dsh-persistent-memory
Run the following command in DeepSeek Harness:
dsh plugin install satan9394/dsh-persistent-memory
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install satan9394/dsh-persistent-memory in your terminal to add this persistent memory plugin to DeepSeek Harness; source code available at https://github.com/satan9394/dsh-persistent-memory
About this plugin
DeepSeek Harness sessions are ephemeral by design. Once the window closes, all context disappears and the next conversation starts from scratch, requiring you to re-explain project background and preferences.
dsh-persistent-memory is a lightweight memory-category plugin whose core purpose is to provide a persistent memory layer for Harness, allowing established context to survive across sessions and eliminating the need to rebuild it every time.
It is well suited for developers who work on the same project regularly and want context to carry over between sessions, as well as for long-term users who wish to consolidate personal preferences and recurring constraints.
Use Cases
- Resuming work on the same project across days without re-explaining background
- Retaining coding preferences and project constraints to minimize repetition
- Building up context gradually in long conversations for better coherence
Best For
- Developers maintaining the same project over extended periods
- Harness users who want to retain personal preferences and established constraints
- Technical writers who frequently work across multiple sessions
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.