# evidentlyai/evidently

Evidently is ​​an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.

Repository: https://github.com/evidentlyai/evidently
Canonical: https://ross.abutalabs.com/products/evidently
Homepage: https://discord.gg/xZjKRaNp8b
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: data-drift, jupyter-notebook, pandas-dataframe, machine-learning, model-monitoring, html-report, mlops, data-science, hacktoberfest, data-quality, data-validation, generative-ai, llm, llmops
Last push: 2026-08-05T16:29:57+00:00

## Health v2 (maintenance only)
Score: 89/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 96, release rhythm 74, longevity 100
- inputs: {"age_days": 2107, "days_push": 28, "days_rel": 176, "gap_med": 12, "n_releases_24m": 36}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7849, forks 901 (observed 2026-08-28T04:10:07.391052+00:00)

## What it is
Evidently is an open-source Python framework for evaluating, testing, and monitoring ML and LLM-powered systems, with 100+ built-in metrics from data drift detection to LLM judges. It supports one-off reports, pass/fail test suites for CI/CD, and a self-hostable monitoring dashboard service.

## Use cases
- detect data drift in production ML models
- evaluate LLM and RAG pipeline quality
- run data validation checks in CI/CD
- monitor model performance over time with a dashboard
- generate HTML reports for ML experiments
- test tabular and text data quality
- set up regression tests for ML models

## When to choose
- you need to evaluate or monitor ML models or LLM apps in Python
- you want drift detection, data quality, and LLM evals in one framework
- you need pass/fail test suites for ML pipelines in CI/CD
- you want a self-hostable monitoring UI for model metrics

## When to avoid
- you need a fully managed no-code monitoring platform (consider Evidently Cloud or alternatives)
- you only need generic application observability like logs and traces rather than ML-specific evals
- you work outside the Python/pandas ecosystem

## Facets
- artifact type: library
- maturity: active
- function: monitoring, testing, data-science, machine-learning, llm-inference, rag, data-visualization, analytics
- domain: machine-learning, data-science, large-language-models, developer-tools
- platform: python, cli, self-hosted, cross-platform
- tags: mlops, llmops, data-drift, model-monitoring, data-quality, data-validation, llm-evaluation, jupyter-notebook, html-reports, test-suites, data-engineering

## Member repositories
- evidentlyai/evidently (main) score 89

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:07.391052+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:33:49.549506+00:00, confidence not recorded.
  - readme: https://github.com/evidentlyai/evidently (fetched 2026-08-28T04:10:07.391052+00:00, sha b3e3e7c2b653)
  - homepage: https://discord.gg/xZjKRaNp8b (fetched 2026-08-29T08:30:24.775240+00:00, sha 59b6f75a027f)
  - registry_pypi: https://pypi.org/pypi/evidently/json (fetched 2026-08-29T08:30:24.784528+00:00, sha 26c536205243)
- Data as of 2026-08-30T08:39:29.467469+00:00.