← back to the directory
Library / SDK Observability & Evaluation

Deepchecks

1Test 2and 3validate 4ML 5and 6LLMs.

the six Ws · specification

W1 Who

By Deepchecks.

W2 What

A suite for testing data and models, including LLM evaluation.

W3 Where

A Python library, plus optional hosted app.

W4 When

From research through production monitoring.

W5 Why

Continuous validation across the ML lifecycle.

W6 With

Python and your datasets.

W7 Watch

Open-source core (AGPL) with a commercial tier; runs on your data locally.

TestingValidationML

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.