{"data":{"slug":"labring-fastgpt","name":"FastGPT","tagline":"A knowledge-based platform for developing and deploying complex question-answering systems","github_url":"https://github.com/labring/FastGPT","owner":"labring","repo":"FastGPT","owner_avatar_url":"https://avatars.githubusercontent.com/u/102226726?v=4","primary_language":"TypeScript","stars":29690,"forks":7320,"topics":["agent","claude","deepseek","llm","mcp","nextjs","openai","qwen","rag","workflow"],"archived":false,"github_pushed_at":"2026-09-18T08:34:57+00:00","maintenance_label":"Very active","stars_delta_30d":324,"url":"https://www.graphcanon.com/tools/labring-fastgpt","markdown_url":"https://www.graphcanon.com/tools/labring-fastgpt.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/labring-fastgpt","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=labring-fastgpt","description":"FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.","homepage_url":"https://fastgpt.io","license":"Other","open_issues":170,"watchers":153,"ai_summary":"FastGPT is a comprehensive AI Agent building platform that offers out-of-the-box capabilities for data processing, RAG retrieval, and visual AI workflow orchestration, enabling users to easily develop and deploy complex question-answering systems.","readme_excerpt":"
\n\n\"fastgpt\n\n# FastGPT\n\n

\n English |\n 简体中文 |\n Bahasa Indonesia |\n ไทย |\n Tiếng Việt |\n 日本語\n

\n\nFastGPT 是一个 AI Agent 构建平台，提供开箱即用的数据处理、模型调用等能力，同时可以通过 Flow 可视化进行工作流编排，从而实现复杂的应用场景。\n\n
\n\n

\n \n \"cloud\"\n \n \n \"document\"\n \n \n \"development\"\n \n \n \"project\"\n \n

