Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Mastra

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 5

  1. Mastra launches Trace Queries for filtering and debugging agent traces

    Mastra introduced Trace Queries, letting users filter and find traces in the Mastra platform and local Studio by trace fields such as time, primitive name, agent/workflow ID, status, score and feedback, and build the same queries via the CLI, the Mastra Client SDK or HTTP observability endpoints. The feature can reach low-level information nested inside a trace — a failed tool call, a low score or thumbs-down feedback — so a coding agent can query for errored or failed traces and slow model calls and then fix them. Each query covers a time range of up to 31 days and can combine up to 100 conditions, with up to 8 filters on trace internals (spans, scores, feedback) and operators including and/or/not, eq, gt, exists and matches; self-hosted projects need DuckDB, PostgreSQL or ClickHouse for observability storage. The CLI requires [email protected] or later and the client SDK requires @mastra/[email protected] or later.

    Mastra Blog · 🔥 0
  2. Mastra adds trace imports from Langfuse to pull observability history into its platform

    Mastra introduced trace imports for Mastra Platform, letting users pull existing traces from third-party observability providers into Mastra, where they appear alongside Mastra-generated traces for debugging, filtering and comparison. Langfuse is supported first, with more providers to follow; Mastra notes that observability data previously could only be exported out to third parties. 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 CLI requires [email protected] and @mastra/[email protected] or later and supports dry-run previews, date windows with --since/--until, and resuming interrupted imports.

    Mastra Blog · 🔥 0
  3. Mastra launches Metrics API for token usage, cost and latency

    Mastra introduced a Metrics API that lets developers query token usage, model cost, latency and error rates for production projects through the Mastra Client SDK, Mastra CLI or observability endpoints. The API supports totals, breakdowns, time series and percentile queries, combinable with time ranges and status filters, for custom reports, dashboards, downstream data pushes or alerts when model costs or error rates rise. According to the Mastra blog, queries require a platform access token and project ID plus the region-specific observability base URL (US and EU), with @mastra/client-js 1.9.0+ and mastra CLI 1.9.2+; Mastra also says the API can be paired with code mode so agents construct their own queries.

    Mastra Blog · 🔥 0
  4. Mastra Observability adds Thread View for agent debugging

    Mastra announced Thread View in its blog, letting users read agent conversation messages alongside the trace steps that produced them in Mastra Studio, and open the full thread to follow the whole conversation in order. The feature targets people debugging agent behavior, including subject-matter experts who did not build the agent; if an agent already uses memory and persists traces with MastraStorageExporter, no additional setup is needed. Mastra says it requires [email protected] or later and was added in PR #25812.

    Mastra Blog · 🔥 0
  5. Mastra launches certified Agency Program with five launch partners

    Mastra announced the Mastra Agency Program, a network of certified agencies and consultancies that build Mastra agents for their clients, aimed at teams that want agents in production but lack in-house expertise. It launches with five partners: Deerfield Group, Blue Drop Labs, Frontleap, Handpicked and Young Security, the last of which designs, builds and operates production AI agents on Mastra. Mastra says every partner was vetted by its FDE team and gets a direct line to the founding team, regular partnership and roadmap updates, and a voice in the product's direction.

    Mastra Blog · 🔥 0

Experience and discussion from the community

Share my Mastra experienceAsk about Mastra

Nobody has shared their experience with Mastra yet.