{"data":{"slug":"unicomai-wanwu","name":"wanwu","tagline":"Enterprise-grade multi-tenant AI agent development platform","github_url":"https://github.com/UnicomAI/wanwu","owner":"UnicomAI","repo":"wanwu","owner_avatar_url":"https://avatars.githubusercontent.com/u/167508496?v=4","primary_language":"Go","stars":2472,"forks":141,"topics":["agent","agentic-ai","agentic-framework","ai","ai-agent","ai-agent-development-framework","ai-agents-framework","development","genai","golang","llm","mcp","open-ai","rag","wanwu","workflow"],"archived":false,"github_pushed_at":"2026-09-04T11:12:23+00:00","maintenance_label":"Active","stars_delta_30d":-120,"url":"https://www.graphcanon.com/tools/unicomai-wanwu","markdown_url":"https://www.graphcanon.com/tools/unicomai-wanwu.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/unicomai-wanwu","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=unicomai-wanwu","description":"China Unicom's Yuanjing Wanwu Agent Platform is an enterprise-grade, multi-tenant AI agent development platform. It helps users build applications such as intelligent agents, workflows, and rag, and also supports model management. The platform features a developer-friendly license, and we welcome all developers to build upon the platform.","homepage_url":null,"license":"Apache-2.0","open_issues":41,"watchers":31,"ai_summary":"China Unicom's Yuanjing Wanwu Agent Platform allows developers to build applications such as intelligent agents and workflows with various deployment methods without needing extensive coding knowledge.","readme_excerpt":"### 🚀 3 Deployment Methods: Reach Business On‑Site\n\nAfter capability building, Wanwu provides 3 deployment paths to minimize FDE delivery difficulty:\n\n#### 📦 Method 1: Out‑of‑the‑Box Platform\n\nUse directly via visual interface; no coding required for creating agents, workflows, and Q&A. Zero‑threshold AI productivity for rapid on‑site validation and delivery.\n\n#### 🔗 Method 2: API Seamless Integration\n\nRESTful API (BaaS) for embedding into OA, CRM, ERP, etc. Fine‑grained permission control enables deep AI integration without changing user habits.\n\n#### 🖥️Method 3: Skill + UniClaw Dedicated Client\n\nFor high‑privilege scenarios (local PC control, DingTalk messages, etc.). FDEs develop Skills and execute via UniClaw to handle cross‑system high‑privilege on‑site operations.\n\nUniClaw download: https://maas.ai-yuanjing.com/app/uniclaw/uniclaw-official.html\n\n------\n\n---\n\n### 🛠️ Infrastructure & Ecosystem\n\n- 🔥 **Apache‑2.0 License**: Free extension, secondary development, and commercial use.\n- ✔ **Model Hub**: Unified access to hundreds of proprietary/open‑source models; deep OpenAI API compatibility and Yuanjing ecosystem support; multiple inference backends.\n- ✔ **Skill Plaza**: 100+ built‑in industry Skills ready to use; no adapters needed for external capabilities.\n- ✔ **Web Search**: Real‑time information, multi‑source integration, intelligent retrieval strategies.\n- ✔ **Multi‑tenant architecture**: Isolated accounts for cost control, data security, and elastic scaling.\n- **✔ Xinchuang compliance**: Certified *Xinchuang AI Software/Hardware System Inspection Certificate*. Supports Kunpeng CPUs, Euler, Kylin, CULinux, TiDB, OceanBase, etc.\n\n------\n\n---\n\n### 🚀 Quick Start\n\n- The workflow module of the Wanwu AI Agent Platform uses the following project, you can go to its warehouse to view the details.\n  - v0.1.8 and earlier: wanwu-agentscope project\n  - v0.2.0 and later: [wanwu-workflow](https://github.com/UnicomAI/wanwu-workflow/tree/dev/wanwu-backend) project\n\n- **Recommended Configuration:**\n  - CPU: 8-core or 16-core; RAM: 32GB; Storage: 200GB or more; GPU: Not required.\n\n- **Model Requirements:**\n  - When using WanwuBot (General Agent) or creating Skills with a single command, the selected model must have a context length >= 32000 when importing.