플러그인

분리된 Git 워크트리에서 결정론적 검증, 점수화 및 명시적인 승자 적용을 통해 코딩 에이전트를 비교합니다.

Run the same prompt through every model you have, and see the difference without squinting.

Evidence-first multi-model coding comparison workbench for DeepSeek Harness

Evidence-backed Skill self-evolution for DeepSeek Harness: redacted trajectory learning, quarantined proposals, arena validation, canary monitoring, automatic rollback.