速 AI 应用构建平台，让您轻松打造智能语音交互应用。通过简单的配置，即可实现多种 AI 对话场景，如智能客服、语音助手、情感陪聊等。\n\n[Deepwiki for Conversationsal AI Agent](https://deepwiki.com/chicogong/conversationsal-ai-agent)\n\n## 🌟 核心特性\n\n- 🎯 **快速集成**：基于 TRTC SDK，快速实现音视频通话功能\n- 🤖 **AI能力丰富**：集成多种 AI 能力，满足不同场景需求\n- ⚙️ **灵活配置**：支持自定义 Agent 配置，轻松扩展新功能\n- 🛡️ **稳定可靠**：依托 TRTC 强大的音视频能力，确保通话质量\n- 🎨 **简单易用**：提供简洁的 API 接口，降低开发门槛\n- 🌐 **多Agent支持**：支持多种Agent类型，满足不同场景需求\n\n## 💯 核心亮点\n\n### 体验优化\n\n- ✅ **自然交互**：支持语义断句、自然停顿和思考时间\n- ✅ **环境适应**：声纹识别技术支持嘈杂环境下的对话，有效过滤背景人声\n- ✅ **真实感提升**：支持环境音模拟，增强对话真实感\n\n### 技术优化\n\n- ⚡ **响应速度**：采用分句策略实现首句快速返回，欢迎语预请求降低耗时\n- 🔊 **语音质量**：服务端噪声过滤，ASR降噪参数优化\n- 🤝 **交互体验**：智能附和语增加拟人化交互，VAD打断优化，单字过滤减少误打断\n\n### 高级功能\n\n- 📊 **服务端回调**：支持延迟统计、内容审核、通话记录存储\n- 📱 **客户端回调**：实时字幕展示、状态展示、异常处理、通话统计\n\n## 🔄 系统架构\n\n下图展示了Conversational AI Agent的核心处理流程，包括语音输入处理、AI生成和输出环节：\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"docs/images/core_process.png\" alt=\"核心处理流程\" width=\"800\"/\u003e\n\u003c/div\u003e\n\n### 主要组件\n\n- **语音输入处理**：包含ASR语音识别、AI VAD、声纹识别和情感识别等模块\n- **AI生成服务**：支持LLM、LLM+RAG、MCP、A2A、Dify、知识引擎等多种生成方式\n- **语音输出处理**：采用拟人化实时TTS技术，提供高质量的语音合成\n\n整个系统通过流式处理实现低延迟、高质量的实时对话体验。\n\n## 🎮 Agent Card 展示\n\n我们的平台支持多种 Agent 类型，每种 Agent 都有其独特的应用场景：\n\n\u003cdiv align=\"center\"\u003e\n\n| Agent 类型     | 核心功能                                                                         | 适用场景               | 实现状态  |\n| -------------- | -------------------------------------------------------------------------------- | ---------------------- | --------- |\n| 外呼客服 Agent | 自动外呼、智能话术、质量监控                                                     | 营销、客服回访         | ✅ 已实现 |\n| 甜妹陪聊 Agent | 自然交互、情感超拟人对话、个性化陪伴                                             | 社交、娱乐             | ✅ 已实现 |\n| 声纹锁定 Agent | 声纹锁定、过滤周边人声、保证高质量通话                                           | 办公室，街道等嘈杂场景 | ✅ 已实现 |\n| MCP Agent      | 接入[MCP](https://github.com/modelcontextprotocol)扩展工具调用等功能             | 更便捷的工具调用       | ✅ 已实现 |\n| A2A Agent      | 接入[A2A](https://github.com/google/A2A)协议                                     | 多Agent对话            | 🔄 开发中 |\n| Coze Agent     | 接入 [Coze](https://www.coze.com) 平台能力                                       | 快速构建智能对话应用   | 🔄 开发中 |\n| Dify Agent     | 接入 [Dify](https://dify.ai) 平台能力                                            | 企业级 AI 应用开发     | 🔄 开发中 |\n| 知识引擎 Agent | 接入[腾讯云知识引擎](https://cloud.tencent.com/product/lke) 企业级知识库解决方案 | 智能问答、知识库查询   | 🔄 开发中 |\n\n\u003c/div\u003e\n如果需要某个Agent可以留言，我们会尽快为您提供。\n当然，您也可以根据您的需求，创建自己的Agent。\n也可以将您的AgentCard贡献到这个项目中，让更多的人使用您的Agent。\n\n## 🚀 快速开始\n\n### 1. 安装依赖\n\n```bash\nnpm install\n```\n\n### 2. 