xby-remember-memory
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-remember-memory
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install xby-skill/xby-remember-memory in DeepSeek Harness to install the plugin; the source code is hosted at https://github.com/xby-skill/xby-remember-memory
About this plugin
AI chat sessions are inherently stateless: close the window, start a new conversation, and every project context, style preference, and domain-specific term you discussed is gone. You end up re-explaining the same background over and over. xby-remember-memory plugs a category-based persistent memory layer into the DeepSeek Harness plugin system so that Claude can recall what you saved in previous sessions.
The workflow is straightforward: you define a category (for example project-alpha or writing-style), store tagged memory entries under it, and retrieve or delete them as needed. Four core commands cover the full lifecycle — remember_memory, retrieve_memories, remove_memory_category, and remove_specific_memory. The API key is set once and persists across restarts, so there is no re-configuration overhead.
It is built for developers, writers, and teams who collaborate with AI over the long term: whenever you want Claude to carry a consistent understanding of a project, a writing voice, or a glossary across sessions without re-prompting every time, this plugin serves as an external memory layer for your workflow.
Use Cases
- Retaining project context across chat sessions
- Persisting personal writing-style preferences
- Managing and retrieving a domain glossary by category
Best For
- Developers collaborating with AI long-term
- Writers who need a consistent voice across sessions
- Teams wanting to cut down on repetitive prompting
Related Plugins
Memory layer for coding agents that indexes local session history and auto-recalls relevant context before edits, commands, and failures, with no manual search needed.
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.