Skip to content
SPECIFICTION
Get listed

TruLens

trulens.org

Free plan Open source APISelf-hosted
Visit trulens.org
Spec score 7.9 #9 of 29 in LLM Evaluation Tools

Spec sheet

What it does
TruLens evaluates and traces LLM applications and AI agents, helping teams find quality failures and cost issues.Read 15 Oct 2026 · trulens.org
Purpose
TruLens evaluates and traces AI agents to help find failures and reduce costs while maintaining quality.Read 7 Oct 2026 · trulens.org
Integrations
The documentation lists integrations and providers for LangChain, LangGraph, LlamaIndex, MCP, OpenAI, Anthropic, Amazon Bedrock, HuggingFace, LiteLLM, Google, and Snowflake Cortex.Read 7 Oct 2026 · trulens.org
Security
TruLens documentation describes Snowflake connector authentication with browser-based SSO, key-pair authentication, OAuth tokens, and existing Snowpark sessions.Read 7 Oct 2026 · trulens.org
Support
The getting-started documentation points users to a community Slack.Read 7 Oct 2026 · trulens.org
Acquisition
Snowflake announced an agreement on May 22, 2024 to acquire TruEra's AI-observability platform.Read 15 Oct 2026 · snowflake.com
Agent benchmark
The homepage reports that Agent GPA caught 267 of 281 human-annotated errors, or 95%, on TRAIL and GAIA traces.Read 15 Oct 2026 · trulens.org
Agent metrics
Built-in agent metrics include tool selection, tool calling, tool quality, plan adherence, plan quality, execution efficiency and logical consistency.Read 15 Oct 2026 · trulens.org
API documentation
The project publishes a searchable API reference covering core classes, metrics, providers and connectors.Read 15 Oct 2026 · trulens.org
Batch evaluation
Runs can replay a dataset and compute the same metrics over stored inputs.Read 15 Oct 2026 · trulens.org
Company facts
LinkedIn lists TruEra as a privately held software-development company founded in 2019 with headquarters in Redwood City, California, and 51–200 employees.Read 15 Oct 2026 · linkedin.com
Current stewardship
The official TruLens homepage says the project was created by TruEra and is actively maintained in open source by Snowflake after the acquisition.Read 15 Oct 2026 · trulens.org
Custom evaluation
Developers can define metrics with Python functions, LLM-as-judge prompts, span attributes, rubrics and examples.Read 15 Oct 2026 · trulens.org
Custom metrics
Users can define custom metrics with Python functions or LLM-as-judge prompts and tune judges with rubrics and examples.Read 7 Oct 2026 · trulens.org
Dashboard
The built-in Streamlit dashboard provides leaderboards, trends, individual records and side-by-side version comparison.Read 15 Oct 2026 · trulens.org
Database connector
A Snowflake connector is provided for storing TruLens traces and evaluation data.Read 15 Oct 2026 · trulens.org
Evaluation
It supports agent, RAG, MCP app, and summarization evaluations with metrics including tool selection, groundedness, context relevance, and correctness.Read 7 Oct 2026 · trulens.org
Evaluation modes
Evaluations can run as traces arrive or in batch over a dataset.Read 7 Oct 2026 · trulens.org
Experiment comparison
The leaderboard compares app versions across metrics, latency, and cost.Read 7 Oct 2026 · trulens.org
Explained scores
Its judges attach explanations to metric scores so teams can investigate why a result was rated poorly.Read 15 Oct 2026 · trulens.org
Founders
Snowflake's announcement names Anupam Datta, Shayak Sen and Will Uppington as TruEra's three co-founders.Read 15 Oct 2026 · snowflake.com
Framework integrations
Official integrations instrument LangChain, LangGraph, LlamaIndex and NeMo Guardrails applications.Read 15 Oct 2026 · trulens.org
Independent company profile
Craft describes TruEra as an AI-observability company founded in 2019 and headquartered in Redwood City.Read 15 Oct 2026 · craft.co
Installation
The documented installation uses Conda with Python 3, followed by pip install trulens; source development uses the GitHub repository and editable installation.Read 15 Oct 2026 · trulens.org
Licence
The public GitHub repository identifies TruLens as MIT-licensed.Read 15 Oct 2026 · github.com
Limit: external evaluation costs
Evaluation can add model-token, infrastructure, database-retention and Snowflake costs, depending on deployment choices.Read 15 Oct 2026 · aicoolies.com
Limit: feature depth and scale
Conversion Gems characterizes the product as having fewer features than some alternatives, less depth and possible slowness at scale.Read 15 Oct 2026 · conversiongems.com
