dsh-plugin-memory
Persistent five-layer memory plugin for DeepSeek Harness with relevance-based context injection, agent tools, and optional LLM extraction.
Install
$ dsh plugin --profile web add github:NattoCB/dsh-plugin-memoryPlugin 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.
Key Capabilities
- Maintains global profile memory and per-project indexes, topics, and append-only daily logs.
- Injects entry memory once per session and relevant topic memory on each agent step.
- Uses LLM ranking when configured, with keyword-based relevance fallback when no LLM route is available.
- Optionally performs debounced idle-time LLM extraction from recent session events.
- Registers six tools: memory_write, memory_read, memory_search, memory_daily, memory_forget, and memory_profile.
- Constrains booted index content to 200 lines or 40,000 characters.
Useful For
- Retaining user preferences and background across DSH sessions.
- Keeping project-specific decisions, conventions, and notes available to an agent.
- Recording dated project updates through daily memory logs.
- Searching, editing, or deleting stored memory through agent tools.
- Adding relevance-based context without configuring an LLM route.
Who It Fits
- DeepSeek Harness users with a plugin-capable profile.
- Single-user DSH users who want persistent global and project context.
- Agent workflows that benefit from reusable project notes and user profiles.
Documented Limitations
- Requires a DeepSeek Harness installation and plugin-capable profile.
- It has no HTTP API or GUI panel.
- LLM-based relevance ranking and automatic extraction require a configured LLM provider and model; otherwise it uses keyword relevance only.
- Auto-extraction is best-effort, runs after a 60-second idle debounce by default, and examines a configurable recent-event window.
- DSH is treated as a single-user environment; memory paths do not include user-ID isolation.
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 1 runtime, 8 development, 7 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- NattoCB/dsh-plugin-memory
- Registry source
- Community submission
- Registry classification
- Plugin
- Source checked
- a83fcce · 2026-09-19
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
- 3GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-08-21
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Composable three-tier memory control plane for DeepSeek Harness with runtime context, searchable documents, and pluggable long-term memory.
View plugin →Long-term spatiotemporal memory, zero-LLM whitebox reasoning, and knowledge flywheel integration for DeepSeek Harness via AEIS.
View plugin →Traceable, searchable, cross-session knowledge graph memory engine for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed safety and session audit.
View plugin →