An open-source LLM application devops platform for enterprises, covering workflows, RAG, agents, model management, evaluation and fine-tuning.
- Stars
- 23,006
- Forks
- 3,194
- Open issues
- 21
- Last commit
- 3 hours ago
What is it?
MaxKB (Max Knowledge Brain) is an open-source platform for building enterprise AI agents. It targets scenarios such as intelligent customer service, internal corporate knowledge bases, academic research and education, where a chatbot must answer questions from a specific body of documents.
The platform includes a RAG pipeline that accepts uploaded documents or automatically crawled online pages, splits the text and vectorizes it to ground model answers. A workflow engine and function library let users orchestrate multi-step AI processes, and MCP tool use is supported. Business systems can be connected without custom coding so existing products can add Q&A capabilities.
MaxKB works with both private models such as DeepSeek, Llama and Qwen and public APIs such as OpenAI, Claude, Gemini and MiniMax. It handles text, image, audio and video input and output. The stack uses Vue.js for the frontend, Python with Django on the backend, LangChain for LLM orchestration, and PostgreSQL with pgvector for storage. It can be started with a single Docker command.
Key features
- 01Document upload and web crawling feed a RAG pipeline with automatic text splitting and vectorization.
- 02Visual workflow engine with a function library for orchestrating multi-step AI processes.
- 03MCP tool-use support for agents.
- 04Works with both private models (DeepSeek, Llama, Qwen) and public APIs (OpenAI, Claude, Gemini).
- 05Native text, image, audio and video input and output.
- 06Zero-code integration into third-party business systems.
Use cases
- Building an internal knowledge-base assistant that answers staff questions from company documents.
- Adding a Q&A chatbot to an existing customer service system.
- Prototyping multi-step agent workflows that call external tools via MCP.
- Deploying a private LLM-backed Q&A system on self-hosted infrastructure.
Quick start
- 1
Start the MaxKB container with Docker
docker run -d --name=maxkb --restart=always -p 8080:8080 -v ~/.maxkb:/opt/maxkb 1panel/maxkb - 2
Open the web interface at your server IP on port 8080 and log in with the default admin account
Things to know
- The default admin password is published in the README and should be changed after first login.
- Using large models requires your own API keys or self-hosted models.
Topics
FAQ
- What is MaxKB?
- Open-source platform for building enterprise-grade AI agents, with RAG knowledge bases, visual workflows and MCP tool use. MaxKB (Max Knowledge Brain) is an open-source platform for building enterprise AI agents. It targets scenarios such as intelligent customer service, internal corporate knowledge bases, academic research and education, where a chatbot must answer questions from a specific body of documents.
- Is MaxKB free to use? What license does it have?
- MaxKB is open source under the GPL-3.0 license. Check the license terms before using it in commercial products.
- Is MaxKB still maintained?
- Actively maintained. The last commit to MaxKB was on Oct 21, 2026.
- What can I use MaxKB for?
- Building an internal knowledge-base assistant that answers staff questions from company documents. Adding a Q&A chatbot to an existing customer service system. Prototyping multi-step agent workflows that call external tools via MCP. Deploying a private LLM-backed Q&A system on self-hosted infrastructure.
- How do I install MaxKB?
- Start the MaxKB container with Docker: docker run -d --name=maxkb --restart=always -p 8080:8080 -v ~/.maxkb:/opt/maxkb 1panel/maxkb Open the web interface at your server IP on port 8080 and log in with the default admin account
- Where can I get MaxKB?
- The source code and installation instructions are on GitHub: https://github.com/1Panel-dev/MaxKB
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source LLM app development platform combining visual agentic workflows, RAG pipelines, model management and observability in one workspace.
FastGPT is an open-source AI Agent building platform with data processing, RAG knowledge bases, and visual workflow orchestration for LLM apps.
A zero-code platform that generates production-style AI agents from natural-language descriptions, with built-in tools, memory and orchestration.
Self-hostable personal AI assistant as a single Go binary, combining LLM chat, RAG knowledge bases, and agent loops for browsing, shell, and MCP tools.
Open-source AI app builder for creating and running agentic workflows with a visual drag-and-drop editor and multiple LLM providers.