benz-ai-x

Dsh Research Graph — AI skill for Claude Code

AI community

DSH Research Graph · 研图 — DeepSeek Harness plugin for research topics, traceable knowledge cards, and reusable AI discussions.

How to install Dsh Research Graph

This entry records only its repository, not the path inside it, so there is no exact command to give. Open benz-ai-x/dsh-research-graph and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Dsh Research Graph does

DSH Research Graph · 研图 — DeepSeek Harness plugin for research topics, traceable knowledge cards, and reusable AI discussions.

Alternatives in AI

Wiki Graph — Build the LLM Wiki knowledge graph 2.3k ★
Loushang — AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool 1.3k ★
Memtrace Public — Structural memory for AI coding agents 466 ★

README

description: "A DeepSeek Harness Web plugin for AI conversation graphs, research topics, and source-linked Knowledge Cards. Explore capabilities, check compatibility, and install the research workbench." kind: "package-bundle"

DSH Research Graph

[![CI](https://github.com/benz-ai-x/dsh-research-graph/actions/workflows/ci.yml/badge.svg)](https://github.com/benz-ai-x/dsh-research-graph/actions/workflows/ci.yml) [![npm](https://img.shields.io/npm/v/%40benz-ai-x%2Fdsh-research-graph/next?logo=npm)](https://www.npmjs.com/package/@benz-ai-x/dsh-research-graph) [![MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)

**English** | [简体中文](README.zh.md)

An independently maintained, open-source **AI research workbench plugin** for [DeepSeek Harness (DSH)](https://github.com/deepseek-ai/deepseek-harness), running inside **DSH Web**. Organize conversations into research topics and traceable Knowledge Cards for product research, technical research, and ongoing knowledge management.

Capability map

---
config:
  flowchart:
    nodeSpacing: 16
    rankSpacing: 32
---
flowchart LR
  G["DSH Research Graph"] --> O["Organize research"] & K["Capture knowledge"] & R["Extend research"]
  O --> O1["Cross-workspace topics"] & O2["Conversation graph
Branches · Merges
Subagent records"]
  K --> K1["History search
Sources · Digests"] & K2["Knowledge Cards
AI extraction · Review · Revisions"]
  R --> R1["Synthesis · Frozen materials"] & R2["Follow-up discussions
Markdown export"]
  classDef brand fill:#2563eb,stroke:#2563eb,color:#fff
  classDef group fill:#eff6ff,stroke:#93c5fd,color:#1e3a8a
  classDef feature fill:#f8fafc,stroke:#cbd5e1,color:#0f172a
  class G brand
  class O,K,R group
  class O1,O2,K1,K2,R1,R2 feature