dsh-task-memory
Run the following command in DeepSeek Harness:
dsh plugin install wangyihao0001-oss/dsh-task-memory
Paste the following prompt into your AI chat to install this plugin:
In DeepSeek Harness, install this plugin using the command dsh plugin install wangyihao0001-oss/dsh-task-memory, with the source code available at https://github.com/wangyihao0001-oss/dsh-task-memory。
About this plugin
In DeepSeek Harness, most memory plugins offer global or workspace-wide storage, which can lead to data confusion or leakage between different tasks. The dsh-task-memory plugin addresses this by introducing task isolation, storing each task's memories in separate vaults derived by default from the session directory, ensuring clear data boundaries. Its core capabilities include binding sessions to specific tasks, storing and retrieving memories, keyword search, and current task confirmation through tools like memory_bind_task, memory_remember, and memory_search, enabling efficient memory management in isolated contexts. This plugin is ideal for developers juggling multiple projects or tasks, such as in microservices development where each service task requires independent memory management, and it suits scenarios demanding high data privacy and isolation to prevent accidental sharing of sensitive information. Overall, it ensures reliability through atomic writes and locking mechanisms, focusing on task-level memory management to provide a flexible and secure memory solution for DeepSeek Harness users.
Use Cases
- In microservices development, storing configuration memories independently for each service.
- Maintaining memory context isolation when switching projects in multi-task workflows.
- Environments requiring protection against sensitive information leakage across tasks.
Best For
- Software developers handling multiple projects simultaneously.
- Teams using DeepSeek Harness for complex task management.
- Organizations with strict requirements for data privacy and isolation.
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.