dsh-stickies
Run the following command in DeepSeek Harness:
dsh plugin install ming-xia/dsh-stickies
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install ming-xia/dsh-stickies in your DeepSeek Harness environment (source: https://github.com/ming-xia/dsh-stickies ), then restart the Web profile as prompted to activate the stickies button in the conversation title bar.
About this plugin
When you are iterating on requirements or breaking down tasks with a model in DeepSeek Harness, scattered checklists and context often get buried in the chat log, and grabbing a quick note means context-switching to an external tool. dsh-stickies embeds a lightweight sticky pad right beside your conversation so you can capture requirements, questions, to-dos, and working context without ever leaving the page.
The core workflow covers the full note-taking loop: an inline directory stays parallel to the conversation and can be dragged out into a resizable floating card. Markdown editing and preview support headings, lists, checklists, code blocks, tables, and more. Checklist items can be checked inline with state written back to the source. Color, ordering, and sizing are fully adjustable, and revision history with version rollback keeps every change traceable. All data is stored locally through the Harness Web Server. No cloud account, no external data service.
Best suited for developers and product managers who do product breakdown, technical research, task management, or code review inside Harness, and who treat the conversation as their primary work surface and want to turn fleeting ideas into structured notes on the fly.
Use Cases
- Capture requirements, issues, and to-dos right beside the conversation
- Drag stickies out into resizable floating cards to organize context while chatting
- Check off Markdown lists with state written back, and roll back to a prior version if needed
Best For
- Developers doing product breakdown and task management in Harness
- Heavy users who treat the conversation page as their primary workspace
- Users who need purely local storage and prefer no cloud note service
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.