dsh-cite
Run the following command in DeepSeek Harness:
dsh plugin install wanghehe123/dsh-cite
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, run the install command with the full GitHub source code address https://github.com/wanghehe123/dsh-cite.
About this plugin
In deep conversations or complex tasks, it is often difficult to review context or cite old sessions because traditional chat logs lack effective referencing mechanisms, leading to fragmented information that is hard to reuse. The 'Citation' plugin solves this problem through innovative interactions: users can directly select any text in the chat, add personal insights like annotations, or cite this content as evidence in new conversations. At the same time, it supports using the @ symbol to quickly retrieve and reference historical sessions, generating read-only snapshots with sources without manual text copying. This tool is perfect for users who need to track project progress long-term, perform code reviews, or build complex knowledge bases, as it improves dialogue continuity and allows the AI model to better understand context dependencies.
Screenshots
Use Cases
- Select key code snippets and annotate them during reviews.
- Cite old sessions as factual evidence for new tasks.
- View and manage generated files directly in replies.
Best For
- Developers needing to continuously reference context in conversations.
- Researchers relying on historical data as evidence.
- Teams needing efficient management and tracing of project files.
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.