AI Agent Hub
Back to plugins
🧠

dsh-memory

Memory Updated 2026.08.25

Run the following command in DeepSeek Harness:

dsh plugin install haitang1/dsh-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 haitang1/dsh-memory. Source: https://github.com/haitang1/dsh-memory

About this plugin

When working with DeepSeek Harness or Codex-like systems, a common pain point is the loss of context between sessions. The dsh-memory plugin addresses this by providing a durable, auto-injected memory layer for every session. Through its intelligent summarization mechanism, the plugin automatically distills conversation turns into summaries and periodically re-consolidates them into a global memory file, ensuring the agent never forgets previous interactions.

Its core capability lies in robust memory management tools. Users can interact with the memory using tools like memory_read, memory_add, and memory_search, while also benefiting from scoped management across workspaces or projects. Additionally, the plugin includes an auto-memory skill that guides agents to proactively identify key facts and write them to memory, enabling truly autonomous memory maintenance.

This is an ideal choice for developers building complex AI applications or agents that require long-term coherence and contextual memory. By injecting distilled summaries into every prompt, it ensures agents do not forget past interactions, significantly enhancing the quality and reliability of multi-turn dialogues.

Use Cases

  • Build agent systems with long-term memory capabilities
  • Ensure context is not lost in multi-turn dialogue
  • Provide persistent knowledge storage for AI assistants

Best For

  • DeepSeek Harness plugin developers
  • AI engineers building complex RAG applications
  • Agent project managers handling long-term interaction tasks