{"id":50718203,"url":"https://github.com/Haohao-end/openagent","last_synced_at":"2026-06-26T22:00:47.405Z","repository":{"id":300142969,"uuid":"1005290568","full_name":"Haohao-end/openagent","owner":"Haohao-end","description":"AI Agent Development Platform - Supports multiple models (OpenAI/DeepSeek/Wenxin/Tongyi), knowledge base management, workflow automation, and enterprise-grade security. Built with Flask + Vue3 + LangChain, featuring one-click Docker deployment.","archived":false,"fork":false,"pushed_at":"2026-06-22T09:17:12.000Z","size":41279,"stargazers_count":815,"open_issues_count":44,"forks_count":81,"subscribers_count":31,"default_branch":"main","last_synced_at":"2026-06-22T11:12:04.686Z","etag":null,"topics":["agent","ai","celery","deepagents","deepresearch","deepseek","docker","faiss-vector-database","flask","harness-engineering","langchain","langgraph","llmops","mcp","nginx","postgresql","skills","tailwindcss","vue","weaviate"],"latest_commit_sha":null,"homepage":"https://openllm.cloud","language":"Python","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/Haohao-end.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","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":"2025-06-20T02:04:17.000Z","updated_at":"2026-06-22T09:17:17.000Z","dependencies_parsed_at":"2025-10-29T09:14:58.400Z","dependency_job_id":null,"html_url":"https://github.com/Haohao-end/openagent","commit_stats":null,"previous_names":["haohao-end/open-coze","haohao-end/lmforge-end-to-end-llmops-platform-for-multi-model-agents","haohao-end/openagent"],"tags_count":6,"template":false,"template_full_name":null,"purl":"pkg:github/Haohao-end/openagent","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Haohao-end%2Fopenagent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Haohao-end%2Fopenagent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Haohao-end%2Fopenagent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Haohao-end%2Fopenagent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Haohao-end","download_url":"https://codeload.github.com/Haohao-end/openagent/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Haohao-end%2Fopenagent/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34834415,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-26T02:00:06.560Z","response_time":106,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["agent","ai","celery","deepagents","deepresearch","deepseek","docker","faiss-vector-database","flask","harness-engineering","langchain","langgraph","llmops","mcp","nginx","postgresql","skills","tailwindcss","vue","weaviate"],"created_at":"2026-06-09T21:00:25.964Z","updated_at":"2026-06-26T22:00:47.395Z","avatar_url":"https://github.com/Haohao-end.png","language":"Python","funding_links":[],"categories":["*Ops for AI"],"sub_categories":["AI Orchestration \u0026 Deployment"],"readme":"\u003ca id=\"readme-top\"\u003e\u003c/a\u003e\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"https://github.com/user-attachments/assets/15024f52-cb4d-4222-bd8e-b7aa385a6f3e\" alt=\"OpenAgent Logo\" width=\"360\" /\u003e\n\n  \u003cp align=\"center\"\u003e\n    An end-to-end AI agent platform for building, orchestrating, publishing, and operating AI applications.\n    \u003cbr /\u003e\n    Flask + LangChain/LangGraph backend, Vue 3 workspace, visual workflows, datasets, tools, and OpenAPI delivery.