Open Issues Need Help
View All on GitHub Re-score an existing run from its JSONL logs about 3 hours ago
enhancement good first issue
Crash-test your voice agent: accents, bad lines, slang, interruptions. Same intent, many surface forms — does the agent still do the right thing?
Python
Mark expectations as advisory rather than blocking about 3 hours ago
enhancement good first issue
Crash-test your voice agent: accents, bad lines, slang, interruptions. Same intent, many surface forms — does the agent still do the right thing?
Python
Add a language to the example scenarios about 3 hours ago
help wanted good first issue
Crash-test your voice agent: accents, bad lines, slang, interruptions. Same intent, many surface forms — does the agent still do the right thing?
Python