Skip to main content

CloudBase AI Development Kit

tip

Seamless integration of DeepSeek + Hunyuan dual models for AI agent development, supporting scenarios such as mini programs, h5, official accounts, and WeChat Customer Service.

New users get a free trial for the first month and receive 1 million tokens.

Learn more

Tencent CloudBase provides the CloudBase AI Development Kit to help developers quickly build their own AI applications.

CloudBase AI Intelligence

In Cloud Development AI+, we provide a series of AI-related features, such as large model access, Agent, etc., to help developers quickly integrate AI capabilities into their mini-programs, web, or applications. We also offer Cloud Development Copilot to accelerate user development and help users build their applications faster.

Agent Building

Agent, or AI Agent, is based on large models, with strong language understanding and generation capabilities, and can perform complex tasks in various domains.

Core ScenariosCapability DescriptionOperation Guide
Intelligent Q&A AgentZero-code: 🧠 Supports integration with vertical knowledge bases ✅ Supports multi-turn conversations/intent recognition/multi-language scenariosSetup Guide
Automated Intelligent AgentZero-code + MCP Extension: 🧠 Empowers AI to invoke external world capabilities through MCP. AI automatically decomposes tasks, invokes MCP to connect everything and executeSetup Guide
Function-based AgentFor professional developers: 🧠 Complex scenario Agent, invokes AI large models, MCP plugins, knowledge bases by coding, integrates business data and interfaces to implement custom code logicSetup Guide

Agent Building Function Entry: Agent Building

View Detailed Documentation

Cloud Development Copilot is based on built by the Agent building capabilities of AI+

Agent Integration

Developed Agent can be used in the following ways:

Core ScenariosCapability DescriptionOperation Guide
Mini Program⚡ Instant Response/Intelligent Answering/Multi-scenario Script SupportAccess Now
web Application⚡ Instant Response/Intelligent Answering/Multi-scenario Script SupportAccess Now
Official Account Customer Service⚡ Instant Response/Intelligent Answering/Multi-scenario Script SupportAccess Now
Mini Program Customer Service⚡ Instant Response/Intelligent Answering/Multi-scenario Script SupportAccess Now
WeCom Customer Service⚡ Instant Response/Intelligent Answering/Knowledge Base Integration/Multi-scenario Script SupportAccess Now
Service Account Customer Service⚡ Instant Response/Intelligent Answering/Knowledge Base Integration/Multi-scenario Script SupportAccess Now
Integration into Existing Applications🔧 Seamless integration solution for existing Mini Programs/PC/H5Code Integration Solution

Agent UI

We also provide Agent UI, which enables direct use in Mini Programs, web, or applications without developing a chat interface.

Component NameOperation Guide
Mini Program Source Code Component IntegrationQuick Integration
WeDa Visual Component IntegrationQuick Integration
React Component IntegrationQuick Integration

AI SDK

We provide multi-end SDKs, enabling developers to quickly integrate Agent and achieve interaction with the Agent.

The complete guide for Mini Programs can refer to the Mini Program Integration with CloudBase AI Capabilities Guide

Core ScenariosOperation Guide
WeChat Mini Program IntegrationQuick Integration
WeChat Mini Game IntegrationQuick Integration
WeChat Cross-End Framework IntegrationQuick Integration
web Client IntegrationQuick Integration
Node.js Client IntegrationQuick Integration
Integration in WeDaQuick Integration
App Client IntegrationQuick Integration
Other Languages and Frameworks IntegrationQuick Integration

Knowledge Base

A knowledge base is an integration of data, information, and knowledge content. By using a knowledge base, existing data, information, and content can be consolidated, vectorized, and quickly located through operations such as querying, retrieval, and analysis. Through the integration of Agents and knowledge bases, Agents can access domain-specific information or knowledge, enabling quick and accurate responses based on the knowledge base content in scenarios like problem solving, knowledge Q&A, and data retrieval.

Agent is an intelligent solution based on AI large models combined with knowledge bases, enabling intelligent Q&A, intelligent retrieval, intelligent customer service, and other functions.

See Knowledge Base Getting Started

See Knowledge Base Getting Started

MCP

MCP is an open protocol that standardizes how AI applications provide context to large language models (LLMs). Think of MCP as the USB-C interface for AI applications. Just as USB-C provides a standardized way for devices to connect various peripherals and accessories, MCP offers a standardized way for AI models to connect different data sources and tools.

The core of MCP adopts a Client-Server architecture, where a single application can connect to multiple MCP Servers.

As long as AI applications implement MCP, they can connect to any MCP Server to extend their capabilities. After joining an MCP Server, the tool invocation process is as follows:

In this way, MCP achieves:

  1. Plug and Play: AI applications only need to implement the MCP protocol to access a rich ecosystem of third-party tools.
  2. Standardization: All tools follow a unified description format and invocation method.
  3. Decoupling Tools and Applications: Tool providers can independently develop and maintain tools without needing to understand the internal implementation of AI applications.
  4. Resource Sharing: Tools developed once can be reused by multiple AI applications.

View MCP Getting Started

Beta Feedback Discussion Group

AI+ Beta Feedback and Discussion Group, developers are welcome to join