dshai.org
EN
Submit a plugin
Back to all plugins

dsh-eval

@hccccc01333

About

Agent evaluation platform for DeepSeek Harness: benchmark YAML, headless dsh orchestration, trace-based metrics, LLM judge, paired A/B, keyless replay, and cross-harness import.

Description collected from the plugin's own repository or package metadata.

Install

terminal 
npx @deepseek-ai/dsh plugin add dsh-eval
Adds the package and lets the kernel resolve what it injects.

Topics

agent-evaluationbenchmarkdsheval

Similar plugins

visionpower

@piercehuang663

VisionPower: a portable image understanding MCP server for Codex, Claude Desktop, Cursor, and other agents.

MediaModels
858 npm

inkstone

@banlanzs

Experimental

Browse and manage conversation history from Claude Code, Codex CLI, OpenCode, Reasonix, Oh My PI (omp), Pi, and DeepSeek Harness (dsh)

ModelsTerminal
364 npm

dsh-vision

@237229953-create

DSH plugin: text-only models (e.g. DeepSeek-V4) automatically see images via a vision model. Official surface-replace, cache-friendly, human transcript untouched. Text-only model automatic image recognition bridge