llm-evaluation 4

oh-my-knowledge v0.54.0 Đã xác minh 23

OMK — Observe. Measure. Know. Evidence-backed knowledge changes for AI applications.

dsh plugin add oh-my-knowledge
dsh-replay-lab v0.1.6 Đã xác minh Giao diện web 1

Replay real DeepSeek Harness turns against Standard, Minimal, Anchored, or plugin candidates with frozen request-surface evidence

dsh plugin add @webwalkerhq/dsh-replay-lab
dsh-plugin-abtest v0.1.0 Đã xác minh

Paired experiments and promotion gates for DSH plugins.

dsh plugin add dsh-plugin-abtest
dsh-model-pk v0.1.3 Đã xác minh Giao diện web

PK 2-10 models on the same prompt, files, and tools in DeepSeek Harness.

dsh plugin add @yuanyang749/dsh-model-pk