\n  \u003c/p\u003e\n\n  \u003cp align=\"center\"\u003e\n    \u003cstrong\u003eSponsored by \u003ca href=\"https://www.atlascloud.ai/?utm_source=github\u0026utm_medium=link\u0026utm_campaign=openagent\"\u003eAtlas Cloud\u003c/a\u003e and \u003ca href=\"https://bloome.im/agent/join/j5CfmWJj?ref=uqIIEORd\"\u003eBloome\u003c/a\u003e\u003c/strong\u003e\n  \u003c/p\u003e\n\n  \u003cp align=\"center\"\u003e\n    \u003ca href=\"https://openllm.cloud\"\u003eVisit Website\u003c/a\u003e\n    ·\n    \u003ca href=\"https://s.apifox.cn/c76bd530-fd50-429c-94cc-f0e41c2675d1/api-305434417\"\u003eAPI Docs\u003c/a\u003e\n    ·\n    \u003ca href=\"README_ZH.md\"\u003e中文文档\u003c/a\u003e\n    ·\n    \u003ca href=\"https://github.com/Haohao-end/openagent\"\u003eGitHub\u003c/a\u003e\n  \u003c/p\u003e\n\n  \u003cp align=\"center\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/python-3.11+-3776AB?logo=python\u0026logoColor=white\" alt=\"Python 3.11+\" /\u003e\n    \u003cimg src=\"https://img.shields.io/badge/flask-3.x-000000?logo=flask\u0026logoColor=white\" alt=\"Flask\" /\u003e\n    \u003cimg src=\"https://img.shields.io/badge/vue-3-4FC08D?logo=vue.js\u0026logoColor=white\" alt=\"Vue 3\" /\u003e\n    \u003cimg src=\"https://img.shields.io/badge/docker-compose-2496ED?logo=docker\u0026logoColor=white\" alt=\"Docker Compose\" /\u003e\n    \u003cimg src=\"https://img.shields.io/badge/weaviate-vector%20db-00C6A7\" alt=\"Weaviate\" /\u003e\n    \u003ca href=\"https://deepwiki.com/Haohao-end/openagent\"\u003e\u003cimg src=\"https://deepwiki.com/badge.svg\" alt=\"Ask DeepWiki\" /\u003e\u003c/a\u003e\n  \u003c/p\u003e\n\u003c/div\u003e\n\n## Table of Contents\n\n- [About The Project](#about-the-project)\n- [Architecture](#architecture)\n- [Built With](#built-with)\n- [Getting Started](#getting-started)\n- [Usage](#usage)\n- [Testing](#testing)\n- [Contact](#contact)\n- [Acknowledgments](#acknowledgments)\n\n## About The Project\n\n\u003cimg width=\"2560\" height=\"1418\" alt=\"OpenAgent Product Overview\" src=\"https://github.com/user-attachments/assets/0f8f7517-1622-46ea-9554-fb13af4841a1\" /\u003e\n\nOpenAgent is a full-stack platform for teams building AI applications rather than a single chat demo. The repository combines a Flask backend, Celery workers, a Vue 3 frontend, visual workflow authoring, dataset and document management, public app and workflow publishing, and OpenAPI-based delivery.\n\nWhat the current codebase already supports:\n\n- Use the home assistant to route user requests to published public agents through A2A, or turn natural-language requirements into new AI app creation flows.\n- Build and manage AI apps from a dedicated workspace with draft, publish, analysis, version comparison, and prompt comparison flows.\n- Enable Deep Research to let the app decompose complex tasks and coordinate bound capabilities across multi-step execution, suitable for scenarios requiring deep reasoning and concrete outputs.\n- Design workflows visually with nodes for LLMs, tool calls, dataset retrieval, code execution, HTTP requests, branching, text processing, template transforms, and structured parameter extraction.\n- Manage datasets, upload documents, inspect segments, and connect retrieval to agents and workflows.\n- Browse public apps, tools, and workflows through store-style views.\n- Expose published apps over REST and SSE through `POST /api/openapi/chat`.\n\n## Architecture\n\n\u003ca href=\"https://github.com/user-attachments/assets/f6bdccf2-a6ff-4924-b68b-ec4d3581796e\"\u003e\n  \u003cimg src=\"https://github.com/user-attachments/assets/f6bdccf2-a6ff-4924-b68b-ec4d3581796e\" alt=\"Basic chatbot architecture\" width=\"100%\" /\u003e\n\u003c/a\u003e\n\nClick the diagram to view the full-resolution architecture image.