Skip to main content
TraceRoot is an open-source AI agent improvement platform. Instrument your code with a few lines, get full visibility into every LLM call, tool invocation, and agent decision. Run detectors to catch failures and hallucinations the moment they happen. Then let TraceRoot’s AI agent analyze findings, debug failures and create fix PRs automatically.

​
Key Capabilities

Tracing

Capture every LLM call, tool use, and agent step with OpenTelemetry-based instrumentation.

Detectors

Continuously evaluate every trace with an LLM; get alerted the moment your agent fails, hallucinates, or drifts.

TraceRoot Agent

Root cause analysis and automated fix PRs — powered by the TraceRoot Agent with access to your source code.

Evaluations

Test changes against versioned datasets and compare scores across evaluation runs.

Dashboards

Explore latency, cost, and error metrics with filtered, reusable widgets.

Alerts

Monitor metric thresholds and send notifications to your team’s Slack channel.
Start with the quickstart, or learn how workspaces, projects, and roles organize access to your data.