Repository unavailableThe source repository is currently unavailable. Plugin information is preserved from the last successful DSH Plugin Registry snapshot.
DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-memory

Cross-session memory plugin for DeepSeek Harness with automatic memory prompts, daily workspace notes, search, and optional vector fusion.

UI & ProductivityDeveloper Tools
2GitHub Stars0ForksUpdated2026-09-04

Install

$ dsh plugin --profile web add "github:zhouzhencheng07/dsh-memory"

Plugin Overview & Capabilities

AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.

source-grounded
dsh-memory is an installable DeepSeek Harness bundle plugin. It prompts the main agent to preserve useful information through a memory_write tool, stores per-workspace daily Markdown notes under DSH_HOME, and exposes memory_search with ranked keyword retrieval and optional Ollama-compatible embedding fusion.

Key Capabilities

  • Injects an Auto-Memory reminder into main-agent system prompts; it can be disabled with autoMemory: false.
  • Provides memory_write to upsert a top-level topic section in the current workspace's daily memory file.
  • Provides memory_search with heading-aware Markdown chunk retrieval, snippets, keyword matching, and daily score decay.
  • Can combine keyword and vector results using RRF when an Ollama-compatible embedding endpoint is configured.
  • Adds a plugin settings card with hot-reloaded persistent configuration.

Useful For

  • Carry project decisions or recurring context across DeepSeek Harness sessions.
  • Retrieve prior workspace notes without opening entire memory files.
  • Maintain daily, workspace-specific Markdown memory notes outside project directories.
  • Optionally improve memory retrieval with a self-configured embedding service.

Who It Fits

  • DeepSeek Harness users who want persistent cross-session context.
  • Users managing recurring work across multiple workspaces.
  • Users able to provide an Ollama-compatible embedding endpoint for optional vector search.

Documented Limitations

  • Memory writing depends on the main agent deciding to call memory_write after receiving the Auto-Memory reminder.
  • Vector fusion requires a configured Ollama-compatible /api/embed service; unavailable vector service falls back to keyword-only search.
  • Installation and plugin updates require restarting dsh web to take effect.
  • Memory is stored as daily Markdown files under $DSH_HOME/dsh-memory/ rather than inside workspace directories.

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

No automated security signals have been published yet.

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
zhouzhencheng07/dsh-memory
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
64e9d2e · 2026-09-10

This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.

Repository Activity

GitHub stars
2GitHub stars
Forks
0
Open issues
0
Last commit
2026-09-04
Last release
2026-08-28
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app