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.

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

dsh-layered-memory

Layered Memory

L0~L3 hierarchical distillation memory plugin for DeepSeek Harness: automatically captures conversations (L0), extracts atomic memories (L1), integrates scenario blocks (L2), distills core profiles/team methodologies (L3), and automatically recalls and injects them before model steps. Ported from th

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

npx -y @deepseek-ai/dsh plugin --profile web add github:JunNanLYS/dsh-layered-memory#69028fbee43e9950fffecc578430909fc827527e
对话界面实录(浅色主题):用户消息

Description

L0~L3 hierarchical distillation memory plugin for DeepSeek Harness: automatically captures conversations (L0), extracts atomic memories (L1), integrates scenario blocks (L2), distills core profiles/team methodologies (L3), and automatically recalls and injects them before model steps. Ported from the pipeline design of MemoryCore (TencentDB Agent Memory).

Compatibility and provenance

Layered Memory is published as dsh-layered-memory and currently resolves to version 0.11.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
github
Registry updated
10/16/2026

Versions

0.11.0stable
9/7/2026
0.10.0stable
9/6/2026
0.9.2stable
8/31/2026
Show 21 more versionsCollapse versions
0.9.1stable
8/31/2026
0.9.0stable
8/31/2026
0.8.12stable
8/31/2026
0.8.11stable
8/29/2026
0.8.10stable
8/28/2026
0.8.9stable
8/27/2026
0.8.8stable
8/26/2026
0.8.7stable
8/25/2026
0.8.6stable
8/24/2026
0.8.5stable
8/23/2026
0.8.4stable
8/22/2026
0.8.3stable
8/21/2026
0.8.2stable
8/20/2026
0.8.1stable
8/20/2026
0.8.0stable
8/18/2026

Related plugins

Loading related plugins…

Latest
0.11.0
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
web
License
MIT
Source
github
GitHub
★ 13
Weekly downloads
404
Last push
9/7/2026
View source ↗Project homepage ↗
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
0.7.1stable
8/17/2026
0.7.0stable
8/17/2026
0.6.1stable
8/16/2026
0.6.0stable
8/16/2026
0.5.4stable
8/16/2026
0.5.3stable
8/16/2026

Related plugins

More verified plugins in memory-context.

Hindsight Coding Agents@vectorize-io/hindsight-coding-agentsReflect-only Hindsight long-term memory for coding agents (harness-pluggable: opencode, …), with automatic background ingestion (no setup CLI).Memory Plugin@openviking/dsh-memory-pluginOpenViking memory and context bundle for DeepSeek HarnessAb Memorydsh-ab-memory--- description: "The dsh-ab-memory package: a cross-session, file-backed agent memory with five tools (remember / recall / forget / load_skill / distill) and an always-on light injection." kind: "package-reference" ---Contextdsh-contextA DeepSeek Harness plugin for context insight and management, with context dashboard and context command, for understanding how the context is made of, and how it evolves.