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.

Experimental Ralph Bundle — DSH Plugin for DeepSeek Harness
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins

@deepseek-ai/dsh-experimental-ralph-bundle

Experimental Ralph Bundle

Run explicitly requested repeated work with fresh agents.

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

npx -y @deepseek-ai/dsh plugin --profile web add @deepseek-ai/dsh-experimental-ralph-bundle@0.2.1-alpha.2
READMECompatibilityVersions

Compatibility and provenance

Experimental Ralph Bundle is published as @deepseek-ai/dsh-experimental-ralph-bundle and currently resolves to version 0.2.1-alpha.2. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
any
Release source
npm
Registry updated
10/16/2026

Versions

0.2.1-alpha.2prerelease
10/9/2026
Show 2 more versionsCollapse versions
0.2.1-alpha.4prerelease
10/15/2026
0.2.1-alpha.3prerelease
10/14/2026

Related plugins

Loading related plugins…

Latest
0.2.1-alpha.2
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
10.3 kB
Files
11
Surface
any
License
MIT
Source
npm
GitHub
★ 250.8k
Weekly downloads
12,578
Security scan
✓ v0.2.1-alpha.2 scan passed
Last push
10/15/2026
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

Related plugins

More verified plugins in agents-orchestration.

Headless@deepseek-ai/dsh-headlessThe dsh one-shot bundle: a direct core Agent/Session runner over dsh-base with no Host, HTTP, or browser layerExperimental Agent Team Profile@deepseek-ai/dsh-experimental-agent-team-profileAgent Teams collaboration, tools, and Web UI in one experimental bundleHindsight 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).Experimental Agent Team Web Profile@deepseek-ai/dsh-experimental-agent-team-web-profileExperimental Web profile layer for Agent Teams Remote and UI plugins

README


description: "Run explicitly requested repeated work with fresh agents." kind: "package-bundle"

@deepseek-ai/dsh-experimental-ralph-bundle

English | 中文

Summary

Add the experimental Ralph tool to every Agent as a global tool for human-requested repeated work with fresh child agents. It ships switched off in Web and Desktop. Select it in Plugins to enable it.

Table of Contents

  • Use this package
  • Understand the implementation
  • Further Exploration
  • Model Experience
  • Known Limitations and Deferred Work
  • Dev Note

Use this package

In Web or Desktop, open Plugins and enable Ralph loops in Official. Switch it off to remove its profile layer.

Enabling or disabling the bundle registers or removes its global tools in the running Host, so every Agent sees the change on its next request, in every preset including minimal.


Understand the implementation

Implementation details — click to expand

cordis.patch.yml inserts the Host group optional-ralph, which isolates its own workflowEngine and registers tool-ralph in the global tool layer. Later profile patches can replace the tool's configuration or disable it by row id; an override alone does not select the bundle. The profile composer owns patch ordering and errors.


Further Exploration

Capability implementation


Model Experience

Indirectly, through the capability implementation, which owns model context and results.

KV Cache effect

The layer adds no request content directly; the capability implementation owns cache effects from tools, prompts, and results. Toggling the bundle changes the tool list of live Sessions, which invalidates their cached request prefix once.

Known Limitations and Deferred Work

  • Ralph requires explicit human intent to run a loop and can consume substantial model tokens across rounds. Its workflow engine is isolated from other workflow tools.

Dev Note

Maintainer context — click to expand

None.