A self-improving loop for voice AI agents. Uses karpathy's autoresearch as foundation.
-
Updated
Mar 18, 2026 - Python
A self-improving loop for voice AI agents. Uses karpathy's autoresearch as foundation.
Evaluate and improve voice AI agents with adversarial callers, keep/revert prompt loops, and overnight self-tests across Vapi, Smallest AI, and ElevenLabs
Optimize AI agents autonomously by iterating code changes and evals to improve performance using LangSmith observability and automated experiments.
Add a description, image, and links to the system-prompt-optimization topic page so that developers can more easily learn about it.
To associate your repository with the system-prompt-optimization topic, visit your repo's landing page and select "manage topics."