MaxKB
An open-source platform for building enterprise-grade AI agents, combining a RAG pipeline, an agentic workflow engine and MCP tool use, aimed at uses such as customer service and internal knowledge bases.
MaxKB, short for Max Knowledge Brain, is an open-source platform for building enterprise-grade AI agents. It combines a retrieval-augmented generation pipeline with a workflow engine and MCP tool use, and is applied in scenarios such as intelligent customer service, internal knowledge bases, academic research and education.
Its RAG pipeline accepts directly uploaded documents or automatically crawled online documents, with automatic text splitting and vectorization to reduce hallucination in question answering. Its agentic workflow engine, function library and MCP tool use let a team orchestrate AI processes for more complex business scenarios, and it can be integrated into existing business systems without writing code. It is model-agnostic, supporting private models such as DeepSeek, Llama and Qwen as well as public models such as OpenAI, Claude, Gemini and MiniMax, and natively handles text, image, audio and video input and output.
It runs as a Docker container, with a Vue.js frontend, a Python/Django backend, LangChain, and PostgreSQL with pgvector for storage. It is licensed under the GPL-3.0 license.