Back to Home
ScienceOL icon

Xyzen

Verified Safe

by ScienceOL

Overview

A comprehensive AI-powered chat component and backend service for React applications, featuring LLM integration, agent orchestration with LangChain/LangGraph, customizable tools, and multi-protocol chat capabilities.

Installation

Run Command
uv run python -m app.main

Environment Variables

  • XYZEN_ENV
  • XYZEN_DEBUG
  • XYZEN_HOST
  • XYZEN_PORT
  • XYZEN_LOGGER_LEVEL
  • XYZEN_DATABASE_ENGINE
  • XYZEN_DATABASE_POSTGRES_HOST
  • XYZEN_DATABASE_POSTGRES_PORT
  • XYZEN_DATABASE_POSTGRES_USER
  • XYZEN_DATABASE_POSTGRES_PASSWORD
  • XYZEN_DATABASE_POSTGRES_DBNAME
  • XYZEN_DATABASE_SQLITE_PATH
  • XYZEN_LLM_PROVIDER
  • XYZEN_LLM_KEY
  • XYZEN_LLM_ENDPOINT
  • XYZEN_LLM_VERSION
  • XYZEN_LLM_DEPLOYMENT
  • XYZEN_MCP_SMITHERY_KEY
  • SMITHERY_API_KEY
  • XYZEN_DIFY_DIFYAPI
  • XYZEN_DIFY_DIFYKEY1
  • XYZEN_DIFY_DIFYKEY2
  • XYZEN_DIFY_TIMEOUT
  • XYZEN_LAB_API
  • XYZEN_LAB_TIMEOUT
  • XYZEN_ADMIN_SECRET

Security Notes

The project implements a sandbox for user-defined tools, which is a strong positive for security. It includes API proxies for external services (Bohrium, Smithery, OpenAPI) to mitigate CORS, but these always introduce an additional attack surface. A specific hardcoded API key (`BOHRAPP_X_APP_KEY`) exists for a particular BohrApp integration, though other keys are configurable. The use of `subprocess.Popen` is contained to specific, well-defined external tools (Playwright MCP) and is not exposed to arbitrary user input. Overall, while external integrations add complexity, the core design appears mindful of security risks, especially for dynamic tool execution.

Similar Servers

Stats

Interest Score38
Security Score7
Cost ClassMedium
Avg Tokens500
Stars12
Forks3
Last Update2025-12-05

Tags

AILLMChatbotAgentsLangChainLangGraphFastAPIPostgreSQLReactWebSocket