dsh-memento-tab
Run the following command in DeepSeek Harness:
dsh plugin install inxups/dsh-memento-tab
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install inxups/dsh-memento-tab in your terminal, source available at https://github.com/inxups/dsh-memento-tab; after a dsh restart the fourth session tab will appear.
About this plugin
Upstream dsh-memento gives DSH a memory layer, but searching, rewriting, consolidating, and exporting memory entries all live in the command line with no visible surface to manage the library as a whole. dsh-memento-tab is a companion plugin (not a fork) that moves every /memory verb into a fourth session tab: four budget cards with progress bars, 220ms-debounced substring search with track and scope filters, inline editing and deletion, checkbox-driven consolidation, proposal approve and reject, full-library export and atomic import, adapter format cards, and an audit trail, all in one closed loop.
A few design choices deserve a second look. The read path uses listEntries instead of query, so opening the tab, typing in the search box, or toggling filters never bumps recall_count; your browsing does not reorder the very list you are looking at, nor does it shift the model retrieval ranking. Writes have no privileged channel: every mutation walks the same approval waterfall that a model memory-tool call would, and writePolicy set to off means off with no tab bypass. Upstream can only affect this plugin through published seams, so version bumps never cause merge conflicts.
Best for users who rely on dsh-memento memory layer day to day and regularly need to tidy, consolidate, or migrate entries across workspaces: check a budget, rewrite a line, merge three into one, export and walk away, without reaching for /memory subcommands over and over.
Use Cases
- Search, rewrite, and consolidate memory entries through a visual panel
- Export and import memory across workspaces while preserving layer keys
- Monitor four-layer budget usage and audit every read or write
Best For
- DSH users who depend on the dsh-memento memory layer daily
- Dev teams that frequently consolidate or migrate memory across workspaces
- Project leads who need visual budget and audit tracking
Related Plugins
Memory layer for coding agents that indexes local session history and auto-recalls relevant context before edits, commands, and failures, with no manual search needed.
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.