← Back to home@raktim-mondol

academic-harness

Academic Harness as a DeepSeek Harness (DSH) profile plugin: research persona, scientific skills catalogue, living lab notebook, and specialist subagents.

Stars
1
Language
Python
Created
Aug 28, 2026
Updated
Oct 26, 2026
GitHub repo

Introduction

Academic Harness

verify DeepSeek Harness 0.2.1+

A research workbench for DeepSeek Harness — literature and web discovery, verbatim paper memory, a writing oracle for LaTeX, systematic-review and hypothesis ledgers, 730 scientific skills, and local self-improvement, all inside the DSH web UI.

Academic Harness is a DSH profile: it installs as a plugin, adds a preset with a research persona and academic tools, and keeps the general-purpose tools available on every preset.

Architecture overview

Why Academic Harness

PrincipleWhat it means in practice
Evidence, not citation-shaped guessesPaperMemory stores papers as content-addressed Markdown and anchors claims to exact quote spans. quote_check and trace verify a quotation before it becomes a citation; an empty cite means do not invent one. Read more
A writing oracle with a gateThe vendored ah_* engine inventories every number, citation, unit, and claim in a LaTeX tree. A turn closes only when it introduced no open blocker or major. Read more
Auditable research ledgersSystematic reviews and hypothesis tournaments live in append-only logs under the workspace, so a resumed session sees the same protocol, screening decisions, and ratings. Reviews · Tournaments
Discovery across the real literatureOpenAlex, Semantic Scholar, PubMed/Europe PMC, arXiv, and Crossref through one literature_search entry point, plus Consensus, Parallel, Firecrawl, Scite, CORE, Elicit, and FutureHouse. Read more
A lab notebook that survives context lossA JSONL notebook shared across the delegation tree, a schema-validated scientific_result card, and deletion-only reply folding at five levels. Read more
Local-first by designWorkspace search (zvec-grep), PaperMemory, TextFold, ledgers, and the RSI store stay on disk. No key is required to boot. Read more

Install

Requires DeepSeek Harness 0.2.1 or later.

npm install -g @deepseek-ai/dsh

Then either:

A — from the DSH Web UI (recommended): open Plugins → Add plugin, paste github:raktim-mondol/academic-harness, click Install, and start a new chat.

B — a dedicated CLI profile:

dsh plugin --profile academic-harness add github:raktim-mondol/academic-harness
dsh --profile academic-harness

Confirm the preset selector at the top of the message box reads Academic Harness. The academic tools are preset-only; a session left on Standard/PTC will fail with tools[name] is not a function.

Full instructions, migration from researchcraft, troubleshooting, and the "one DSH surface at a time" rule are in Install and run.

What is inside

Capability map

SurfaceHighlightsGuide
Search and discoveryliterature_search router, OpenAlex, Semantic Scholar, PubMed, arXiv, Crossref, Consensus, Parallel, Firecrawl, Scite, Tavily, Exa, Perplexity, Jina, CORE, Elicit, FutureHouseSearch
Papers and evidencepaper_download, paper_fold, pdf_to_markdown, PaperMemory's 14 tools, integrity_check, Paper2AgentPapers
Writing and citationah_* writing oracle and gate, citation, manuscript_citations, LaTeX, scientific-figure-making, diagram-design, image_generate, mermaid_render (Pele)Writing
Reviews and hypothesesreview PRISMA-style ledger, coscientist Glicko-2 tournament, published-results feedback, cross-session priorsResearch
Clinical and policy recordsclinicaltrials, openfda, dataset_search, journal_policy, funder_policyResearch
Workspace and notebookzvec-grep semantic search, lab notebook, scientific_result, fold_text, research_template, sci_inspectWorkspace
Compute and delegationrunpod_run/modal_run/vastai_run, subagent_pro, subagent_vision, specialist briefs, agent-browserCompute · Agents
Skills730 bundled skills: 140 domain, 16 methodology, 503 expert profiles, 23 drug-discovery, plus writing, figures, agents, and computeSkills
Self-improvementLocal RSI: capture, diagnose, admit, inject, compare against control, promote or quarantineRSI
ConfigurationSettings → Academic Harness API keys; every credential is optional at installConfiguration

The complete tool list, with scope and links, is the tool index. The architecture guide explains which tools are available on every preset and which are preset-only.

How a request works

Request lifecycle

Discovery finds candidate papers, paper_resolve collapses their identifiers, and integrity_check reports retraction status. A downloaded PDF is stored as content-addressed Markdown in PaperMemory, and a quotation must pass quote_check or trace before the agent treats it as evidence. The notebook records the work; scientific_result records the final finding.

Documentation

Start hereGo deeperReference
Install and runSearchTool index
ArchitecturePapers and evidenceConfiguration
Documentation homeWritingChangelog
ResearchDevelopment
WorkspaceOptional tools
Compute · Agents · Skills · RSIEngine notes

Requirements and scope

  • DSH 0.2.1+. The plugin's bundle patches the web-app layer, so the profile must include @deepseek-ai/dsh-web-app; the standard web profile does.
  • A preset check matters. The research persona, search connectors, PaperMemory, zvec-grep, paper tools, citation/review/tournament tools, and the subagent_pro/subagent_vision routes are scoped to the Academic Harness preset. Only the general-purpose tools (notebook, fold, images, LaTeX, PDF, Mermaid, compute, templates) are on every preset.
  • Keys are optional. No credential is needed to install or start; each connector stays disabled until its key is present. Some runtimes install in the background on first use — see Architecture.
  • One DSH surface at a time. dsh-web, dsh-tui, dsh-martty, and academic-harness share $DSH_HOME, port 3080, and the zvec-grep daemon. Stop the previous one before starting another; see Install.
  • Renamed in v0.16.0 from dsh-researchcraft / ResearchCraft. Old env names are still honored; migration is in Install.

Development

npm install       # once, for the Settings page build
npm run build     # after any client/ change
npm run docs:diagrams   # regenerate the SVG figures from docs/diagrams/*.mmd

Server-side code is plain ESM JS with no build step. Tests are plain Node scripts; see Development for the full suite and the paper_fold live test.

License

MIT — see LICENSE. Scientific skills are vendored or adapted from several open-source catalogues; NOTICE records exactly what was copied, renamed, or adapted from each.