GitHub · Python
open-compass/AgentCompass
[EMNLP 2026] AgentCompass is an extensible open-source evaluation infrastructure for systematically assessing LLM/VLM agent capabilities.
- Stars
- 197
- Forks
- 49
- Stars gained in 24 hours
- +1
- Forks gained in 24 hours
- +2
Topics: agent, benchmark-framework, claude-code, codex, evaluation-framework, harness
Latest data point: Nov 20, 2026 · 197 stars · 49 forks