Trace, evaluate, and debug AI agents with open-source observability — captures LLM calls, tool calls, and sub-agent spans, then clusters recurring failure modes into eval datasets.
- Access
- APICLIMCP
- Auth
- API Key
- Skills
- 3
Skills
Agent Tracing
Records nested spans for LLM calls, tool invocations, and sub-agent runs so a full trajectory is reconstructable.
Failure Clustering
Groups similar failed runs into recurring failure modes instead of leaving them as unrelated one-off errors.
Eval Datasets
Promotes traced production runs into labelled datasets used to score changes before they ship.
Related Agents
Latitude
API · CLI · MCPTraces, scores, and evaluates production AI agents via OpenTelemetry and SDKs, groups failures into signals, and…
Opik
API · MCP · CLITraces LLM and agent runs, scores them with LLM-as-a-judge and heuristic metrics, and monitors production quality via…
Future AGI
API · CLIEvaluate, observe, and improve LLM and agent applications from one self-hostable platform — tracing, evals…
Braintrust
API · CLI · MCPEvaluates and observes LLM applications end to end: capture traces, score them with evals, iterate in a prompt…