Mastra platform
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 4
- Mastra Platform Adds Observability Alerts for AI Agents
Mastra introduced observability alerts that monitor AI agent behavior against configurable thresholds for errors, traffic volume, latency, token usage, model costs and evaluation scores. According to Mastra, alerts can be scoped by agent, tool, model or user and delivered through Slack, Discord, Microsoft Teams, email, webhooks, PagerDuty or incident.io, with enabled rules checked every five minutes.
Mastra Blog · 🔥 3 - Mastra Adds $25 Starter Plan for AI Agent Deployments
Mastra introduced a $25 Starter plan that includes one Small dedicated server with its compute included, according to the vendor’s blog. The tier raises monthly allowances for compute, data, observability events, and connections, while usage beyond those limits is billed separately; serverless agents remain free to run on every plan. Mastra also changed how compute is measured, updated allowances across its plans, and renamed the former free Starter tier to Free.
Mastra Blog · 🔥 0 - Mastra Platform adds trace imports, starting with Langfuse
Mastra introduced trace imports, letting users pull existing traces from third-party observability providers into the Mastra platform; Langfuse is the first supported source, with more providers to follow. Imported traces appear alongside Mastra-generated traces in the platform and deployed Studio for debugging, filtering and comparison. Mastra says imports preserve span types such as agent_run, model_generation and tool_call, along with parent-child structure, timestamps, inputs, outputs, usage and cost, while scores, feedback, datasets, attachments and logs are omitted. The feature requires [email protected] and @mastra/[email protected] or later and supports dry-run previews, date-window imports and resuming interrupted imports.
Mastra Blog · 🔥 0 - Mastra launches Metrics API for its platform
Mastra released a Metrics API that lets developers query token usage, model cost, latency and error rates from production Mastra projects via the Mastra Client SDK, Mastra CLI or observability endpoints. The API supports totals, breakdowns, time series and percentile data, and can combine queries with time ranges and status filters to build custom reports, dashboards, downstream data feeds and alerts. Mastra says metrics aggregate across every run, whereas traces show what happened in a single run.
Mastra Blog · 🔥 0
Experience and discussion from the community
Share my Mastra platform experienceAsk about Mastra platform
Nobody has shared their experience with Mastra platform yet.