Yuxi-Know is an LLM agent orchestration platform that coordinates multiple AI agents through graph-based workflows to decompose and execute complex reasoning tasks. It functions as a multi-tenant AI workspace with an agentic chat interface, combining retrieval-augmented generation with knowledge graph management for enterprise document processing and retrieval.
The platform distinguishes itself through graph-based agent orchestration, where directed acyclic graphs define execution dependencies between reasoning steps, enabling parallel or sequential task decomposition. It provides multi-tenant environment isolation with tenant-specific knowledge bases, virtual file systems, and session management, alongside a plugin-based sandbox tool system for executing user-defined scripts in isolated environments. The system integrates OCR-driven document ingestion, background job monitoring, and a retrieval-augmented generation pipeline that combines vector database queries with knowledge graph traversal for grounded responses.
Additional capabilities include knowledge graph reasoning for multi-hop inference, super admin account creation for access control, and deployment options spanning full-stack Docker Compose launch, a resource-conserving lite mode, and offline setup for environments without internet access. The platform is configured through a scripted API key setup process and provides a web interface with auto-generated API documentation.