dsh-research-graph
Run the following command in DeepSeek Harness:
dsh plugin install benz-ai-x/dsh-research-graph
Paste the following prompt into your AI chat to install this plugin:
Open the plugin page at https://github.com/benz-ai-x/dsh-research-graph in DeepSeek Harness Web and run dsh plugin install benz-ai-x/dsh-research-graph to install.
About this plugin
As AI conversations increasingly carry the weight of product research, technical evaluation, and knowledge management, a recurring frustration emerges: discussions scatter across a timeline, conclusions are hard to trace back, multiple sources cannot be compared side by side, and the next research session starts from zero context. DSH Research Graph was built to close that gap.
It organizes conversations inside DSH Web into a visual research graph with drag, collapse, and branch-merge inspection. Key conclusions, conditions, and open questions are captured as Knowledge Cards with one-click source tracing back to the exact original turns. A built-in AI analysis module extracts selected passages, compares two to three materials, and lets you review before saving. You can also resume a discussion from any historical turn or card revision while retaining all the materials used, then export the results as a Markdown research report.
It suits product researchers, technical evaluators, and knowledge managers who want a conversation-as-research workflow, especially those already working inside DSH Web with DeepSeek for daily dialogue.
Screenshots
Use Cases
- Organize multi-turn AI conversations into a traceable, collapsible research graph
- Compare multiple sources and export a Markdown research report
- Resume a discussion from a historical turn while retaining all original materials
Best For
- Teams conducting product research and technical evaluation
- DSH Web users who rely on DeepSeek for daily dialogue
- Independent researchers needing long-term knowledge curation and deliverable archiving
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.