dsh-remember
Run the following command in DeepSeek Harness:
dsh plugin install Arborsm/dsh-remember
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install Arborsm/dsh-remember in your terminal to install the plugin; the source code is available at https://github.com/Arborsm/dsh-remember .
About this plugin
If you work on long-running projects with DeepSeek Harness, the most frustrating part is context loss: every new session starts from zero, and you end up re-explaining project background, past decisions, and pitfalls you have already gone through. dsh-remember lets the model remember on its own—it scans idle sessions in the background, distills useful experience into a set of plain Markdown memory files, injects a summary at the start of each subsequent conversation, and greps the originals on demand when details are needed.
The whole design avoids vector databases and external services. Every memory is a text file under ~/.dsh-memory/ that you can open, search, and version with Git. Built-in capabilities include automatic extraction, incremental consolidation with pruning of stale never-cited entries, automatic recall with a configurable token cap, one-click translation with incremental caching, and gzip bundle export/import with content-hash dedup. A sidebar status panel and memory viewer let you inspect, manage, or pause everything at any time.
If you frequently have multi-round, cross-day, cross-project conversations with dsh and want memories that stay fully local, human-readable, and under your control without any third-party service, dsh-remember is built for you.
Screenshots
Use Cases
- Maintaining project context automatically across multi-day conversations
- Eliminating repetitive background and preference explanations in new sessions
- Accumulating and managing AI session experience locally as Markdown files
Best For
- Engineers running long-term development projects on dsh
- Independent developers who prioritize data locality and privacy
- Heavy AI users who need cross-session experience accumulation without external services
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.