DSH插件商店

dsh-project-memory

luoyuejun9

Evidence-backed, human-approved project memory for DeepSeek Harness

dsh-workstate

luoyuejun9

Structured work-state checkpoints and safe agent handoffs for DeepSeek Harness

dsh-swarm-router

r600a-code

DSH plugin: sub-agent matrix swarm — routes heterogeneous tasks to the most suitable model (OpenRouter-like + cfgpu.com/llm/square), dispatches each via in-process subagents. 32/32 benchmark green.

dsh-openclaw-persona

AskingTheHeavens

DSH profile bundle: load OpenClaw-style persona files (SOUL.md, IDENTITY.md, USER.md, TOOLS.md, MEMORY.md, AGENTS.md, HEARTBEAT.md, memory/*.md) into every DSH session whose workspace contains an openclaw/ subdirectory.

knotline

MrMaii

把 Agent 从对话框搬到一张图上——连线即执行 / Orchestrate AI agents by drawing lines

dsh-memory-hermes

SipengXie2024

Hermes-style bounded memory + self-curating skill library for DeepSeek Harness (dsh): two-file curated memory, background review loop, LLM library curator. Out-of-tree Cordis plugin.

dsh-rewind

SipengXie2024

Claude Code-style rewind for DeepSeek Harness (dsh): edit a past user message and re-run on a forked session, restore files to the turn boundary, or branch with a summary

dsh-review

Viger1

Packaged multi-agent adversarial code review for DeepSeek Harness — parallel finders, then a verifier per finding, so only confirmed defects survive.

challenge-project-methodology

hlxstc-create

A battle-tested methodology for high-difficulty AI-agent projects: grading gates, evidence-driven verification & self-evolution. OpenClaw & DSH versions.

dsh-subagent-effort

shijunan126-creator

DeepSeek Harness plugin: subagents with their own model & reasoning effort — GUI settings card + subagent_select tool