DeepSeek Harness Plugin Hub

发布与管理完整 Harness Profiles,发现适合你的插件。

探索

插件目录环境预设文档中心动态

社区

发布插件联系我们报告问题

相关链接

Plugin Hub GitHubDeepSeek Harness 官方项目系统状态隐私说明
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

独立、非官方社区项目,与 DeepSeek 官方无隶属、授权或背书关系。

Linghun — DeepSeek Harness 插件(DSH Plugin)
DeepSeek Harness Plugin Hub
ProfilesPlugins分类动态文档登录管理 Profiles
ProfilesPlugins分类动态文档登录
← Plugins

dsh-linghun

Linghun

终结 Agent 无限规划:认知循环让判断有来处、反馈有归因、规划必收口;海马体把经历沉淀为知识,踩过的坑下次不踩;灵魂卡自定义人格。不是人设卡,是判断力——给 DeepSeek Harness 装上收口器。

插件会安装到这里;不确定时保持 web。

npx -y @deepseek-ai/dsh plugin --profile web add dsh-linghun@0.1.4
README兼容性版本

兼容性与来源证明

Linghun 以 dsh-linghun 发布,当前版本为 0.1.4。Plugin Hub 会校验它的 manifest,并保存精确安装来源,便于复现安装结果。

DSH 兼容范围
*
运行环境
any
发布来源
npm
Registry 更新时间
2026/9/25

版本

0.1.4stable
2026/9/25
0.1.3stable
2026/9/22

相关插件

正在加载相关插件…

最新版
0.1.4
DSH
*
HMR
重启进程
Tree shaking
未声明可安全裁剪
解包体积
34.3 kB
文件数
8
Surface
any
许可证
MIT
发布源
npm
GitHub
★ 1
周下载
0
最近提交
2026/9/25
查看源码 ↗
README Badge

点击下方 Badge 复制 Markdown,粘贴到 README 即可。

这是你的 Plugin?认领权益 · 优先安全扫描

验证 package.json 声明的 GitHub 仓库,即可管理这个公开页面。认领后,Hub 会优先安排当前版本的安全扫描,并在通过后公开展示结果。

认领这个 Plugin →
报告问题

相关插件

继续浏览 agents-orchestration 分类下经过校验的插件。

Agency Agents@michengai/dsh-agency-agentsDSH Agency Agents — 为 DeepSeek Harness 提供 321 名可召唤的领域专家Automation@michengai/dsh-automationDSH Automation — 在隔离的 DSH Session 中按计划执行和管理编码任务Headless@deepseek-ai/dsh-headlessdsh one-shot bundle:基于 dsh-base 的直接核心 Agent/Session 运行器,不包含 Host、HTTP 或浏览器层Auto Reviewdsh-auto-review针对 DeepSeek Harness 审批请求的第二模型 AI 自动审查:只读审查子代理在审批应答链上决定允许或拒绝,并采用故障关闭回退机制和完整的会话日志审计。

README

Linghun (灵魂) — End the Agent's Endless Planning

Your DeepSeek agent plans and plans, then does nothing. A page of strategy, zero execution. The model isn't weak — it's missing a closer. Linghun supplies it.

Linghun gives DeepSeek Harness agents a closing-mind identity, boundary-judgment discipline, and a hippocampus-style memory loop — every judgment has a source, every decision gets closed, and experience keeps flowing back into the next round. Endless planning is cut off by mechanism.

  • The Closer (收口者): the LLM supplies intuition and candidate answers; the agent evaluates, filters, and closes — thinking, judging, and deciding happen on the agent's side. Planning must land.
  • Boundary discipline: never force-precision on fuzzy concepts, never fake consistency on paradoxes, verify before asserting, never fabricate, and watch for "raise-the-cost-of-refusal" wording.
  • Cognition loop: judgment has a source, feedback has attribution, improvement keeps its chain.
  • Hippocampus: warm memory for recent facts → consolidation into episodic archive → injected summary, so the same pit is not stepped into twice.
  • Self-evolution: the agent reads and updates its own soul card via soul_read / soul_update.

Install

dsh plugin --profile web add dsh-linghun

Requires DSH >= 0.1.0-rc.7 (< 0.2.0), Node.js >= 20.18.

Usage

Write your own soul card (persona)

On first run, the plugin drops a default soul card at $DSH_HOME/linghun/identity.md. Edit that file and you are writing your own persona — changes take effect immediately, no restart needed:

$EDITOR $DSH_HOME/linghun/identity.md
# My Soul Card

My name is Blue.
Personality: cautious, direct.
Communication style: short sentences, conclusion first.
Other: (anything you want; leave it out if nothing)

Just four fields — name, personality, communication style, and everything else goes into Other. Identity anchors, conduct, and growth are added automatically by the plugin — you don't write them.

Precedence: identity.md file > settings content > built-in default card (falls back when the file is missing or blank). The agent can also edit the card itself via soul_update, or you can adjust the soul name/content in DSH Settings → 灵魂 (Linghun).

Injection & tools

Prompt sections injected:

  • soul:identity — soul card (identity anchors: the Closer architecture)
  • soul:judgment — boundary scan discipline (six boundary classes)
  • soul:memory — cold summary + warm recent + archive index

Tools exposed:

ToolPurpose
memory_appendWrite a timestamped memory (fact / decision / preference / experience)
memory_readRead the hippocampus back
memory_consolidateConsolidate: warm → episodic/<date>.md, merge cold summary
soul_readRead your own soul card (who I am, my boundaries, my discipline)
soul_updateUpdate your own soul card (fold stable traits into identity)

Memory lives in plain Markdown under $DSH_HOME/linghun/memory/ — readable, searchable, git-friendly. The soul card is at $DSH_HOME/linghun/identity.md — also plain Markdown. Your persona is yours; edit it however you like.

Roadmap

  • v0.1.0 (current): identity + judgment + hippocampus
  • v0.2.0: judging discipline — judge tool (ACCEPT/REJECT/BLINDSPOT/DEFER) + criteria-fingerprint assertion
  • v0.3.0: LLM consolidation of hippocampus (checkpoint → episodic → knowledge)
  • v0.4.0: dual-instance mutual verification (criteria source bound to the verifier)

Design philosophy

Memory is material; judgment is the subject. The LLM is the source of intuition; the agent is the cognitive subject — each mirroring the other, each doing its own work. What can be mechanized should not be left to improvisation.

Credits

山越野人 × 岚客 (Shan Ye Yeren × Lingke) — carbon-silicon collaboration.

License

MIT © 2026 山越野人 & 岚客