dsh-obsidian-vault
Run the following command in DeepSeek Harness:
dsh plugin install satan9394/dsh-obsidian-vault
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install satan9394/dsh-obsidian-vault in your DeepSeek Harness terminal to install the plugin; the source is available at https://github.com/satan9394/dsh-obsidian-vault .
About this plugin
Every time you close DeepSeek Harness, the conversational context vanishes with it. You end up re-pasting background, restating preferences, and breaking your flow. dsh-obsidian-vault bridges the Harness memory layer to your Obsidian Vault, turning the notes you already maintain into a persistent store that carries across sessions.
The idea is straightforward: move memory out of a temporary in-session buffer and into the Markdown notes you already open every day. You can browse, edit, and search what the AI has logged right inside Obsidian, without juggling two separate tools.
It is built for developers and writers who already rely on Obsidian for knowledge management and want their DeepSeek Harness sessions to remember context beyond a single window.
Use Cases
- Keep project context and preferences across sessions without re-explaining
- Browse and edit AI-captured notes directly inside Obsidian
- Unify personal knowledge management and AI memory in one set of Markdown files
Best For
- Developers and writers already using Obsidian for knowledge management
- Harness users who want their AI assistant to retain memory across sessions
- Users who prefer the Markdown ecosystem and dislike data lock-in
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.