dsh-vault
Run the following command in DeepSeek Harness:
dsh plugin install feiyang-dev/dsh-vault
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, use the command 'dsh plugin install feiyang-dev/dsh-vault', with the full source repository available at https://github.com/feiyang-dev/dsh-vault.
About this plugin
DeepSeek Harness users may face the risk of data loss, such as when the desktop client forcibly resets local data due to plugin load failures, erasing chat histories, workspace settings, and credentials. The dsh-vault plugin addresses this issue by implementing automatic backups to a secure external location, ensuring quick recovery even after data wipes. Its core capabilities include continuous backup, intelligent detection of data loss, and one-click restore, accessible via the Web settings page or natural language tools for easy management of backup history and selective recovery. Ideal for individuals or teams relying on DeepSeek Harness for work or creation, dsh-vault serves as a reliable safety net to protect data from accidental loss.
Use Cases
- Quickly restore chat records and settings when DeepSeek Harness data is wiped.
- Automatically back up workspace data regularly to prevent accidental loss.
- Detect data risk events and trigger backups for continuous protection.
Best For
- Individual users who rely on DeepSeek Harness for work or creation.
- Teams or collaborative environments prioritizing data security and recovery.
- DeepSeek Harness community members needing backup solutions.
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.