The one rule: one agent execution = one trace. LLM calls and tool calls are child spans of that trace, not separate traces.
Get started
Quickstart
Install the SDK, point it at Lemma, and send your first trace in a few minutes.
Lemma tracing skill
Let a coding agent install the SDK and add tracing from the public Lemma repo.
Building high-quality traces
The ideal instrumentation path, with bad → better → best examples.
How it works
- Instrument with the SDK. Wrap one agent execution in
lemma.trace(), and record generation, tool, and app work inside it. - The SDK sends to Lemma over HTTPS, using your Lemma credentials.
- Lemma reads the trace shape to show inputs and outputs, model calls, tool calls, threads, and to run automated issue detection.
What to instrument
Instrument every part of your agent. Each layer unlocks more of Lemma, and a complete trace is what powers full debugging and automated issue detection. Aim to record all of them.
See Building high-quality traces for what a complete, well-instrumented trace looks like.
What you can do with Lemma
Trace agents - see the full execution tree for every trace: LLM calls, tools, retrieval, latency, and errors. Debug failures - inspect inputs, outputs, and errors across nested spans; filter by user, session, and custom attributes. Connect your IDE - use the Lemma MCP server to query traces from Cursor, Claude Desktop, or Claude Code.Choose your path
Instrument with the SDK
Install the SDK, then add traces, generations, tool calls, and spans.
Building high-quality traces
The ideal instrumentation path, with bad → better → best examples.