← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-shoucang-memory

Long-term memory management plugin for DeepSeek Harness with automated distillation, reflection, and hybrid retrieval.

UI & ProductivityDeveloper ToolsSkills & Workflows
5GitHub Stars0ForksUpdated2026-09-27

Install

$ dsh plugin --profile web add github:Fishsb/dsh-shoucang-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-shoucang-memory (Shoucang) is a local-first long-term memory plugin for DeepSeek Harness (DSH). It automatically distills session insights after idle periods, summarizes principles during deep sleep cycles, and supports hybrid lexical plus vector recall (via Ollama bge-m3 or fallback lexical search). All memory data resides locally with automatic Git snapshots and includes a built-in UI panel for configuration, telemetry, and profile management.

Key Capabilities

  • Automatic session distillation after conversation idle timeouts
  • Deep sleep periodic reflection to synthesize learned agent principles and user personas
  • Hybrid retrieval combining lexical code matching and local vector embeddings
  • Context-aware minimal index injection with pointers to detailed notes
  • Lifecycle management with active, warm, cold, and archived memory states
  • Local-first storage with automatic Git commit snapshots for version tracking
  • Web settings panel integrated into the DSH interface for observation and configuration

Useful For

  • Maintaining user preferences, operational guidelines, and project knowledge across multiple DSH sessions
  • Preventing context window bloat by injecting only relevant memory pointers rather than entire chat histories
  • Auditing and controlling AI memory state through a dedicated web dashboard and local markdown files

Who It Fits

  • DeepSeek Harness users seeking persistent cross-session memory without cloud storage leaks
  • Developers needing reproducible agent behaviors and persistent guidelines across task sessions

Documented Limitations

  • Vector embedding capabilities require an accessible OpenAI-compatible or Ollama endpoint running an embedding model like bge-m3; otherwise defaults to lexical search
  • Memory capacity thresholds strictly reject writes once character limits are reached to prevent context explosion

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.

Dependency Counts

package.json declares 0 runtime, 8 development, 4 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Declared

GitHub reports the repository license as Apache-2.0.

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

Source & Registry Notes

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

Source repository
Fishsb/dsh-shoucang-memory
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
0022ad1 · 2026-10-24

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
5GitHub stars
Forks
0
Open issues
2
Last commit
2026-09-27
Last release
2026-09-14
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