look-here
Run the following command in DeepSeek Harness:
dsh plugin install ZanderKong/look-here
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install ZanderKong/look-here to install from https://github.com/ZanderKong/look-here, then restart the Web service when prompted.
About this plugin
Scrolling through a long DSH response, the most natural impulse is to pause, point at a sentence, and ask what it means or how it fits together. Look Here is built for exactly that moment: select text, and a nearby dot appears. A short press triggers a quick explanation or custom follow-up question; a long press lets you add an annotation. Every side call runs through an independent ctx.llm invocation, so nothing leaks into the main conversation.
The memory and annotation workflow is where it really shines. Save explanations you like and they resurface when the same term reappears later. Gather several anchored notes in a drawer, edit them freely, then drag the whole batch into the DSH composer. The draft updates silently, and only you decide when to hit send, because Look Here never auto-submits a main-session message.
It suits technical writers, documentation reviewers, and learners who read long DSH responses closely and like to annotate as they go. The UI is bilingual in Chinese and English, supports theme colors, configurable selection gestures, and reduced-motion preferences for comfortable extended reading.
Use Cases
- Select a sentence in a long DSH response and short-press the dot for an isolated explanation that does not touch the main conversation
- Collect several anchored notes, edit them freely in the drawer, then drag the whole batch into the composer
- Save explanations of key terms so they resurface automatically the next time the same term appears
Best For
- Technical writers who read long DSH responses closely and annotate as they go
- Documentation reviewers who batch annotations and want full control over when a draft is sent
- Learners who prefer isolated supplementary explanations without interrupting the main conversation flow
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.