wanwu

Yuanjing Wanwu Agent Platform is an all-in-one, commercial-friendly licensed agent development platform designed for enterprise scenarios. Guided by the core philosophy of open technology and co-construction of ecosystem, we are committed to providing enterprises with secure, efficient, and compliant AI solutions.

Wanwu aims to deliver all tooling capabilities required by Forward Deployed Engineer (FDEs), forming a full‑stack FDE toolchain. It covers core enterprise assets, centers on customers, deeply integrates capabilities into customer systems, drastically lowers the barrier to AI project delivery, and bridges the final mile from build to field. It simplifies every business decision and empowers every FDE.

🌟 Full‑Stack FDE Toolchain: 5 Core Capabilities

To address complex enterprise scenarios, Wanwu provides 5 core agent capabilities to solve delivery pain points, making AI not only thinkable but also doable.

1️⃣ RAG/Knowledge Base Agent

Solves scattered documents and gives AI reliable memory. Provides end‑to‑end knowledge management for massive enterprise documents and policies, building a high‑precision, memory‑enabled knowledge brain to prevent AI hallucinations.

• High‑precision parsing & retrieval: Supports 12 file formats and URL crawling; OCR and MinerU model private deployment; multimodal retrieval, cascaded/adaptive chunking, intelligent ranking, illustrated generation, and source citation.
• GraphRAG enhancement: Built‑in UniAI‑GraphRAG with domain ontology modeling, greatly improving completeness and logic in cross‑document summarization and multi‑hop reasoning, with industry‑leading F1 score.
• External knowledge base compatibility: Supports API import of knowledge bases created in Dify for retrieval in agents, chat, and workflows.

2️⃣ Ontology Agent

Handles structured data and enables multi‑step reasoning and decision‑making. Breaks the limitation that LLMs only understand text, adapting to complex structured business data.

• Deep reasoning & decision‑making: Automatically builds business knowledge networks from enterprise data and documents, empowering AI with deep reasoning and closed‑loop action. It elevates LLMs from knowledge Q&A to business analysis brains.

3️⃣ Workflow Agent

Manages complex processes and ensures AI follows business rules.

For contract review, expense approval, and other complex workflows, standardizes AI execution paths via low‑code for stable delivery.

• Visual orchestration: Low‑code drag‑and‑drop canvas with built‑in conditional branches, APIs, LLMs, knowledge bases, code, MCP, etc. Supports end‑to‑end debugging and performance analysis.
• Zero‑code orchestration closed‑loop: Industry‑first zero‑code Skill invocation in agent development, closing the loop from intent recognition to skill execution. Flexibly calls built‑in tools, MCP, workflows, etc., parses hundreds of pages in seconds, and displays results in a unified workspace.

4️⃣ GUI Agent (Download Client)

Operates various applications without APIs. Eliminates integration barriers for legacy or non‑API systems by giving AI vision and click capabilities.

• UI‑level interaction: AI directly operates application interfaces without underlying API integration.
• Sandbox support: Isolated Docker containers for each bot to safely execute UI operations.

5️⃣ General Agent + Skill Development

Unifies all capabilities with natural language. Industry‑first dual engine of General Agent + Vertical‑scene Skills, building a super agent that is both knowledgeable and professional for complex interactive needs.

• All‑around brain & minimal construction: Professional analyst‑level multi‑step reasoning; one‑sentence Skill creation turns business experience into a dedicated toolbox via natural language; one‑click conversion of platform apps to Skills.

🚀 3 Deployment Methods: Reach Business On‑Site

After capability building, Wanwu provides 3 deployment paths to minimize FDE delivery difficulty:

📦 Method 1: Out‑of‑the‑Box Platform

Use 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.

🔗 Method 2: API Seamless Integration

RESTful API (BaaS) for embedding into OA, CRM, ERP, etc. Fine‑grained permission control enables deep AI integration without changing user habits.

🖥️Method 3: Skill + UniClaw Dedicated Client

For 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.

UniClaw download: https://maas.ai-yuanjing.com/app/uniclaw/uniclaw-official.html

🛠️ Infrastructure & Ecosystem

• 🔥 Apache‑2.0 License: Free extension, secondary development, and commercial use.
• ✔ Model Hub: Unified access to hundreds of proprietary/open‑source models; deep OpenAI API compatibility and Yuanjing ecosystem support; multiple inference backends.
• ✔ Skill Plaza: 100+ built‑in industry Skills ready to use; no adapters needed for external capabilities.
• ✔ Web Search: Real‑time information, multi‑source integration, intelligent retrieval strategies.
• ✔ Multi‑tenant architecture: Isolated accounts for cost control, data security, and elastic scaling.
• ✔ Xinchuang compliance: Certified Xinchuang AI Software/Hardware System Inspection Certificate. Supports Kunpeng CPUs, Euler, Kylin, CULinux, TiDB, OceanBase, etc.

🚩 Core Function Modules

1. Model Management (Model Hub)

▸ Supports the unified access and lifecycle management of hundreds of proprietary/open-source large models (including GPT, Claude, Llama, etc.)

▸ Deeply adapts to OpenAI API standards and Unicom Yuanjing ecological models, realizing seamless switching of heterogeneous models

▸ Provides multi-inference backend support (vLLM, TGI, etc.) and self-hosted solutions to meet the computing power needs of enterprises of different scales

2. MCP

▸ Standardized interfaces: Enable AI models to seamlessly connect to various external tools (such as GitHub, Slack, databases, etc.) without the need to develop adapters for each data source separately

▸ Built-in rich and selected recommendations: Integrates 100+ industry MCP interfaces, making it easy for users to call up quickly and easily

3. Web Search

▸ Real-time information acquisition: Possesses powerful web search capabilities, capable of obtaining the latest information from the Internet in real-time. In question and answer scenarios, when a user's question requires the latest news, data, and other information, the platform can quickly search and return accurate results, enhancing the timeliness and accuracy of the answers

▸ Multi-source data integration: Integrates various Internet data sources, including news websites, academic databases, industry reports, etc. Through the integration and analysis of multi-source data, it provides users with more comprehensive and in-depth information. For example, in market research scenarios, relevant data can be obtained from multiple data sources at the same time for comprehensive analysis and evaluation

▸ Intelligent search strategy: Adopt intelligent search algorithms, automatically optimize search strategies based on user questions to improve search efficiency and accuracy. Support keyword search, semantic search and other search methods to meet the needs of different users. At the same time, intelligently sort and filter search results, prioritize the display of the most relevant and valuable informatio