{"id":47298264,"url":"https://github.com/tgoai/tgo","last_synced_at":"2026-03-31T01:00:49.692Z","repository":{"id":325212053,"uuid":"1098866858","full_name":"tgoai/tgo","owner":"tgoai","description":"Open-source AI Agent Customer Service Platform. Build AI agent teams with LLM orchestration, RAG knowledge base, multi-channel support, and human collaboration.","archived":false,"fork":false,"pushed_at":"2026-03-11T13:13:41.000Z","size":47406,"stargazers_count":400,"open_issues_count":15,"forks_count":79,"subscribers_count":3,"default_branch":"main","last_synced_at":"2026-03-11T15:57:59.761Z","etag":null,"topics":["ai-agent","artificial-intelligence","chatbot","customer-service","customer-support","llm","rag"],"latest_commit_sha":null,"homepage":"https://tgo.ai","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tgoai.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":"AGENTS.md","dco":null,"cla":null}},"created_at":"2025-11-18T08:47:29.000Z","updated_at":"2026-03-11T13:13:46.000Z","dependencies_parsed_at":null,"dependency_job_id":"87e2b96b-d834-4e04-ac72-8ecf30a38238","html_url":"https://github.com/tgoai/tgo","commit_stats":null,"previous_names":["tgoai/tgo"],"tags_count":30,"template":false,"template_full_name":null,"purl":"pkg:github/tgoai/tgo","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tgoai%2Ftgo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tgoai%2Ftgo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tgoai%2Ftgo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tgoai%2Ftgo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tgoai","download_url":"https://codeload.github.com/tgoai/tgo/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tgoai%2Ftgo/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31216658,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-30T15:24:02.938Z","status":"ssl_error","status_checked_at":"2026-03-30T15:23:44.804Z","response_time":138,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: 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":["ai-agent","artificial-intelligence","chatbot","customer-service","customer-support","llm","rag"],"created_at":"2026-03-16T20:00:36.052Z","updated_at":"2026-03-31T01:00:49.685Z","avatar_url":"https://github.com/tgoai.png","language":"Python","funding_links":[],"categories":["TypeScript"],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"resources/readme-banner-en.svg\" width=\"100%\" alt=\"Build AI Agent Teams for Customer Service\"\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"./README.md\"\u003eEnglish\u003c/a\u003e | \u003ca href=\"./README_CN.md\"\u003e简体中文\u003c/a\u003e | \u003ca href=\"./README_TC.md\"\u003e繁體中文\u003c/a\u003e | \u003ca href=\"./README_JP.md\"\u003e日本語\u003c/a\u003e | \u003ca href=\"./README_RU.md\"\u003eРусский\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://tgo.ai\"\u003eWebsite\u003c/a\u003e | \u003ca href=\"https://tgo.ai\"\u003eDocumentation\u003c/a\u003e\n\u003c/p\u003e\n\n## TGO Introduction\n\nTGO is an open-source AI agent customer service platform dedicated to helping enterprises \"Build AI Agent Teams for Customer Service\". It integrates multi-channel access, agent orchestration, knowledge base management (RAG), and human agent collaboration.\n\n\u003cimg src=\"resources/home_en.png\" width=\"100%\"\u003e\n\n## 🚀 Quick Start\n\n### One-Click Deployment\n\nRun the following command on your server to check requirements, clone the repository, and start the services:\n\n```bash\nREF=latest curl -fsSL https://raw.githubusercontent.com/tgoai/tgo/main/bootstrap.sh | bash\n```\n\n\u003e **For users in China** (using Gitee and Aliyun mirrors):\n\u003e ```bash\n\u003e REF=latest curl -fsSL https://gitee.com/tgoai/tgo/raw/main/bootstrap_cn.sh | bash\n\u003e ```\n\n---\n\nFor more details, please visit the [Documentation](https://tgo.ai).\n\n## ✨ Features\n\n### 🤖 AI Agent Orchestration\n- **Multi-Agent Support** - Configure multiple AI agents for different business scenarios\n- **Multi-Model Integration** - Connect with various LLM providers (OpenAI, Anthropic, etc.)\n- **Streaming Response** - Real-time AI responses via SSE for smooth conversation experience\n- **Context Memory** - Maintain conversation history for coherent dialogue\n\n### 📚 Knowledge Base (RAG)\n- **Document Knowledge Base** - Upload documents to enhance AI response accuracy\n- **Q\u0026A Knowledge Base** - Create question-answer pairs for quick knowledge expansion\n- **Website Knowledge Base** - Crawl website content to keep information up-to-date\n- **Smart Retrieval** - Vector-based semantic search for precise answers\n\n### 🔧 MCP Tools Integration\n- **Tool Store** - Rich library of MCP tools, enable on demand\n- **Custom Tools** - Project-level tool configuration and management\n- **OpenAPI