dsh-scholar: An AI Research Workspace for Computational Research on DeepSeek Harness
lzszq/dsh-scholar
DSH Scholar is a DeepSeek Harness plugin that provides an integrated research workspace for computational research, combining project conversations, materials, code, experiments, evidence, and TeX manuscripts with governed execution and traceable methodology.
dsh-scholar is a DSH plugin for DeepSeek Harness that provides a recoverable project environment for computational research such as machine learning, data science, and bioinformatics. It unifies conversations, materials, code, experiments, evidence, and TeX manuscripts, with stage-aware guidance, controlled execution, and traceable methodology. Configure local, Docker, or remote SSH environments via Runner Profiles, and rely on the default gate-only mode to keep research gates intact.
How to Install
dsh plugin --profile web add github:lzszq/dsh-scholar- Category
- Data & Knowledge
- Platform
- DSH Plugin
- Author
- lzszq
- Distribution
- Plugin
dsh-scholar Key Features
dsh-scholar Repo Summary
What Does It Do?
DSH Scholar is a DSH plugin for DeepSeek Harness that provides an AI research workspace for computational research, such as machine learning, data science, and bioinformatics. It solves the problem of scattered project conversations, materials, code, data, experiments, evidence, and TeX manuscripts by keeping them in one recoverable project. Core capabilities include stage-aware research guidance, governed research workflow, controlled execution, integrated workspace, traceable methodology, and visible collaboration.
Core Features
- Stage-aware research guidance: supports natural conversation, Grill Me intake, file upload, visual-model input, explicit slash commands, and an authoritative next-step prompt for the current research stage.
- Governed research workflow: Scope, Idea, Contract, Evidence, Direction, and Release decisions remain explicit, revision-bound, and auditable.
- Controlled execution: Runner Profiles describe local, local-Docker, or remote-SSH environments, including pinned container images and declared NVIDIA GPU capability.
- Integrated workspace: project-scoped Chat, editable files, session-bound Web terminals, run logs, artifacts, TeX source, compilation diagnostics, and PDF preview share the same context.
- Traceable methodology: Protocol revisions, run classifications, synthesis requests, assurance results, reviewer findings, knowledge-pack activation, and claim-to-evidence links are recorded as durable research state.
- Visible collaboration: Trajectory and Topology expose subagent parent-child relationships, status, follow-ups, and outputs.
How to Use This Plugin?
After enabling it in DSH, you can start from a new question or continue existing work. Use Grill Me to collect the project Brief and slash commands to control research stages. Configure the execution environment by selecting a Runner Profile (local, Docker, or remote SSH) in Settings → Execution environment. Formal experiments must bind immutable code and data snapshots, a frozen Protocol, and an explicit Runner Profile. The default gate-only mode ensures agents cannot impersonate a Human principal, fabricate accepted Evidence, or bypass a research Gate; full-auto mode only auto-approves allowlisted Scope, Idea, Contract, and Budget Gates of an exact registered FixtureProfile.
This page is an independent rewrite of the plugin's official README — for authoritative documentation and the latest changes, refer to the source: lzszq/dsh-scholar. The plugin is third-party code that runs on your machine once installed; inclusion does not imply endorsement — please review the source before installing.
DSH Plugin FAQ
