BiBoyang/dsh-eval-harness

DSH plug-in evaluation tool: YAML use case driven real agent regression evaluation + baseline comparison PASS/WARN/FAIL access control｜Regression eval harness for DeepSeek Harness

Agent Capabilities ★ 5 updated — — untested

View on GitHub ↗

Install

dsh plugin --profile web add github:BiBoyang/dsh-eval-harness

Details

Repo: BiBoyang/dsh-eval-harness
Category: Agent Capabilities
Stars: 5
Last push: —
First seen: —