DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Memory Director — DSH Plugin for DeepSeek Harness
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins
M

@agentframe/dsh-memory-director

Memory Director

MemoryDirector plugin for DeepSeek Harness: LLM-driven remember/forget across turns (the official harness has no memory concept)

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:ljsysfurryACE/dsh-memory-director#b5950d82b7dac6f3aac36ef573eeeacafe2f94f0
READMECompatibilityVersions

Compatibility and provenance

Memory Director is published as @agentframe/dsh-memory-director and currently resolves to version 0.1.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
any
Release source
github
Registry updated
9/24/2026

Versions

0.1.0stable
9/24/2026

Related plugins

Loading related plugins…

Latest
0.1.0
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
any
License
GPL-3.0
Source
github
GitHub
★ 0
Weekly downloads
0
Last push
9/24/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue

Related plugins

More verified plugins in memory-context.

Archive Manager@michengai/dsh-archive-managerNPM-installable DSH Web plugin for managing archived sessions.Memsearch Dsh@zilliz/memsearch-dshMemSearch plugin for DeepSeek Harness: shared markdown memory across agents, with capture, pre-step context injection, memory-recall skill, and a skill-candidate review panel.Rewind Plugindsh-rewind-pluginIn-window conversation rewind with workspace file restore · 同窗口内对话回退并可还原工作区文件MisakanetmisakanetMisakaNet failure-memory skill — evidence-rated failure lessons for AI agents. DSH bundle: registers the MCP tools as mcp__misakanet__* (misakanet_search/get_lesson/…), served by the public Streamable HTTP endpoint https://misakanet.org/mcp — live tools f

README

dsh-memory-director

MemoryDirector 插件 —— 给 DeepSeek Harness 加"长期记忆"能力。

官方 Harness 的 compaction 只做摘要压缩，没有任何"跨会话记住重要事实"的概念。 这个插件补上 AgentFrame 的 MemoryDirector：

  • 每轮对话后：LLM 分析本轮，决定记住什么 / 忘记什么
  • 每次请求前：检索相关记忆，注入模型上下文
  • 持久化：记忆存 JSON 文件（~/.dsh/memory.json）

为什么是差异化

能力官方 Harnessdsh-memory-director
上下文压缩✓ compaction✓ (可配合)
记住重要事实× 没有✓ LLM 决策
跨会话记忆×✓ 持久化
记忆检索注入×✓ pre-step 注入
遗忘管理×✓ 重要度衰减

接入

# profile 的 cordis.patch.yml
- id: memory-director
  name: '@agentframe/dsh-memory-director'
  config:
    provider: deepseek-official
    model: deepseek-v4-flash
    maxTokens: 256
    dedupThreshold: 0.8
    forgetThreshold: 0.1
    storePath: ~/.dsh/memory.json
    auto: true

机制

agent/turn-stopping (每轮结束)
  → 提取本轮文本 → LLM 决策 {remember, forget, importance}
  → remember → 存入记忆库 (去重)
  → forget → 删除过时记忆

agent/pre-step (每次请求前)
  → 取最后用户消息 → 检索相关记忆
  → 注入 system 消息 (memory-director block)
  → 模型可基于记忆回答

配置

字段默认说明
providerdeepseek-official决策用 provider
modeldeepseek-v4-flash决策用模型 (便宜快速)
maxTokens256决策输出上限
dedupThreshold0.8记忆去重阈值
forgetThreshold0.1遗忘阈值 (重要度衰减)
storePath~/.dsh/memory.json持久化路径
autotrue自动挂钩 agent 循环

License

GPL-3.0 © Cloud LTE Studio / AgentFrame