@zagents/darwin
MITAn LLM supercharger and cost optimizer: freeze the model class, evolve the gemini. Measured on full SWE-bench Lite (300, official swebench Docker): 7.7% open-loop -> 15.3% +repair -> 29.3% (deepseek-v4-pro base) -> 40.3% v4-pro+frontier-tail hybrid, ~$0.0
100
Security score
0 known advisories in v0.2.6
Weekly downloads
—
Unpacked size
422.7 kB
Dependencies
0
Last publish
1 month ago
Security advisories
No known vulnerabilities affect v0.2.6.