DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-mnemosyne-memory

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

Developer ToolsSkills & Workflows
1GitHub Stars0ForksUpdated2026-08-25

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 management plugin for DeepSeek Harness (DSH). It provides AI agents with persistent cross-session memory, vector-based semantic search, automated reflection cycles, knowledge page generation, and Git history seeding. It supports local offline embeddings via Ollama as well as cloud-based providers such as Google Gemini, OpenAI, and DeepSeek.

Key Capabilities

  • Cross-session persistent memory storage for decisions, insights, and context
  • Vector semantic search and recall across workspace memories
  • Automated LLM reflection to extract insights and conventions periodically
  • Knowledge page generation with incremental delta updates
  • Codebase survey and Git commit history seeding into memory banks
  • Support for multiple embedding providers including Ollama, Gemini, DeepSeek, and OpenAI

Useful For

  • Retaining project context, decisions, and architecture across different DSH sessions
  • Indexing local codebases and Git history to provide historical context to AI agents
  • Running local offline memory recall using Ollama without sending data to external APIs

Who It Fits

  • DeepSeek Harness developers needing persistent memory across sessions
  • AI agent developers building complex long-running coding assistants
  • Engineers requiring privacy-preserving, local-first memory indexing via Ollama

Documented Limitations

  • Requires Node.js >= 18 and DeepSeek Harness >= 0.1.0-rc.7
  • Local embedding models (e.g. nomic-embed-text) require an active Ollama instance
  • Cloud embedding providers require valid external API keys

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
fjzzwxp/dsh-mnemosyne-memory
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
e98a92b · 2026-08-26

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
2026-08-25
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