DSH-PLUGIN STORE / LIVE CATALOG
聚合 GitHub 上的 DSH 插件，打造 DeepSeek Harness 生态的一站式目录。
113 个项目，匹配「omp」
rinDBeans
DeepSeek V4 Pro/Flash unified anchored agent preset for DeepSeek Harness (official API & opencode-go): two-stage RL-aligned bootstrap, model-aware path routing, epoch-aware long-session stability
Soulize
A DeepSeek Harness (dsh) agent preset for making large engineering tasks deliberate, integrated, and verifiable from the first turn.
dsh-plugins
Auxiliary models for DeepSeek Harness: vision understanding and context compression through dedicated model routes. DeepSeek Harness 辅助模型插件：为视觉理解、上下文压缩、审批审查、子代理、会话标题与图片生成提供独立的模型路由、工具与系统提示，全程不触碰主对话模型。
falling-ts
Aggressive context compaction for local-first agents. Runs Qwen3.8‑27B on self‑hosted llama.cpp at low context, shrinking history so the live prompt stays small, fast, and private—delivering a big‑window experience without API cost or data egress. 面向本地的激进上下文压缩插件。自托管 llama.cpp 低上下文运行 Qwen3.8‑27B,不断收缩历史、保持常驻 prompt 小而快,兼顾隐私与大窗口体验,零 API 成本、数据不出本机。
Altairpaca
Evidence-backed, explainable multi-model routing for DeepSeek Harness — policy resolution, provenance, and compatibility boundaries.
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。
yyyy231209
Company Is a Word. 一句话开一家AI公司 - open-source multi-agent orchestration framework for non-developers. 小白5分钟拥有自己的AI公司，可DIY任意行业、调教子Agent、无限家公司，支持飞书遥控。MIT
polaris-smart
Turn your devices into a fleet — dsh plugin for decentralized multi-device collaboration: mDNS discovery, key pairing, SSH direct exec. Tools auto-register for dsh agents.
yindf
Context folding for DeepSeek Harness (DSH): wrap work in named tasks, fold finished spans into short summaries, recall originals on demand.
SaiSenBox
Session-level multi-prompt library and system prompt injector for DeepSeek Harness Web
Tikzen
Interactive multi-agent collaboration, meetings, group chats, and task execution for DeepSeek Harness.
Context Assembler DSH — DeepSeek Harness 上下文汇编插件：按话题块编排上下文，最大化每 token 互信息密度
lifeodyssey
DeepSeek Harness plugin: compress tool output, cut up to 20% of context, without touching the context cache or agent performance.
rongxingda
Prompt enhancement plugin for the DeepSeek Harness web GUI: one-click rewrite of the composer draft into a structured prompt, with preview, fill-back, and undo.
zhang-jiazhi
将原作者 linshenkx 的 prompt-optimizer 移植到 DeepSeek Harness 的第三方插件（非官方）
Ottohere-Mourn
Teach once, replay anywhere — harness-agnostic Teach-by-Demonstration engine (Record → Compile → Replay → Verify) with OpenMausBot and DeepSeek Harness integrations.
joekytc
Run multi-agent task pipelines on DSH like a team — plan, execute, review, and deliver code through a visual kanban with provable completion.
wjxn13
Headroom context-compression proxy integration for DeepSeek Harness: detect/install/start Headroom, auto-configure the DeepSeek compressed route, one-click route-switch UI. Built on headroomlabs-ai/headroom (Apache-2.0).
1420079678-ctrl
Organ-based agent plugin platform for DeepSeek Harness: 23 organs, nerve impulses, a heartbeat, reflex arcs that fire with zero model calls, sleep-time memory consolidation and closed-loop self-healing. On-demand tool schema gating cuts prompt tokens by 82%.
FuqiangCraft
Desktop companion plugin and native shell for DeepSeek Harness (DSH)
JoukoPuro
一个 DeepSeek Harness（DSH）插件： 在 Web 输入框的工具行中添加一个 ✨ 图标按钮。点击后选择打磨风格，已接入的大模型 会把你草稿中的提示词改写得更专业、更易被 AI 理解 。A DeepSeek Harness plugin: icon-only composer button that rewrites your prompt via the connected LLM (balanced/concise/detailed/code styles, i18n)
MichengAI
DSH PUA — 为 DeepSeek Harness 提供 PUA 任务推进、角色风味、验收循环和运行状态卡片 · PUA task persistence, personas, verification loops, and live status cards for DeepSeek Harness
MimicHunterZ
DSH plugin for agent-driven span compaction: compress chosen conversation spans into self-written checkpoints instead of the official head-anchored full-context sweep.
Nana7mi0721
让LLM模型将描述转化为用于ANIMA模型的自然语言提示词
