xerrors/Yuxi-Know
Yuxi Know
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.
Features
- Agent Orchestration Platforms - An AI platform that coordinates multiple agents through graph-based workflows for complex reasoning and task execution.
- Agent Workflow Orchestrations - Coordinates multiple LLM agents through graph-based workflows for complex reasoning and task execution.
- Agentic Workflow Graphs - Coordinates multiple LLM agents through a directed acyclic graph where nodes represent reasoning steps and edges define execution dependencies.
- Graph Retrieval Augmented Generation - Combines vector database queries with knowledge graph traversal to ground agent responses in indexed enterprise documents.
- Interactive Agent Chat Interfaces - Presents retrieved and reasoned knowledge through an interactive conversational chat interface.
- RAG Context Retrieval - Queries indexed document collections to fetch relevant context for grounding agent responses.
- RAG Knowledge Management - Processes enterprise documents using retrieval-augmented generation and knowledge graphs for retrieval.
- Tenant-Specific Knowledge Workspaces - Provides isolated AI workspaces with tenant-specific knowledge bases, file systems, and session management.
- Graph-Based Workflow Models - An engine that decomposes complex tasks into parallel or sequential steps using graph-based agent coordination.
- Graph Reasoning Systems - Traverses entity-relation graphs to infer connections and answer multi-hop reasoning questions.
- Workspace Isolations - Separates organizations into isolated workspaces with tenant-specific knowledge bases, virtual file systems, and session management.
- Sandboxed Plugin Runtimes - Executes user-defined tools and scripts in isolated sandbox environments with configurable resource limits.
