AI Agent Hub
Back to plugins
dsh-memory-dashboard preview

dsh-memory-dashboard

Memory Updated 2026.08.28

Run the following command in DeepSeek Harness:

dsh plugin install perinchiang/dsh-memory-dashboard

Paste the following prompt into your AI chat to install this plugin:

Run dsh plugin install perinchiang/dsh-memory-dashboard in DeepSeek Harness to install this plugin (source repository: https://github.com/perinchiang/dsh-memory-dashboard), then restart dsh web to activate it.

About this plugin

If you have dsh-tdai-memory and the TencentDB Agent Memory backend running but lack a convenient way to browse your locally accumulated memory data, dsh-memory-dashboard fills that gap. Instead of spinning up a separate dashboard, it drops a Memory entry point right at the top of the Harness conversation page, so you can switch perspective between active dialogue and the L0-through-L3 memory layers at a glance.

The experience is deliberately restrained and practical: the Overview pane surfaces per-layer counts, current layer share, and session stats in one view; the Layer Selector stays in sync with the record list, with local search and incremental loading; tapping a single memory opens a mobile-friendly Bottom Sheet with technical metadata collapsed by default. Most importantly, when a memory entry can be traced back to its originating session, you get a one-click jump back to that Harness conversation to restore full context.

This plugin is best suited for developers who have already deployed dsh-tdai-memory, have a local vectors.db in place, and want to inspect memory structure in read-only mode without touching the backend. It registers GET routes only, opens SQLite in read-only mode, writes nothing, and makes no TencentDB API calls, making it safe to keep active in production.

Screenshots

Use Cases

  • Quickly identify which layer a memory entry belongs to and inspect its metadata mid-conversation
  • Search local memory records and jump back to the originating Harness session for full context
  • Compare L0-through-L3 layer counts and shares to evaluate the memory refinement pipeline

Best For

  • Developers who have deployed dsh-tdai-memory and want to visualize local memory structure
  • Ops and QA engineers auditing TDAI memory data without modifying the backend
  • Developers debugging Harness memory features on mobile who need a compact information layout