trulens
Library to systematically track and evaluate LLM based applications.
Decision gist · record as of 2026-08-14
Yes. TruLens is actively maintained, has low install friction, carries a permissive MIT license, and solves a concrete problem—systematic tracing and evaluation of LLM applications—that most LLM teams face. It is adopted by major organizations and integrates with standard observability infrastructure. Install it if you need to debug agent failures, compare LLM app versions, or measure quality-cost tradeoffs.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later; LLM provider packages must be installed separately for feedback evaluation.
- Low friction: pure Python wheel with five internal runtime dependencies (trulens-core, trulens-dashboard, trulens-feedback, trulens-otel-semconv, trulens_eval).
- Active maintenance as of 2026-08-14 with 3508 GitHub stars.
License · maintenance · safety
MIT (permissive) — MIT license (permissive) allows commercial and private use with minimal restrictions—suitable for production deployment in most organizational contexts.
last release 2026-08-14 (0 days) · last repo commit 2026-08-14 · 3,508 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 107,852 downloads/mo, #12,591 on PyPI
Alternatives
Verify before relying
pip install trulens
from trulens.core.otel.instrument import instrument
from trulens.otel.semconv.trace import SpanAttributes
class MyRAG:
@instrument(
span_type=SpanAttributes.SpanType.RETRIEVAL,
attributes={
SpanAttributes.RETRIEVAL.QUERY_TEXT: "query",
SpanAttributes.RETRIEVAL.RETRIEVED_CONTEXTS: "return",
},
)
def retrieve(self, query: str) -> list:
pass- Whether the seven agentic evaluators are available in the base package or distributed across the five runtime dependencies.
- Whether the Run API for batch evaluation and Selector API are part of core or split across dependencies.
- Performance characteristics and latency overhead of inline vs. batch evaluation on large datasets.
What it is and what it does
TruLens is an open-source library for systematically tracing and evaluating LLM-based applications. It uses OpenTelemetry-native instrumentation to capture every function call, LLM generation, retrieval, and tool invocation as structured spans, then scores outputs using LLM judges that explain their reasoning. The core workflow is: decorate your app functions with the @instrument decorator, run queries or batch datasets through your app, collect traces and evaluation scores, then compare versions to identify which performs best on the tradeoff between quality and cost.
The package bundles five internal components (trulens-core, trulens-dashboard, trulens-feedback, trulens-otel-semconv, trulens_eval) and is designed to integrate with existing observability infrastructure via OTLP backends. It includes evaluators for agentic systems and supports both inline evaluation (as the app runs) and offline batch evaluation over pre-collected datasets. Additional LLM provider packages and app framework integrations are installed separately.
Use it for
- Trace retrieval latency and token usage in a RAG pipeline to identify cost-quality tradeoffs.
- Evaluate agent reasoning chains step-by-step to catch logical inconsistencies and tool-selection errors.
- Compare two versions of an LLM application on a fixed dataset using batch evaluation.
- Export traces to an OTLP backend to correlate LLM behavior with infrastructure metrics.
- Score context relevance and groundedness of RAG outputs using LLM judges.
- Capture Model Context Protocol tool calls with structured spans to debug agentic workflows.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
TruLens is actively maintained, has low install friction, carries a permissive MIT license, and solves a concrete problem—systematic tracing and evaluation of LLM applications—that most LLM teams face. It is adopted by major organizations and integrates with standard observability infrastructure. Install it if you need to debug agent failures, compare LLM app versions, or measure quality-cost tradeoffs.
Install
trulens on PyPI
Before you install
Low friction: pure Python wheel with five internal runtime dependencies (trulens-core, trulens-dashboard, trulens-feedback, trulens-otel-semconv, trulens_eval). Active maintenance as of 2026-08-14 with 3508 GitHub stars.
Requires Python 3.10 or later; LLM provider packages must be installed separately for feedback evaluation.
License in practice
MIT license (permissive) allows commercial and private use with minimal restrictions—suitable for production deployment in most organizational contexts.
Quickstart
pip install trulens
from trulens.core.otel.instrument import instrument
from trulens.otel.semconv.trace import SpanAttributes
class MyRAG:
@instrument(
span_type=SpanAttributes.SpanType.RETRIEVAL,
attributes={
SpanAttributes.RETRIEVAL.QUERY_TEXT: "query",
SpanAttributes.RETRIEVAL.RETRIEVED_CONTEXTS: "return",
},
)
def retrieve(self, query: str) -> list:
passVerify before relying
- Whether the seven agentic evaluators are available in the base package or distributed across the five runtime dependencies.
- Whether the Run API for batch evaluation and Selector API are part of core or split across dependencies.
- Performance characteristics and latency overhead of inline vs. batch evaluation on large datasets.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release <4.0,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 5 packagestrulens-coretrulens-dashboardtrulens-feedbacktrulens-otel-semconvtrulens_eval |
| Maintenance | Actively maintained 0 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 107,852 / month, #12,591 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 3 - AlphaLicense :: OSI Approved :: MIT LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14 |
Evidence: trulens-2.13.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “agentic system evaluation”
- trulensTruLens instruments LLM applications to trace execution step-by-step,…
- trulens-coreInstruments LLM applications with OpenTelemetry-native tracing and…
- bfcl-evalEvaluates and benchmarks large language models' ability to invoke…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also judgeval · trulens-core · ragas · cleanlab-tlm · opik · lmnr · opentelemetry-instrumentation-llamaindex · opentelemetry-instrumentation-openai-agents · evidently · weave