dsh-tool-user-memory
Run the following command in DeepSeek Harness:
dsh plugin install IAMLieutenant/dsh-tool-user-memory
Paste the following prompt into your AI chat to install this plugin:
To install the plugin in DeepSeek Harness, run the command `dsh plugin install IAMLieutenant/dsh-tool-user-memory`. The full source code is available at https://github.com/IAMLieutenant/dsh-tool-user-memory.
About this plugin
By default, every new session in DeepSeek Harness starts with the agent as a 'stranger,' completely forgetting previous interactions. This forces users to repeatedly introduce their language preferences, project backgrounds, and goals, wasting time and breaking workflow continuity. The dsh-tool-user-memory plugin is designed to address this pain point by introducing a persistent user profile system. It enables the agent to remember key personal preferences and context across sessions, leading to a more consistent and personalized interaction experience.
The core strength of this plugin lies in its seamless memory management. With simple commands, users can have the agent store stable preferences such as communication style, frequently used programming languages, or long-term project objectives. Memory content is securely saved as a Markdown file and automatically injected into the system prompt for every new session, ensuring the agent intuitively understands the user without manual loading or tool calls. Additionally, the plugin provides memory_update and memory_get tools, allowing the agent to proactively learn, query, or adjust memories while keeping users in full control—able to manually edit or delete entries as needed.
dsh-tool-user-memory is especially suited for users who frequently rely on DeepSeek Harness for complex tasks and value efficiency and personalization. Whether you are a developer, researcher, or casual user, if you want the agent to remember your habits and project details to avoid repetitive introductions, this plugin can significantly enhance interaction smoothness. It transforms the agent from a 'resetting assistant' into a 'long-term partner who knows you,' saving time and deepening collaborative engagement.
Use Cases
- Enable the agent to remember the user's language habits and communication style
- Automatically load user project background in new sessions to avoid repetition
- View and modify stored user preferences through tools
Best For
- Developers and researchers who frequently use DeepSeek Harness
- Users looking to improve agent interaction efficiency
- Individuals or teams needing personalized assistant support
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.