OpenJudge

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

LLM Mart
15 views 203 listing impressions
0 Visit tool
agent-skills

OpenJudge is an open-source AI evaluation and quality reward framework. It provides over 50 production-grade graders. It integrates with LangSmith and Langfuse for full-stack monitoring.

It supports VERL and other RL training frameworks, converting evaluation results into reward signals. It is available under the Apache 2.0 license.

Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.

Comments (0)

Sign in to join the conversation.

No comments yet.

Related tools

Open Science
The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and…
Clipcat Skill
TikTok e-commerce video generation, replication, and analysis SKILL
Capcut Cli
Independent, unofficial CLI to edit CapCut and JianYing (剪映) projects — subtitles, timing, speed, volume, templates, cut long-form to shorts. No API needed, rea…
Cli
Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. I…