agentscope-ai/OpenJudge

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

50
/ 100
Established

This project helps AI application developers, machine learning engineers, and researchers assess and improve the quality of their AI agents or chatbots. It takes in test data and the AI application's responses, then provides objective quality scores and detailed feedback. The primary users are those building and refining AI-powered products.

459 stars.

Use this if you need a reliable way to systematically evaluate your AI application's performance, from general text quality to agent-specific behaviors like tool use, and want to easily integrate this into your development workflow for continuous optimization.

Not ideal if you are looking for a general-purpose analytics tool or a platform for evaluating traditional software applications, as its focus is specifically on AI application quality and optimization.

AI-application-development LLM-evaluation chatbot-testing agent-performance-tuning ML-quality-assurance
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 15 / 25

How are scores calculated?

Stars

459

Forks

37

Language

Python

License

Apache-2.0

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/agentscope-ai/OpenJudge"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.