dsh-maestro-memory
Run the following command in DeepSeek Harness:
dsh plugin install ddtcorex/dsh-maestro-memory
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, run the command: dsh plugin install ddtcorex/dsh-maestro-memory, with the full source address https://github.com/ddtcorex/dsh-maestro-memory.
About this plugin
DeepSeek Harness AI sessions often lose memory after restart, leading to fragmented interactions and repeated context setup. The dsh-maestro-memory plugin solves this by providing durable memory and todos storage, preserving user data across sessions for a seamless experience. Its core capabilities include multi-track memory management (e.g., user, project, daily memories) and task tracking, with features like sensitive data filtering and system prompt injection, enabling the AI to gradually learn and understand user habits and preferences. This plugin is ideal for all DeepSeek Harness users, especially developers and everyday使用者 seeking more personalized AI interactions that remember tasks and context, boosting efficiency and continuity.
Use Cases
- Preserve user preferences and memories across sessions in DeepSeek Harness.
- Track personal, project, or daily tasks using the todo feature.
- Allow AI to gradually accumulate understanding of user habits through the memory system.
Best For
- All individual users of DeepSeek Harness.
- Team members or professionals needing cross-session task and memory management.
- Developers seeking a more personalized AI assistant that remembers context.
Related Plugins
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.
An opinionated, zero-infrastructure file-based memory protocol: human-readable markdown files plus a bounded always-loaded index, curation discipline, and no database or embeddings.