配置环境变量\n\n复制 `env.example` 文件为 `.env`，并填入您的实际配置值：\n\n```bash\ncp env.example .env\n# 然后编辑 .env 文件，填入您的配置信息\n```\n\n主要环境变量包括：\n\n- 腾讯云API凭证（TENCENT_SECRET_ID, TENCENT_SECRET_KEY）：从[腾讯云 API 密钥](https://console.cloud.tencent.com/cam/capi)获取\n- TRTC配置（TRTC_SDK_APP_ID, TRTC_SECRET_KEY）：从[TRTC 控制台](https://console.cloud.tencent.com/trtc/app)获取\n- LLM配置（LLM_API_KEY, LLM_API_URL, LLM_MODEL）：从您的 LLM 服务提供商获取\n- TTS配置：\n  - 腾讯云 TTS: AppId从[TTS 控制台](https://console.cloud.tencent.com/tts)获取，SecretId和SecretKey从[腾讯云 API 密钥](https://console.cloud.tencent.com/cam/capi)获取\n  - Minimax TTS: GroupId, APIKey, VoiceType从 Minimax 控制台获取\n\n### 3. 使用配置向导创建Agent(可选)\n\n运行以下命令来创建您的自定义AI助手：\n\n```bash\nnpm run create\n```\n\n按照提示输入您的配置信息，向导将自动创建Agent配置文件。\n\n### 4. 启动应用\n\n```bash\nnpm start\n```\n\n## 🛠️ 自定义Agent配置\n\n### 配置向导\n\n设置向导将要求您提供以下信息：\n\n- **基本信息**：助手ID、名称、描述、能力列表、语音类型、个性\n- **行为配置**：欢迎消息、打断模式\n- **语音识别配置**：语言模型、热词列表\n- **大语言模型配置**：LLM类型、历史长度、系统提示词\n- **文本转语音配置**：TTS提供商、语音模型、语速\n\n## 📦 项目结构\n\n```\nconversational-ai-agent/\n│\n├── public/                    # 静态资源\n│   ├── index.html             # 主页面\n│   └── assets/                # 图片等静态资源\n│\n├── src/                       # 源代码目录\n│   ├── js/                    # JavaScript 文件\n│   │   ├── api.js             # API 调用相关\n│   │   ├── app.js             # 应用主逻辑\n│   │   ├── trtc-client.js     # TRTC客户端\n│   │   ├── metrics.js         # 指标相关\n│   │   ├── constants.js       # 常量定义\n│   │   ├── agent-card.js      # 代理卡片\n│   │   └── ui.js              # UI 相关\n│   │\n│   ├── styles/                # CSS 样式文件\n│   │   └── styles.css         # 主样式文件\n│   │\n│   └── agent_cards/           # 代理卡片配置\n│       ├── assets/            # 代理卡片资源\n│       ├── scripts/           # 配置工具脚本\n│       │   └── create_agent.js # AI-Agent创建工具\n│       ├── sweet_girl.js      # 代理配置\n│       ├── mcp_tencent_map.js # 代理配置\n│       ├── default.js         # 默认代理\n│       └── index.js           # 导出配置\n│\n├── docs/                      # 文档\n│\n├── server.js                  # 服务器入口文件\n├── env.example                # 环境变量示例\n├── package.json               # 项目配置\n└── README.md                  # 项目说明\n```\n\n## 🤝 贡献指南\n\n我们欢迎任何形式的贡献！请查看我们的 [贡献指南](CONTRIBUTING.md) 了解更多信息。\n\n## 📄 许可证\n\n本项目采用 [MIT 许可证](LICENSE)。\n\n## 📞 联系我们\n\n- 邮箱：chicogong@tencent.com\n- TRTC-AI文档：[产品文档](https://cloud.tencent.com/document/product/647/110584)\n- 问题反馈：[GitHub Issues](https://github.com/yourusername/trtc-ai-build-quickly/issues)\n- 提交工单：[提交工单](https://cloud.tencent.com/online-service?from=doc_647)\n\n## 🙏\n\n感谢您使用Conversationsal AI Agent !!\n\n\u003cdiv align=\"center\"\u003e\n  \u003csub\u003eBuilt with ❤️ by chico\u003c/sub\u003e\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchicogong%2Fconversational-ai-agent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fchicogong%2Fconversational-ai-agent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchicogong%2Fconversational-ai-agent/lists"}