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。
351 个项目，匹配「agent」
Co-Engram
Self-evolving team memory
Soulize
A DeepSeek Harness (dsh) agent preset for making large engineering tasks deliberate, integrated, and verifiable from the first turn.
dongsheng123132
Open task handoff protocol for DeepSeek Harness, WorkBuddy, Claude Code and Codex — verified state, not chat logs
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。
lincong1987
dsh plugin: flexible model switch for sub‑agent & plan execution. 为子代理和计划执行选择更合适的模型。
yangdcm
Role-based multi-agent expert team for DeepSeek Harness: one sentence in, a staged and gated team delivery out. 12 role subagents, 9 gated phases, shared-workspace artifacts, zero runtime dependencies.
Altairpaca
Evidence-backed, explainable multi-model routing for DeepSeek Harness — policy resolution, provenance, and compatibility boundaries.
chenzheshushi-commits
Self-evolving memory + skill lifecycle for DeepSeek Harness — durable cross-session memory with zero-token deterministic recall, tiered approval, reinforcement learning from repetition, and anti-bloat convergence for both skills and memory.
isheng-eqi
Hermes-style persistent memory (MEMORY.md / USER.md) for DeepSeek Harness (DSH) — a faithful port of hermes-agent MemoryStore: bounded, file-backed, model-curated, frozen-snapshot injection.
jasen215
DeepSeek Harness (DSH) plugin for self-improving AI agents: continual learning, persistent memory, cross-session knowledge, review-and-refine workflows, and automatic rollback.
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。
Culeot
Cross-session long-term memory plugin for DeepSeek Harness (DSH)
benz-ai-x
DSH Research Graph · 研图 — DeepSeek Harness plugin for research topics, traceable knowledge cards, and reusable AI discussions.
gezi-wen
File-based cross-session memory for DeepSeek Harness (DSH) — every memory is a plain Markdown file. 纯 Markdown 存储，无数据库、无 worker、无端口；从 Claude Code 无损迁移记忆与人格，带记忆星图与可选的记忆整理。
tianyaojiudi-prog
DSH(DeepSeek Harness) 插件：把一段可在设置页随时改写的文字，作为全局系统提示词段注入到所有会话，含子代理与工作流内部子代理；文本与开关即时生效，无需重启。
unknowbug
Modular engineering methodology framework for AI agents — reverse engineering & software development (core + re-binary / re-code / swe modules).
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
zhujunpeng12
Local-first persistent memory infrastructure for DeepSeek Harness: hot bootstrap, Chinese-BM25 cold recall, lease-lock transactional writes, read-only governance
Cavan-Ou
Battle-tested multi-agent collaboration playbook for DeepSeek Harness: model-tier routing, spec discipline, git single-writer rule — as an installable skill. 多 agent 管线里运行 DSH 的实战协作规范
Noelune
Unified fleet-wide agent memory system for DeepSeek Harness — shared Obsidian Vault for dsh, Codex, Claude Code & Hermes with dependency-free Python FTS5 core.
PwnKY
DeepSeek Harness 的 Codex 式会话深度链接插件：dsh:// 深链，跨对话读取上下文
Tianbuyu-wwx
Bidirectional bridge between Hermes Agent and DeepSeek Harness (DSH). v0.2.4 — single-bundle Cordis plugin replacing the archived hermes-foundation/-oneshot-arbitrate/-dispatch-bridge triad.
Tikzen
Interactive multi-agent collaboration, meetings, group chats, and task execution for DeepSeek Harness.
ZekaiShi
Unified DeepSeek Harness plugin: role-based subagent routing + per-agent evolution (prefercmd/memory as knowledge allow/deny lists), so repeated tasks start from proven commands and save tokens. Unified subagent routing and evolution: prefercmd/memory serve as knowledge allow/deny lists, saving tokens.