\n\nhttps://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409bd33f6d4\n\n## 快速开始\n\n可以通过 Docker 快速启动 FastGPT，在终端输入以下命令，根据引导完成输入即可拉取配置。\n\n```bash\n# 输入命令拉取配置文件\nbash <(curl -fsSL https://doc.fastgpt.io/deploy/install.sh)\n# 启动\ndocker compose up -d\n```\n\n完全启动后，可通过 `http://localhost:3000` 访问 FastGPT，默认账号为 `root`，密码为 `1234`。\n\n如果你遇到问题，可以[查看完整 Docker 部署教程](https://doc.fastgpt.io/self-host/deploy/docker)\n\n## 🛸 使用方式\n\n- **云服务版本** \n 如果你不需要私有化部署，可以直接使用我们提供的云服务版本，地址为：[fastgpt.io](https://fastgpt.io/?source=github&utm_source=github&utm_medium=referral&utm_campaign=github_home&utm_content=cloud_service_link)\n\n- **社区自托管版本** \n 可以使用[Docker](https://doc.fastgpt.io/self-host/deploy/docker)快速部署，也可以使用[Sealos Cloud](https://doc.fastgpt.io/self-host/deploy/sealos) 来一键部署FastGPT。\n\n- **商业版** \n 如果你需要更完整的功能，或深度的服务支持，可以选择我们的[商业版](https://doc.fastgpt.io/guide/version/commercial)。我们除了提供完整的软件外，还提供相应的场景落地辅导，具体可提交[商业咨询](https://fastgpt.cn/zh/contact?source=github&utm_source=github&utm_medium=referral&utm_campaign=github_home&utm_content=commercial_consultation)\n\n## 💡 核心功能\n\n| | |\n| ---------------------------------- | ---------------------------------- |\n| | |\n| | |\n\n`1` 应用编排能力\n - [x] Agent Skill 编排\n - [x] 对话工作流、插件工作流，包含基础的 RPA 节点\n - [x] 用户交互\n - [x] 双向 MCP\n - [ ] 辅助生成工作流\n\n`2` 应用调试能力\n - [x] 知识库单点搜索测试\n - [x] 对话时反馈引用并可修改与删除\n - [x] 完整调用链路日志\n - [x] 应用评测\n - [ ] 高级编排 DeBug 调试模式\n - [ ] 应用节点日志\n\n`3` 知识库能力\n - [x] 多库复用，混用\n - [x] chunk 记录修改和删除\n - [x] 支持手动输入，直接分段，QA 拆分导入\n - [x] 支持 TXT，MD，HTML，PDF，Docx，PPTX，CSV，XLSX (有需要更多 File Loader 可 PR )，支持 URL 读取、CSV 批量导入\n - [x] 混合检索 & 重排\n - [x] API 知识库\n\n`4` 插件能力\n - [x] 系统工具热更新\n - [ ] RAG 模块热更新\n - [ ] Agent-loop 热更新\n - [ ] AI 实时生成插件\n\n`5` 运营能力\n - [x] 免登录分享窗口\n - [x] iframe 一键嵌入\n - [x] 统一查阅对话记录，并对数据进行标注\n - [x] 应用运营日志\n\n\n \"#\"\n\n\n## 💪 我们的项目 & 链接\n\n- [快速开始本地开发](https://doc.fastgpt.io/self-host/dev/)\n- [OpenAPI 文档](https://cloud.fastgpt.io/apidoc/systemopenapi)\n- [FastGPT-plugin](https://github.com/labring/fastgpt-plugin)\n- [AI Proxy: 模型聚合负载均衡服务](https://github.com/labring/aiproxy)\n- [Sealos：快速部署集群应用](https://github.com/labring/sealos)\n\n\n \"#\"\n\n\n## 🌿 第三方生态\n\n- [AI Proxy：大模型聚合服务](https://sealos.run/aiproxy/?k=fastgpt-github/)\n- [SiliconCloud (硅基流动) —— 开源模型在线体验平台](https://cloud.siliconflow.cn/i/TR9Ym0c4)\n\n","github_created_at":"2023-02-23T16:53:25+00:00","created_at":"2026-07-07T17:32:16.2707+00:00","updated_at":"2026-09-20T04:32:59.9143+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"agent","name":"agent"},{"slug":"claude","name":"claude"},{"slug":"deepseek","name":"deepseek"},{"slug":"llm","name":"llm"},{"slug":"mcp","name":"mcp"},{"slug":"nextjs","name":"nextjs"},{"slug":"openai","name":"openai"},{"slug":"qwen","name":"qwen"}],"trust":{"provenance":{"is_fork":false,"github_id":605673387,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:44:14.972Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":25,"days_since_push":0,"last_release_at":"2026-09-11T10:11:32Z","stars_delta_30d":324,"open_issues_delta_30d":5},"security_summary":{"status":"no_manifest","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-09-18T08:44:16.686Z","medium_count":0,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-18T08:44:13.812Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:44:13.812Z"},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-09-18T08:44:13.812Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-09-18T08:44:13.812Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need a comprehensive platform that supports data processing, RAG retrieval, and visual AI workflow orchestration for developing complex question-answering systems.","If you prefer a platform that allows for easy deployment without extensive setup or configuration.","When you require a solution that supports multiple knowledge bases and flexible data import formats, including TXT, MD, HTML, PDF, Docx, PPTX, CSV, XLSX, and URL reading."],"when_not_to_use":["If you are looking for a platform that supports real-time AI plugin generation, as this feature is not yet available in FastGPT.","When you need a platform that supports RAG module hot updates or Agent-loop hot updates, as these features are currently under development.","If you require advanced debugging modes for complex workflows, as this feature is not yet implemented in FastGPT."],"source":"enrich:decision_facts","observed_at":"2026-09-18T09:15:18.438Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"FastGPT is a knowledge-based platform for developing and deploying complex question-answering systems, offering out-of-the-box capabilities for data processing, RAG retrieval, and visual AI workflow orchestration."}]}}