DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-mnemosyne-memory

Permanent long-term memory, vector semantic search, and LLM reflection plugin for DeepSeek Harness.

Developer ToolsSkills & Workflows
1GitHub Stars0ForksUpdated2026-09-20

Install

$ dsh plugin --profile web add $(pwd)

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-mnemosyne-memory is a long-term memory and knowledge persistence plugin for DeepSeek Harness (DSH). It provides cross-session memory retention, vector-based semantic retrieval, automated LLM reflection, Git commit history seeding, and knowledge page generation. Supporting both cloud providers (such as Gemini/DeepSeek) and local offline embeddings via Ollama, it exposes 11 mnemo_* tools for context management across DSH workspaces.

Key Capabilities

  • Permanent cross-session memory storage and retrieval
  • Vector-based semantic search with configurable embedding providers (Ollama, Gemini, OpenAI, DeepSeek)
  • Automated LLM reflection to extract insights and decisions
  • Auto-generation and delta refreshing of workspace knowledge pages
  • Git history import and codebase survey for automated context building
  • 11 mnemo_* tools including mnemo_recall, mnemo_store, mnemo_reflect, and mnemo_diagnose

Useful For

  • Persisting project decisions, conventions, and architectural context across DSH sessions
  • Searching past AI interactions and knowledge bases using semantic natural language queries
  • Maintaining offline, privacy-first local memory stores via Ollama
  • Inheriting repository commit history to seed new workspace agent context

Who It Fits

  • DeepSeek Harness users requiring cross-session persistence for AI agents
  • Developers looking for local or cloud-backed semantic memory in DSH
  • Teams managing complex multi-turn coding workflows across multiple sessions

Documented Limitations

  • Requires Node.js >= 18.0.0 and DSH >= 0.1.0-rc.7
  • Offline mode requires a local Ollama instance with an embedding model (e.g., nomic-embed-text) installed
  • Cloud embedding providers require valid external API keys (e.g. Gemini, OpenAI, or DeepSeek)

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 1 runtime, 0 development, 2 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

Source & Registry Notes

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

Source repository
Witchwarren2344/dsh-mnemosyne-memory
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
cf4b3d0 · 2026-09-21

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
1GitHub stars
Forks
0
Open issues
0
Last commit
2026-09-20
Last release
No release detected
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