dsh-client-ui-obsidian-memory
Run the following command in DeepSeek Harness:
dsh plugin install detongz/dsh-client-ui-obsidian-memory
Paste the following prompt into your AI chat to install this plugin:
When installing dsh-client-ui-obsidian-memory in DeepSeek Harness, point to its GitHub source at https://github.com/detongz/dsh-client-ui-obsidian-memory.
About this plugin
It addresses a familiar problem: an AI agent often loses context once a session ends, leaving important notes, references, and reusable conclusions scattered across chat history. This plugin connects DSH to a local Obsidian or plain Markdown vault, letting the agent keep reading, searching, and updating its own knowledge base. The data stays on your machine, requires no external server, and works with the Codex/ directory structure recommended by the community.
Its core capability is a set of file-vault memory tools: read, list, search, write, and append. The agent can look up past notes, save new findings, and add fresh context to specific Markdown files over time. The plugin also surfaces a status panel in DSH's left sidebar, helping you confirm that the vault is connected and see which tools are available, while keeping file access constrained to the configured directory to reduce accidental edits elsewhere.
This is best for people who already use Obsidian or prefer local Markdown as their knowledge system. If you want DSH agents to remember project notes, research trails, writing materials, or personal preferences while keeping that memory visible, editable, and portable, this plugin offers a practical way to build on files you already own.
Screenshots
Use Cases
- Let the agent keep searching local notes after a session ends
- Append project findings to Markdown memory files
- View Obsidian vault status in the DSH sidebar
Best For
- Heavy Obsidian users
- People who manage knowledge in local Markdown
- Users who need persistent memory for AI agents
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.