\n\n- **Security Statement:**\n  - All middleware components (MySQL, Redis, MinIO, Kafka, Elasticsearch, etc.) support custom passwords configured in the `.env` file.\n  - For front-end and back-end user password transmission, RSA asymmetric encryption is used to encrypt passwords. The key pair is automatically generated on first service startup; custom key pairs can also be configured via `WANWU_BFF_LOGIN_RSA_PATH` in `.env`.\n  - It is strongly recommended to change all default passwords and keep them secure before deploying in a production environment to avoid security risks associated with default credentials.\n\n- **Docker Installation (Recommended)**\n\n1. Before the first run\n\n    1.1 Copy the environment variable file\n    ```bash\n    cp .env.example .env\n    ```\n\n    1.2 Modify the `WANWU_ARCH` and `WANWU_EXTERNAL_IP` variables in the .env file according to the system\n    ```\n    # amd64 / arm64\n    WANWU_ARCH=amd64\n    \n    # external ip port (Note: if the browser accesses Wanwu deployed on a non-localhost server, you need to change localhost to the external IP, for example, 192.168.xx.xx)\n    WANWU_EXTERNAL_IP=localhost\n    ```\n\n    1.3 Configure the `WANWU_BFF_JWT_SIGNING_KEY` variable in the .env file, a custom complex random string used for generating JWT tokens\n    ```\n    # bff\n    WANWU_BFF_JWT_SIGNING_KEY=\n    ```\n\n    1.4 Copy environment variable file (Ontology Agent)\n    ```bash\n    cp .env.ontology.example .env.ontology\n    ```\n\n    1.5 (Optional) Generate custom RSA keys before the first run (Ontology Agent)\n    > Skip this step to use the default keys baked into the images. To use independent keys in production, generate them as follows.\n\n    - 1.5.1 Generate RSA ke","github_created_at":"2025-06-06T02:45:28+00:00","created_at":"2026-07-15T10:48:36.22359+00:00","updated_at":"2026-09-20T04:27:33.426409+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"}],"tags":[{"slug":"agent","name":"agent"},{"slug":"agentic-ai","name":"agentic-ai"},{"slug":"development","name":"development"},{"slug":"genai","name":"genai"},{"slug":"golang","name":"golang"},{"slug":"llm","name":"llm"},{"slug":"workflow","name":"workflow"}],"trust":{"provenance":{"is_fork":false,"github_id":997136302,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-16T06:00:48.205Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":7,"days_since_push":11,"last_release_at":"2026-09-04T11:12:23Z","stars_delta_30d":-120,"open_issues_delta_30d":5},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":23,"high_count":0,"last_scan_at":"2026-07-15T10:48:37.646Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-16T06:00:48.655Z"},"languages":{"value":["go"],"source":"github.language","observed_at":"2026-09-16T06:00:48.655Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-16T06:00:48.655Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need rapid on-site validation via a zero-threshold visual interface for creating agents.","For seamless API integration into existing CRM or ERP systems to enhance them with AI capabilities.","If your project requires handling high-privilege scenarios, such as system control tasks on local PCs."],"when_not_to_use":["Avoid if your team prefers coding over a visual interface for application development.","Not suitable if you seek tools that do not support Xinchuang compliance and ecosystem integration.","Skip if your project does not require or benefit from multiple deployment methods or a multi-tenant architecture."],"source":"enrich:decision_facts","observed_at":"2026-07-16T21:21:24.415Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Wanwu is an enterprise-grade AI agent development platform from China Unicom that supports visual interface creation, API integration, and privilege-rich local operations."},{"label":"License detail","value":"Apache-2.0 allows free extension, secondary development, and commercial use with full source code access under permissive terms."}]}}