PrototypeCommon
open-compass/AgentCompass
[EMNLP 2026] AgentCompass is an extensible open-source evaluation infrastructure for systematically assessing LLM/VLM agent capabilities.
- Owner
- open-compass (organization)
- Stars
- Stars: 184
- Forks
- Forks: 38
- Language
- Python
- License
- Apache-2.0
- Created
- 2025
- Topics
- agentbenchmark-frameworkevaluation-frameworkharnessclaude-codecodex
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by open-compass
All 14 repos by open-compass- open-compass/opencompassStars: 7,559PythonStable
- open-compass/VLMEvalKitStars: 4,468PythonRC
- open-compass/MixtralKitStars: 767PythonBeta
- open-compass/LawBenchStars: 457PythonAlpha
- open-compass/T-EvalStars: 313PythonAlpha
- open-compass/MMBenchStars: 312Alpha
Nearby in Python
All Python repos- bayshier/voicestudio-zhStars: 184PythonPrototype
- HangYu8123/mini-harnessStars: 184PythonPrototype
- SC-10749/HotlineStars: 184PythonPrototype
- lexrupy/gmateStars: 184PythonPrototype
- bartTC/django-frontendadminStars: 184PythonPrototype
- simonw/geocodersStars: 184PythonPrototype