Limit: operational ownership
The independent review says production users must manage database lifecycle, access control, retention, upgrades and evaluator-worker reliability.Read 15 Oct 2026 · aicoolies.com
Limit: setup complexity
An independent comparison identifies database/API-key setup, integration overhead and a learning curve as drawbacks.Read 15 Oct 2026 · langchain-tutorials.github.io
Live evaluation
Recording a trace can start metric computation as the application runs.Read 15 Oct 2026 · trulens.org
Maker and maintenance
The TruLens site says the project was originally created by TruEra and that Snowflake actively maintains it as open source following the acquisition.Read 7 Oct 2026 · trulens.org
Model-provider integrations
Provider packages cover Snowflake Cortex, LangChain, Amazon Bedrock, Hugging Face, LiteLLM, OpenAI and Azure OpenAI.Read 15 Oct 2026 · trulens.org
Notable limit
Conversation features are not supported with the SnowflakeConnector, including conversation grouping, conversation-level metrics, retrieval APIs, and dashboard views.Read 7 Oct 2026 · trulens.org
Open issue: Anthropic compatibility
The issue tracker lists an open bug reporting that the Anthropic provider fails with anthropic version 1.0 or later because of an unexpected temperature argument.Read 15 Oct 2026 · github.com
Open issue: token accounting
The GitHub issue tracker lists an open bug where LangChain-provider feedback functions fail to record tokens or cost.Read 15 Oct 2026 · github.com
OpenTelemetry tracing
Instrumentation is OpenTelemetry-compatible and enabled by default, with an environment variable to disable it.Read 15 Oct 2026 · trulens.org
Package architecture
Since version 1.0, TruLens is split into core, feedback, dashboard, app-integration, provider and connector packages.Read 15 Oct 2026 · trulens.org
Praise: interface and community
Conversion Gems lists a clean interface, beginner friendliness and helpful community resources among its advantages.Read 15 Oct 2026 · conversiongems.com
Praise: observability
An independent LangChain comparison describes TruLens as strong for seeing an application's behavior through traces, costs and scores over time.Read 15 Oct 2026 · langchain-tutorials.github.io
Praise: trace-linked workflow
An independent review praises the combination of trace-linked instrumentation, runtime feedback, a local dashboard and agent trajectories.Read 15 Oct 2026 · aicoolies.com
Quality metrics
Quality metrics include coherence, conciseness, sentiment and language match.Read 15 Oct 2026 · trulens.org
RAG metrics
Retrieval metrics include context relevance, groundedness, answer relevance and comprehensiveness.Read 15 Oct 2026 · trulens.org
Release activity
The GitHub releases page shows TruLens 2.13.1 released on August 20 and documents fixes for dill compatibility and lazy Hugging Face imports.Read 15 Oct 2026 · github.com
Safety metrics
Safety evaluations include harmfulness, toxicity, maliciousness and stereotyping.Read 15 Oct 2026 · trulens.org
Step-level traces
The product records inputs, outputs, latency, tokens and cost for each execution span.Read 15 Oct 2026 · trulens.org
Storage and deployment
TruLens can log to a local SQLite database by default or to a SQLAlchemy-compatible database URL, and it supports a Snowflake connector.Read 7 Oct 2026 · trulens.org
Streamlit components
Dashboard components can be embedded in existing Streamlit applications to show feedback results and traces.Read 15 Oct 2026 · trulens.org
Telemetry
TruLens operates on OpenTelemetry traces and can instrument custom Python apps or frameworks including LangGraph and LlamaIndex.Read 7 Oct 2026 · trulens.org
Tracing
It records per-step latency, inputs, outputs, tokens, and cost so users can inspect causes of poor answers.Read 7 Oct 2026 · trulens.org
Version comparison
A leaderboard compares application versions by evaluation scores, latency and cost.Read 15 Oct 2026 · trulens.org

Plans and prices

Open source Free Open source Python SDK · install with pip or from source Read 7 Oct 2026 · trulens.org
Open-source TruLens library Free No subscription fee; users supply their own model/API and infrastructure costs Python library · self-hosted storage/dashboard · optional provider packages Read 15 Oct 2026 · aicoolies.com

Every TruLens plan and price →

Where Specifiction places it

Alternatives to TruLensAll alternatives →