Skip to content

UpTrain

Open-source toolkit with 20+ preset checks for grading LLM application outputs and a local dashboard.

By UpTrain · uptrain.ai

Package download activity

Each package is shown on its own; packages that can be installed together are never added up. Week 2026-W40 (2026-09-28 to 2026-10-04).

PyPIuptrain · headline (ranked)

423 downloads in the week, +46.4% vs prior week · rank 43 on PyPI

2026-W29: 3742026-W30: 3732026-W31: 2822026-W32: 6032026-W33: 4452026-W34: 3462026-W35: 5372026-W36: 2302026-W37: 2302026-W38: 3542026-W39: 2892026-W40: 423
2026-W29 to 2026-W40, 12 weeks; min 230, max 603

Reproduce this number (ClickHouse SQL) · registry metadata (mapping checked 2026-10-07)

GitHub stars

uptrain-ai/uptrain: 2,366 stars (rank 28). Stars are a point-in-time count of a repository's bookmarks, not people using the tool.

Series starts 2026-W40 (2,366).

Reproduce (GitHub API) · repository link source

Facts

Facts for UpTrain
CategoriesEvaluation
StatusGenerally available (no release since 2024-05 (checked 2026-10-07))
LicenceApache-2.0source, checked 2026-10-07
Self-hostYessource, checked 2026-10-07
OpenTelemetryUnknownsource, checked 2026-10-07
Pricing modelcontact
Entry priceContact sales; Open-source version free; README says 'We also have a managed version' via booking a call; no prices published; uptrain.ai/pricing returns 404source, checked 2026-10-07
Free tierYes
MeasurabilityMeasured (mapped SDK packages)

Facts last verified 2026-10-07 on first-party pages. Prices as published, taxes excluded; non-USD prices are not converted.

Compare

Spotted an outdated fact? The methodology page explains how facts are checked; corrections are applied at the next weekly build.