SapientiaSapientia
  • Documentation
  • Enterprise
    Introduction
    Getting Started
    Configuration
    Workflow Builder
    Memories
    Performance & Monitoring
    Local API Server
    Troubleshooting

    Performance & Monitoring

    Monitor AI performance metrics, throughput, and system resource usage


    Track and optimize your AI system's performance with real-time monitoring tools.

    Dashboard Performance Status

    View real-time performance metrics and system health status.

    Metrics: Throughput, TTFT and TPS

    Understand key performance indicators like Time To First Token and Tokens Per Second.

    Sapientia

    Run Large Language Models entirely on your device. Sapientia brings AI capabilities to your local environment with complete privacy, offline functionality, and visual workflow orchestration for intelligent agent systems.

    Quick Links

    • Home
    • Documentation

    Resources

    • Privacy Policy
    • Term of use

    Contact Us

    • sapientia@godiscus.com
    InstagramLinkedInGitHubTwitter / X

    ©2026 Sapientia Project by GoDiscus. Made with by Sapientia Team.