← back to the directory
Library / SDK Observability & EvaluationRetrieval & Memory

TruLens

1Evaluate 2and 3track 4LLM 5app 6experiments

the six Ws · specification

W1 Who

Maintained by TruEra (now part of Snowflake).

W2 What

A library for evaluating and tracking LLM apps using programmatic feedback functions.

W3 Where

A Python library run locally with a local dashboard.

W4 When

Reach for it when iterating on RAG and agent quality with quantitative feedback.

W5 Why

Feedback functions give measurable scores to compare app versions.

W6 With

Integrates with LangChain, LlamaIndex, and OpenAI.

W7 Watch

Originated at TruEra (acquired by Snowflake); open-source (MIT) library, self-hostable. Feedback functions may call whatever provider you configure.

EvaluationObservabilityRAGFeedback

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.