DSH插件商店

dsh-memory

FuRongJun-1999

白箱AGI架构探索：元认知（自我认知循环）、持续学习（知识飞轮）、世界模型（条件空间+语义时空图）、自我改进（自举纪律）、零LLM白箱管线与可审计信任护栏。

dsh-argp

yoza10635

Guarded context compaction for DeepSeek Harness (dsh): the LLM proposes, deterministic guards dispose — eager per-atom shrink (extract/summary/false under verbatim guards) + lazy reference-graph eviction (0-LLM) + byte-exact recall from an append-only log. 守卫式上下文压缩：LLM 只提议、确定性守卫裁决——逐原子缩放 + 惰性引用图剪枝（0-LLM）+ 追加式日志逐字节召回；压缩率精确兑现，历史永不销毁。

dsh-anchored-standard-plus

54xkeee

DeepSeek Harness agent preset: fixes DeepSeek V4 Pro degradation (降智) via RL first-request anchoring — bash+str_replace_editor bootstrap, resident plugin tools, per-turn format guard

dsh-fork-inbox-guard

azazo1

DSH host plugin: drop the pending prompts a fork inherits, so a fork child answers the prompt you send it instead of the source session's queue.

dsh-stall-guard

akira399

DeepSeek Harness watchdog plugin: detects truly stalled agent turns (never killing in-progress tasks — in-flight operations are exempt), nudges/terminates only on real silence, records every event to JSONL with a loopback status route

agent-loop-workflow

LeslieWylie

A project-agnostic multi-agent collaboration protocol for the DeepSeek Harness: loop guards that stop runaway agent loops, a six-field handoff format, risk-tiered review routing, and a fixed verify→commit→push→review→close sequence. One skill instead of the same rules copy-pasted into every agent's instructions.

dsh-memory-pack

yehuioc

File-based layered memory skill pack for DeepSeek Harness and skill-driven agent runtimes: 11-layer directory model, Maps-first navigation, producer/review metadata contract, contamination guard, zero-dep scaffold/audit scripts.

dsh-loop-guard

MyRemme

多智能体监工：一个独立模型实时审阅推理文本与工具调用，检测死循环 / 空转 / 偷懒，并按 WARN / BLOCK / STOP 三档落地。DSH 宿主插件 + 浏览器设置界面。

dsh-captain-guard

xyzzing

该仓库暂未提供项目说明。