Mastra Dashboard

This dashboard offers a clear view into Mastra usage and performance. It highlights key metrics such as token consumption, model distribution, error rates, request volumes, and latency trends.

Dashboard Preview

What This Dashboard Monitors

This dashboard tracks critical performance metrics for your Mastra usage using OpenTelemetry to help you:

• Monitor Token Consumption: Track input tokens (user prompts) and output tokens (model responses) to monitor system workload, efficiency trends, and consumption across different workloads.
• Track Reliability: Monitor error rates to identify reliability issues and ensure applications maintain a smooth, dependable experience.
• Analyze Model Adoption: Understand which Mastra model variants are being used most often to track preferences and measure adoption of newer releases.
• Monitor Usage Patterns: Observe token consumption and request volume trends over time to spot adoption curves, peak cycles, and unusual spikes.
• Ensure Responsiveness: Track P95 latency to surface potential slowdowns, spikes, or regressions and maintain consistent user experience.
• Understand Service Distribution: See which services and programming languages are leveraging the Mastra across your stack.
• Track Agent Activity: Monitor which agents are being invoked to understand agent utilization patterns and identify the most active agents in your workflows.
• Analyze Tool Usage: Track which tools are being called to understand tool adoption, usage patterns, and optimize your tool ecosystem.

Metrics Included

Token Usage Metrics

• Total Token Usage (Input & Output): Displays the split between input tokens (user prompts) and output tokens (model responses), showing exactly how much work the system is doing over time.
• Token Usage Over Time: Time series visualization showing token consumption trends to identify adoption patterns, peak cycles, and baseline activity.

Performance & Reliability

• Total Error Rate: Tracks the percentage of Mastra calls that return errors, providing a quick way to identify reliability issues.
• Latency (P95 Over Time): Measures the 95th percentile latency of requests over time to surface potential slowdowns and ensure consistent responsiveness.

Usage Analysis

• Model Distribution: Shows which llm model variants are being called most often, helping track preferences and measure adoption across different models.
• Requests Over Time: Captures the volume of requests sent to Mastra over time, revealing demand patterns and high-traffic windows.

Error Tracking

• Error Records: Table logging all recorded errors with clickable records that link to the originating trace for detailed error investigation.

Agent & Tool Analytics

• List of Agents Being Used: Displays all active agents in your system, showing which agents are being invoked most frequently to help optimize agent workflows and resource allocation.
• List of Tool Calls Being Used: Shows all tools being called across your Mastra workflows, providing visibility into tool adoption patterns and usage frequency to identify optimization opportunities.