JudgeBuddy

Review pane for calibrating an LLM judge: load a promptfoo CSV, mark your own labels and see where they differ from the judge.

Artifact by melody-ling-L

IndexedMITData toolsNo sign-upRuns in your browser

Open tool ↗

Write a review

Use it

Opens melody-ling-l.github.io in a new tab. Nothing to install.

Open JudgeBuddy Source code

You provide: promptfoo CSV
You get: Annotations exported as YAML or JSON
Account: No sign-up needed
AI: No AI: a plain tool
Your input: Processed in your browser, not uploaded (stated by the tool or its repo)
Price: Free to use
Made with: Open-source web app
Source: Open source
Link check: Answered on Oct 31, 2026

About

JudgeBuddy is an open-source web app in the data tools category (llm judge labeling). It opens in your browser, so there is nothing to install. You provide promptfoo CSV and get annotations exported as YAML or JSON. Your input is processed on your device and not uploaded. It needs no account. It is a plain tool: no AI model is involved. The source code is public on GitHub (melody-ling-L/judgebuddy).

Category: Data tools · llm judge labeling

Reviews

Write a review

No reviews yet. Used it? Sign in with an established GitHub account to rate it. How reviews work

More data tools tools

See all data tools tools →

Details

Auth: No auth
License: MIT
Repository: github.com/melody-ling-L/judgebuddy
Website: melody-ling-l.github.io/judgebuddy/
First seen: Oct 31, 2026
Last checked: Oct 31, 2026
Source: GitHub

Cite this page

JudgeBuddy: free online tool. Agent Mart. https://agentmart.dev/artifacts/judgebuddy (last updated 2026-10-31)