\n\n### Built With\n\n- AI framework and orchestration: LangChain, LangGraph, workflow orchestration, tool calling, A2A delegation, skills, memory\n- Knowledge and retrieval: RAG, semantic retrieval, full-text retrieval, hybrid retrieval, Weaviate, FAISS\n- Backend: Python, Flask, SQLAlchemy, Celery, Flask-SocketIO, Redis, PostgreSQL\n- Frontend: Vue 3, JavaScript / TypeScript, Vite, TailwindCSS, Pinia, Vue Flow, Arco Design\n- Infrastructure and delivery: Docker Compose, Nginx, OpenAPI, SSE\n- Model integrations: OpenAI, Atlas Cloud, DeepSeek, Grok, Google, Moonshot, Tongyi, Wenxin, Ollama, Zhipu\n\n### Sponsored By\n\n#### Atlas Cloud\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"ui/public/atlas-cloudXopenagent.jpg\" alt=\"Atlas Cloud\" width=\"560\" /\u003e\n\u003c/p\u003e\n\n- Atlas Cloud is a model provider on OpenRouter. Integrate it in this project via `ATLASCLOUD_API_KEY` and `ATLASCLOUD_API_BASE`.\n- Official website: [Atlas Cloud](https://www.atlascloud.ai/?utm_source=github\u0026utm_medium=link\u0026utm_campaign=openagent)\n- Integration docs: [https://www.atlascloud.ai/docs](https://www.atlascloud.ai/docs)\n\n#### Bloome\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://bloome.im/agent/join/j5CfmWJj?ref=uqIIEORd\"\u003e\n    \u003cimg src=\"ui/public/bloome-outreach-tmp.png\" alt=\"Bloome\" width=\"850\" /\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n- Bloome is an AI-agent IM platform where you can interact with AI agents and build collaborative communities. Official website: [Bloome](https://bloome.im/agent/join/j5CfmWJj?ref=uqIIEORd)\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#readme-top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n## Getting Started\n\n### Prerequisites\n\n- Docker 20.10+\n- Docker Compose 2.x\n- 8 GB+ RAM recommended for the full stack\n- Access to at least one supported model provider API key\n\n### Installation\n\n1. Clone the repository.\n\n   ```bash\n   git clone https://github.com/Haohao-end/openagent.git\n   cd openagent\n   ```\n\n2. Create the runtime environment file.\n\n   ```bash\n   cp api/.env.example api/.env\n   ```\n\n3. Review the minimum required settings in `api/.env`.\n\n   - `JWT_SECRET_KEY`\n   - `POSTGRES_PASSWORD`\n   - `REDIS_PASSWORD`\n   - `WEAVIATE_API_KEY`\n   - `VITE_API_PREFIX`\n   - At least one provider key such as `OPENAI_API_KEY`, `ATLASCLOUD_API_KEY`, `DEEPSEEK_API_KEY`, or `DASHSCOPE_API_KEY`\n\n4. Start the Docker stack.\n\n   ```bash\n   cd docker\n   docker compose up -d --build\n   ```\n\n5. Open the local services.\n\n   | Service | URL | Notes |\n   | --- | --- | --- |\n   | Frontend | http://localhost:3000 | Vue 3 web UI |\n   | API | http://localhost:5001 | Flask REST API |\n   | Nginx | http://localhost | Reverse proxy |\n\n### Local Development\n\nBackend:\n\n```bash\ncd api\npip install -r requirements.txt\nflask run --port 5001\n```\n\nFrontend:\n\n```bash\ncd ui\nnpm install\nnpm run serve\n```\n\nVite serves the frontend on port `5173` by default. The frontend configuration resolves the API base from `VITE_API_PREFIX`, and local development commonly proxies `/api` to the Flask backend.\n\nUseful commands:\n\n```bash\ncd api\npytest\n```\n\n```bash\ncd ui\nnpm run type-check\nnpm run lint\nnpm run build\nnpm run test:unit -- --run\n```\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#readme-top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n## Usage\n\n### 1. Home Assistant Experience\n\n\u003cimg width=\"2560\" height=\"1418\" alt=\"OpenAgent Home Assistant\" src=\"https://github.com/user-attachments/assets/7ebb7827-838b-4bd2-b522-9f544f32416a\" /\u003e\n\nUse the home page as the default assistant entry point to route user questions to the most relevant published public agents through A2A, or describe a new idea in natural language and trigger AI app creation. The same surface also supports multi-turn chat, suggested prompts, image upload, and audio input.