Schema** - Auto-parse schemas to generate interactive forms\n\n### 🌐 Multi-Channel Access\n- **Web Widget** - Embeddable chat widget for websites\n- **WeChat Integration** - Official Account and Mini Program support\n- **Unified Management** - Manage all channels from a single dashboard\n\n### 💬 Real-time Communication\n- **WuKongIM Integration** - Stable and reliable instant messaging\n- **WebSocket Connection** - Efficient bidirectional communication\n- **Message Sync** - Read/unread status, delivery confirmation\n- **Rich Media** - Support for text, images, files and more\n\n### 👥 Human-AI Collaboration\n- **Smart Handoff** - Seamlessly transfer to human agents when needed\n- **Visitor Management** - Collect visitor info, assign sessions, track history\n- **Agent Workspace** - Unified interface for human agents\n\n### 🎨 UI Widget System\n- **Structured Display** - Render orders, products, logistics as beautiful cards\n- **Rich Components** - Order cards, logistics tracking, product display, price comparison\n- **Action Protocol** - Standardized URI protocol for interactions\n\n## 📦 Repository Structure\n\n| Repository | Description | Tech Stack |\n|:---|:---|:---|\n| [tgo-ai](repos/tgo-ai) | AI/ML operations service for managing agents, tool bindings, knowledge bases, and usage analytics | Python / FastAPI |\n| [tgo-api](repos/tgo-api) | Core business logic service handling user management, visitor tracking, assignment, and communication | Python / FastAPI |\n| [tgo-cli](repos/tgo-cli) | CLI tool \u0026 MCP Server enabling AI agents to execute customer service operations with 40+ built-in tools | TypeScript / Node.js |\n| [tgo-device-agent](repos/tgo-device-agent) | Embedded agent running on managed devices providing file and shell capabilities via TCP JSON-RPC | Go |\n| [tgo-device-control](repos/tgo-device-control) | Device control service managing TCP/JSON-RPC connections for remote device management with MCP Agent | Python / FastAPI |\n| [tgo-platform](repos/tgo-platform) | Multi-channel message intake service supporting WeChat, Feishu, DingTalk, Telegram, Slack, email, etc. | Python / FastAPI |\n| [tgo-plugin-runtime](repos/tgo-plugin-runtime) | Plugin lifecycle management and execution service with dynamic tool synchronization | Python / FastAPI |\n| [tgo-rag](repos/tgo-rag) | RAG service providing document processing, hybrid semantic/full-text search, and async processing | Python / FastAPI |\n| [tgo-web](repos/tgo-web) | Admin frontend with real-time chat, AI agent management, knowledge base, and MCP tool integration | TypeScript / React 19 |\n| [tgo-workflow](repos/tgo-workflow) | AI Agent workflow execution engine supporting DAG topology with LLM, API, condition, and tool nodes | Python / FastAPI |\n\n### Widget SDKs\n\n| Repository | Description | Tech Stack |\n|:---|:---|:---|\n| [tgo-widget-js](repos/tgo-widget-js) | Embeddable customer service chat widget (Intercom-style) for websites | TypeScript / React 18 |\n| [tgo-widget-ios](repos/tgo-widget-ios) | Native iOS customer service chat SDK with SwiftUI views and UIKit bridging | Swift / SwiftUI |\n| [tgo-widget-flutter](repos/tgo-widget-flutter) | Cross-platform customer service chat widget for iOS and Android | Dart / Flutter |\n| [tgo-widget-cli](repos/tgo-widget-cli) | Visitor-facing CLI tool \u0026 MCP Server providing customer service interface | TypeScript / Node.js |\n| [tgo-widget-miniprogram](repos/tgo-widget-miniprogram) | WeChat Mini Program chat widget component with AI streaming responses and Markdown rendering | TypeScript |\n\n## 🏗️ System Architecture\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"resources/architecture_en.svg\" width=\"100%\" alt=\"TGO System Architecture\"\u003e\n\u003c/p\u003e\n\n## Product Preview\n\n| | |\n|:---:|:---:|\n| **Dashboard** \u003cbr\u003e \u003cimg src=\"resources/screenshot/en/home_dark.png\" width=\"100%\"\u003e | **Agent Orchestration** \u003cbr\u003e \u003cimg src=\"resources/screenshot/en/agent_dark.png\" width=\"100%\"\u003e |\n| **Knowledge Base** \u003cbr\u003e \u003cimg src=\"resources/screenshot/en/knowledge_dark.png\" width=\"100%\"\u003e | **Q\u0026A Debugging** \u003cbr\u003e \u003cimg src=\"resources/screenshot/en/knowledge_qa_dark.png\" width=\"100%\"\u003e |\n| **MCP Tools** \u003cbr\u003e \u003cimg src=\"resources/screenshot/en/mcp_dark.png\" width=\"100%\"\u003e | **Platform Admin** \u003cbr\u003e \u003cimg src=\"resources/screenshot/en/platform_dark.png\" width=\"100%\"\u003e |\n\n## System Requirements\n- **CPU**: \u003e= 4 Core\n- **RAM**: \u003e= 8 GiB\n- **OS**: macOS / Linux / WSL2\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftgoai%2Ftgo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftgoai%2Ftgo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftgoai%2Ftgo/lists"}