Trace Jev in TypeScript
The TypeScript SDK now traces TypeSafe AI's Jev calls as decision spans with model, tokens and cost.
TraceRoot Changelog
New features, improvements, and fixes from the TraceRoot team.
All updates[15]
15 updates
Introducing Signals
Detectors now group findings into signals: one per recurring problem, each with one root cause analysis.
Use Jev as your detector judge
Power your detectors with Jev using your own TypeSafe AI key.
Introducing TraceRoot dashboards
TraceRoot dashboards bring agent latency, cost, tokens, and failures into configurable views, with a widget builder and links to the underlying traces.
Read traces from your terminal
List recent traces, inspect a span tree and export trace context from the CLI.
Trace Claude Code conversations
Follow each conversation turn through its model calls, tools and nested agents.
Use your own model for detector investigations
Automatic root cause analysis now uses the BYOK model and provider saved for your project.
Trace OpenRouter calls
Trace OpenRouter requests through the OpenAI-compatible SDK in Python or TypeScript.
See what makes up a trace’s token usage and cost
Inspect input, output and cache usage alongside the cost of a trace or individual span.
Trace Microsoft Agent Framework
Capture Microsoft Agent Framework runs, model calls and tools in TraceRoot.
Trace Pydantic AI
Capture Pydantic AI agent runs, model calls and tools with the Python SDK.
Trace the Vercel AI SDK
Inspect model calls and tool steps from Vercel AI SDK applications in TraceRoot.
Agno, DSPy, Mistral and Google ADK tracing
Trace agent runs, model calls and tools across four more Python integrations.
See where time goes in a trace
Find slow steps, parallel calls and gaps with TraceRoot's new Timeline view.
Watch traces as your agent runs
Inspect a trace before the agent has finished.
