azank1/cdv

View on GitHub ↗

Conservative Dual-Verify — judging AI agent work with a deterministic floor + LLM critic (stricter score wins) and Bayesian stopping. Research preview, frozen at v1.0.1; active development continues privately. MIT.

4 ★0 forksPythonUpdated 1mo ago

Topics

agentic-codingai-agentsclaude-codecode-reviewcursorllmmcpmodel-context-protocolverificationvscode-extension
Stars
4★
Forks
0
Language
Python
License
MIT
Created
2026-02-19
Last push
2026-08-04