TruLens

EvaluationMIT

TruLens evaluates and traces LLM applications and agents, recording each step as an OpenTelemetry span and attaching evaluation results to those traces. Its site says the project is shepherded by Snowflake and was originally created by TruEra.

The README lists provider packages for OpenAI, LiteLLM, Google Gemini, AWS Bedrock, Snowflake Cortex and Hugging Face, app packages for LangChain, LangGraph and LlamaIndex, and an MCP span type that records tool name, arguments, output and latency.

Pinout

  • MCP server: not checked yet
  • HTTP API: not checked yet
  • command line: not checked yet
  • Python SDK: supported, verified
  • TypeScript SDK: not checked yet
  • OpenAPI description: not checked yet
Where each pin comes from
InterfaceStatusSource we readRead on
MCP serverNot checked yet——
HTTP APINot checked yet——
Command lineNot checked yet——
Python SDKSupported, verifiedREADME, install (pip install trulens)
TypeScript SDKNot checked yet——
OpenAPI descriptionNot checked yet——

Facts

Facts about TruLens
LicenseMIT. GitHub API, repository license field, read .
Main languagePython (as detected by GitHub). GitHub API, repository record, read .
Publishertruera (GitHub organization). GitHub API, repository record, read .
Latest GitHub releasetrulens-2.16.0, published 2026-10-19. GitHub API, latest release, read .
OpenTelemetryInstrumentation built on OpenTelemetry. README in the repository, read .
MCP tracingMCP span type for tool calls. README in the repository, read .
Last commit. GitHub API, latest commit on the default branch of truera/trulens, read .

Limits

  • Each model provider and framework is a separate package to install next to the core package, as listed in the README.

Strengths

  • Traces are OpenTelemetry spans, so the README states they can go to any OTLP backend.

Alternatives to TruLens

All evaluation tools for agents
  1. Readymade evaluators that score an agent's trajectory of steps.

    Evaluation
  2. Observability and evaluation platform for tracing and improving AI agents.

    Evaluation
  3. Readymade evaluators for LLM applications in Python and TypeScript.

    Evaluation
  4. Python toolkit for metrics and test-set generation for LLM applications.

    Evaluation

Last check: . Method: public repository and docs read automatically, page and day written down. Next check due within 90 days. How we check

Is this your tool? Write to hello@agent-tools.directory from an address on its domain to correct a pin or a fact.