Skip to content

2303572348/deepseek-harness-memory

20Last commit Aug 14, 2026

deepseek-harness-memory DSH plugin

This installable DSH plugin provides Claude Code-style persistent user and workspace memory. It stores Markdown memory files with YAML frontmatter, injects relevant indexes into system prompts, and offers a memory tool for managing and importing memories.

How to install the deepseek-harness-memory DSH plugin

dsh plugin --profile web add .

Copying does not run this command. Review the repository and version before use.

Data source

Snapshot date: Aug 15, 2026

manifest-valid

What the deepseek-harness-memory DSH plugin can do

  • Stores user-level and workspace-level memories as Markdown files with YAML frontmatter
  • Maintains MEMORY.md indexes for stored memories
  • Injects memory indexes and recent memory files into prompts at session setup
  • Provides memory actions: add, update, delete, list, read, and import-claude
  • Can read or import compatible Claude Code memory directories
  • Supports project path aliases to share memory across multiple checkouts

Where the deepseek-harness-memory DSH plugin fits

  • Retaining user preferences and corrections across DSH sessions
  • Keeping project conventions, build commands, and debugging insights available to an agent
  • Migrating or reusing existing Claude Code memory files
  • Sharing project memory across separate local checkouts

Who the deepseek-harness-memory DSH plugin is for

  • DeepSeek Harness users who want persistent cross-session memory
  • Developers migrating from or interoperating with Claude Code memory layouts
  • Teams or individuals working across multiple checkouts of a project

deepseek-harness-memory DSH plugin limitations

  • Memory is stored in plaintext; the README advises against storing secrets or PII.
  • It does not automatically extract memories at turn end; the model must actively use add or update actions.
  • It does not provide /memory or /toggle-memory commands.
  • Prompt injection is bounded by configurable index line, byte, and memory-file limits.

Objective checks

These signals come from public metadata scans. They are not a security certification.

  • dependency counts

    package.json declares 0 runtime, 0 development, 0 peer, and 0 optional dependencies.

    info
  • dsh bundle declared

    package.json declares DSH bundle metadata.

    info
  • license declared

    GitHub reports the repository license as MIT.

    info
  • package manifest available

    A root package.json was captured and can be inspected by the registry.

    info
  • source available

    Public GitHub source metadata is available for this registry snapshot.

    info

deepseek-harness-memory DSH plugin alternatives

deepseek-harness-memory DSH plugin questions

What is the deepseek-harness-memory DSH plugin?

deepseek-harness-memory is a project included in the current DSH plugin snapshot. This page organizes repository metadata and reviewed notes, but you should still inspect the upstream repository before running it.

How do I install the deepseek-harness-memory DSH plugin?

The page shows the install command captured from the source record. Copying does not run it, so confirm the package, profile, and version against upstream documentation first.

Which DSH profile does deepseek-harness-memory use?

The snapshot records web as the deepseek-harness-memory profile. DSH conventions can change quickly, so verify the manifest and README before installation.

Is deepseek-harness-memory compatible with the current DSH release?

The source data does not include a verified compatibility matrix. Check recent commits, releases, and DSH breaking changes, then test in a profile you can roll back.

What should I do if deepseek-harness-memory fails to load?

Check the install command, selected profile, dependency logs, and Cordis startup output first. Keep the exact error string, then compare it with this site's fix pages and upstream issues.

What are the closest alternatives to deepseek-harness-memory?

Related plugins on this page come from the current snapshot and are only candidates. Compare capabilities, maintenance activity, installation method, and limitations before choosing one.