{"id":"maxkb","name":"MaxKB","homepage":"https://github.com/1Panel-dev/MaxKB","repo_url":"https://github.com/1Panel-dev/MaxKB","category":"ai-ml","subcategories":["rag-platform","agent-platform","knowledge-base","chatbot"],"tags":["rag","knowledge-base","agent-platform","mcp-tool-use","langchain","pgvector","django","vue","enterprise","chinese","multimodal","chatbot"],"what_it_does":"Open-source enterprise AI agent platform that combines RAG (retrieval-augmented generation) with agentic workflows and MCP tool-use support. Enables document upload, web crawling, automatic text segmentation and vectorization, and zero-code integration into existing business systems for intelligent Q&A. Supports multiple LLM backends including DeepSeek, Llama, Qwen, OpenAI, Claude, and Gemini.","use_cases":["Building enterprise knowledge base chatbots with RAG","Automating business processes with agentic workflows","Zero-code intelligent Q&A integration into existing systems","Multimodal document processing (text, image, audio, video)","Internal enterprise search and knowledge management"],"not_for":["Lightweight personal chatbot needs (overengineered)","Teams without Docker/infrastructure capabilities","English-first documentation expectations (primarily Chinese docs)"],"best_when":"You need an enterprise-grade self-hosted RAG + agent platform with MCP tool-use support, especially if your team reads Chinese and wants a polished UI for knowledge base management.","avoid_when":"You need English-first documentation, a lightweight solution, or don't want to manage PostgreSQL + pgvector infrastructure. Not an MCP server itself -- it consumes MCP tools rather than exposing them.","alternatives":["dify","ragflow","langflow","flowise","quivr"],"af_score":39.0,"security_score":0.0,"reliability_score":null,"package_type":"mcp_server","discovery_source":["github","openclaw"],"priority":"low","status":"evaluated","version_evaluated":"unknown","last_evaluated":"2026-03-01T09:50:05.834474+00:00","performance":{"latency_p50_ms":null,"latency_p99_ms":null,"uptime_sla_percent":null,"rate_limits":null,"data_source":"llm_estimated","measured_on":null}}