\n\n### 2. App Workspace and Deep Research\n\n\u003cimg width=\"1920\" height=\"1080\" alt=\"OpenAgent App Workspace Deep Research\" src=\"https://github.com/user-attachments/assets/2dd4dc3e-f216-4c8d-96e4-7a2f81e138ae\" /\u003e\n\nThe app workspace is the main work area for an AI app, not a standalone settings page. The left side handles model, prompt, and capability bindings. The right side is used for live debugging, execution traces, and result checks. In the current codebase, the README term `Deep Research` maps to the deep thinking mode behind `enable_deep_thinking`.\n\nKey capabilities:\n\n- Configuration and version management: manage model changes, prompt logic, drafts, publishing, version comparison, prompt comparison, and app duplication in one place.\n- Capability integration: bind plugins, MCP, Skills, child Agent apps, workflows, and datasets through a single workspace.\n- Complex task execution: with `Deep Research` enabled, the app can break work into steps and coordinate bound capabilities across a longer execution chain.\n- Sandbox and artifact output: support script execution, code handling, file generation, and attachment export for tasks that need concrete outputs.\n- Debugging and result verification: use the right-side panel to run real conversations and inspect deep execution timelines, task state, produced artifacts, and final results.\n\n### 3. Visual Workflow Editor\n\n\u003cimg width=\"2560\" height=\"1599\" alt=\"OpenAgent Workflow Editor\" src=\"https://github.com/user-attachments/assets/23b510e2-1232-4f52-9262-812a7523ae21\" /\u003e\n\nAuthor workflows with nodes such as LLM, tool, dataset retrieval, code, HTTP request, template transform, text processor, variable assigner, parameter extractor, if/else, start, and end.\n\n### 4. Dataset and Retrieval\n\n\u003cimg width=\"2560\" height=\"1418\" alt=\"OpenAgent Dataset Management\" src=\"https://github.com/user-attachments/assets/6f000681-db56-461a-bac9-a2dd5d6cd009\" /\u003e\n\nCreate datasets, upload documents, inspect segments, and wire retrieval nodes into workflows or AI apps for knowledge-enabled behavior.\n\n### 5. OpenAPI Delivery\n\n\u003cimg width=\"2560\" height=\"1418\" alt=\"OpenAgent OpenAPI\" src=\"https://github.com/user-attachments/assets/40769d35-89e1-4b76-9686-a431a77a42c7\" /\u003e\n\nPublish an app and call it over `POST /api/openapi/chat` with standard or streaming responses, including support for multi-turn conversation identifiers.\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#readme-top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n## Testing\n\nThe repository already includes automated backend and frontend tests.\n\n- Backend: `cd api \u0026\u0026 pytest`\n- Frontend unit tests: `cd ui \u0026\u0026 npm run test:unit -- --run`\n- Frontend type check: `cd ui \u0026\u0026 npm run type-check`\n- Frontend build validation: `cd ui \u0026\u0026 npm run build`\n\n## Contact\n\n- Project Link: https://github.com/Haohao-end/openagent\n- Website: https://openllm.cloud\n- API Docs: https://s.apifox.cn/c76bd530-fd50-429c-94cc-f0e41c2675d1/api-305434417\n- DeepWiki: https://deepwiki.com/Haohao-end/openagent\n\n## Acknowledgments\n\n- Thanks to Atlas Cloud and Bloome for supporting OpenAgent.\n- Special thanks to Rui Yang and Haoyu Wang (Johns Hopkins University) for responsibly reporting a Host Header poisoning issue in the built-in tool icon URL construction and helping improve the security of this project.\n- Special thanks to Ryan B for responsibly reporting an SSRF vulnerability in the custom API-tool server URL and helping improve the project's outbound request security.\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#readme-top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FHaohao-end%2Fopenagent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FHaohao-end%2Fopenagent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FHaohao-end%2Fopenagent/lists"}