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.

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

dsh-mnemon

Mnemon

Composable, view-based memory for DeepSeek Harness. Pluggable sources and strategies, with layered memory out of the box.

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

npx -y @deepseek-ai/dsh plugin --profile web add github:omdsh-dev/dsh-mnemon#4feee034e0936868e8ebbbb47e425ae85dd73867

Compatibility and provenance

Mnemon is published as dsh-mnemon and currently resolves to version 0.5.29. 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

0.5.29stable
10/14/2026
0.5.28stable
10/11/2026
0.5.27stable
10/10/2026
Show 67 more versionsCollapse versions
0.5.26stable
10/9/2026
0.5.25stable
10/8/2026
0.5.24stable
10/4/2026
0.5.23stable
10/3/2026
0.5.22stable
10/2/2026
0.5.21stable
9/30/2026
0.5.20stable
9/28/2026
0.5.19stable
9/28/2026
0.5.18stable
9/28/2026
0.5.17stable
9/27/2026
0.5.16stable
9/26/2026
0.5.15stable
9/26/2026
0.5.14stable
9/25/2026
0.5.13stable
9/22/2026
0.5.12stable
9/19/2026
0.5.11stable
9/18/2026
0.5.10stable
9/16/2026
0.5.9stable
9/14/2026
0.5.8stable
9/11/2026

Related plugins

Loading related plugins…

Latest
0.5.29
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
web
License
MIT
Source
github
GitHub
★ 0
Weekly downloads
13,442
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
0.5.7stable
9/10/2026
0.5.6stable
9/9/2026
0.5.5stable
9/7/2026
0.5.4stable
9/6/2026
0.5.3stable
9/6/2026
0.5.2stable
9/5/2026
0.5.1stable
9/4/2026
0.5.0stable
9/4/2026
0.5.0-rc.1prerelease
9/3/2026
0.4.7stable
9/3/2026
0.4.6stable
9/2/2026
0.4.5stable
9/2/2026
0.4.4stable
8/31/2026
0.4.3stable
8/31/2026
0.4.2stable
8/31/2026
0.4.1stable
8/30/2026
0.4.0stable
8/30/2026
0.3.6stable
8/30/2026
0.3.5stable
8/28/2026
0.3.4stable
8/27/2026
0.3.3stable
8/27/2026
0.3.2stable
8/25/2026
0.3.1stable
8/25/2026
0.3.0stable
8/24/2026
0.2.16stable
8/22/2026
0.2.15stable
8/21/2026
0.2.14stable
8/20/2026
0.2.13stable
8/19/2026
0.2.12stable
8/19/2026
0.2.11stable
8/19/2026
0.2.10stable
8/19/2026
0.2.9stable
8/17/2026
0.2.8stable
8/17/2026
0.2.7stable
8/17/2026
0.2.6stable
8/17/2026
0.2.5stable
8/17/2026
0.2.4stable
8/17/2026
0.2.3stable
8/17/2026
0.2.2stable
8/17/2026
0.2.1stable
8/17/2026
0.2.0stable
8/17/2026
0.1.6stable
8/16/2026
0.1.5stable
8/16/2026
0.1.4stable
8/14/2026
0.1.3stable
8/14/2026
0.1.2stable
8/14/2026
0.1.1stable
8/14/2026
0.1.0stable
8/13/2026

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 HarnessContextdsh-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.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.