UnicomAI/wanwu

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.

What it solves

Wanwu is an all-in-one agent development platform designed for enterprise scenarios. It aims to bridge the gap between building AI and deploying it in the field by providing a full-stack toolchain for Forward Deployed Engineers (FDEs), reducing the barrier to AI project delivery and ensuring secure, compliant, and efficient AI solutions for businesses.

How it works

The platform integrates five core agent capabilities:

  • RAG/Knowledge Base Agent: Manages massive enterprise documents using high-precision parsing (supporting 12 file formats), multimodal retrieval, and GraphRAG for improved reasoning and cross-document summarization.
  • Ontology Agent: Constructs business knowledge networks from enterprise data to enable deep reasoning and decision-making based on structured business data.
  • Workflow Agent: Uses a low-code drag-and-drop canvas to standardize AI execution paths for complex processes like contract review or expense approval.
  • GUI Agent: Allows AI to operate application interfaces directly via vision and click capabilities, bypassing the need for APIs in legacy systems.
  • General Agent + Skill Development: Combines a general reasoning brain with vertical-scene skills that can be created using natural language ("one-sentence Skill creation").

Who it’s for

It is primarily designed for Forward Deployed Engineers (FDEs) and enterprises in industries such as finance, industry, and government who need to deploy professional, secure, and commercially friendly AI agents.

Highlights

  • Full-Stack Toolchain: Covers everything from knowledge management to UI-level interaction and API integration.
  • GraphRAG & Ontology: Advanced reasoning capabilities that go beyond simple text retrieval to understand structured business logic.
  • ** keluarga Commercial-Friendly**: Apache-2.0 licensed for free extension and commercial use.
  • Xinchuang Compliance: Certified for specific Chinese hardware and software ecosystems (e.g., Kunpeng CPUs, Euler, Kylin).
  • Deployment Flexibility: Offers three paths: an out-of-the-box platform, RESTful API integration (BaaS), or a dedicated client (UniClaw) for high-privilege local operations.

Related

  • Project
    junkai-li/NetCoreKevin

    An enterprise-grade AI agent SaaS framework built on .NET 9 that integrates RAG, multi-agent collaboration, and multi-tenant architecture for building AI middle-platforms.

  • Project
    fim-ai/fim-one

    FIM One is an all-in-one agent platform that integrates global SaaS applications with Chinese enterprise stacks to automate complex workflows across disparate systems.

  • Dispatch
    Qwen3.7-Max: Pushing the Boundaries of Long-Horizon Autonomous Agents

    Alibaba's new Qwen3.7-Max model targets the 'agent era' with specialized capabilities in long-horizon reasoning, GPU kernel optimization, and cross-framework generalization.

  • Dispatch
    Qwen3.7-Max agent model release

    Qwen released Qwen3.7-Max, a new agent-focused foundation model that excels at coding, office automation, and ultra-long-horizon autonomous tasks, now available via Alibaba Cloud Model Studio.

  • Project
    Pinvou/pinvou-agent

    Pinvou Agent is a cross‑platform desktop AI‑assistant that lets you work, design, or code with LLMs. It combines chat with file attachments, a local knowledge base, persona cards, and a plug‑in tool store, producing editable artifacts (Markdown, designs, code) that persist across sessions. Built with React + Vite UI on Tauri 2, it uses the CodeWhale engine for model calls, MCP tool execution and Skills. Supports local vLLM or any OpenAI‑compatible endpoint, runs on Windows/macOS/Linux, and is MIT‑licensed.