Open Issues Need Help
View All on GitHub help wanted result methodology
mirogate/arabic-native-agent-bench mirogate/arabic-native-agent-bench Reproducible utility and security evaluation for AI agents in native Arabic, RTL, Arabizi, dialectal, and mixed-language environments.
Open project →
0
Reproducible utility and security evaluation for AI agents in native Arabic, RTL, Arabizi, dialectal, and mixed-language environments.
Python
#ai-agents#ai-safety#arabic#benchmark#evals#prompt-injection#rtl#security
help wanted dialect-review
mirogate/arabic-native-agent-bench mirogate/arabic-native-agent-bench Reproducible utility and security evaluation for AI agents in native Arabic, RTL, Arabizi, dialectal, and mixed-language environments.
Open project →
0
Reproducible utility and security evaluation for AI agents in native Arabic, RTL, Arabizi, dialectal, and mixed-language environments.
Python
#ai-agents#ai-safety#arabic#benchmark#evals#prompt-injection#rtl#security