1692775560/dsh-Mimir-Academic-research

Mimir — 一站式科研工作台插件：LaTeX 论文边写边编译、arXiv 文献管理、实验追踪、指标图表、GPU 服务器 SSH 任务编排，管理科研全周期。An open-source research workbench plugin for the whole research cycle.

What it solves

Mimir provides a unified, AI-driven workbench for the entire academic research lifecycle. It eliminates the need to jump between disparate tools for literature review, experiment tracking, LaTeX writing, GPU management, and presentation preparation, consolidating these into a single workspace integrated with an AI agent.

How it works

It operates as a plugin for the DeepSeek Harness (dsh), providing a web-based workbench with nine specialized views. An AI agent drives the workflow using a set of slash commands (e.g., /research-plan, /paper-write) and specialized tools for searching arXiv, managing remote GPU jobs, and compiling LaTeX. It also includes eleven bundled "research skills" to automate tasks like novelty checks and citation audits.

Who it’s for

Academic researchers and students who need a structured environment to manage their research pipeline, from initial ideation and literature search to final paper submission and group meeting presentations.

Highlights

  • Nine-View Workbench: Dedicated tabs for Overview, Paper (LaTeX studio), Library (arXiv/web search), Experiments (metric charts), Figures, Meetings (PPT generation), Servers (GPU fleet management), Ledger (research journal), and Venues (conference deadlines).
  • Integrated LaTeX Studio: Overleaf-style editing with real-time compilation and AI-assisted fixes.
  • Agentic Research Tools: Built-in tools for web search (via SearXNG), arXiv search, and remote compute job submission.
  • Research Ledger: A humanized journal that auto-captures idea evolution into a worktree and generates progress reports.
  • Conference Tracking: A built-in catalog of CCF conference deadlines and a per-project watchlist.

Related

  • Project
    dream-num/dsh-univer-office

    A plugin for DeepSeek Harness that enables an AI agent to create, edit, and manage office documents like spreadsheets, presentations, and reports using natural language.

  • Project
    milanglacier/minuet-ai.nvim

    Minuet is a Neovim plugin that adds AI‑powered code completion. It talks to any OpenAI‑compatible or FIM‑compatible LLM (OpenAI, Claude, Ollama, Llama‑cpp, etc.) via curl, and can feed suggestions to virtual‑text, nvim‑cmp, blink‑cmp, or Neovim’s built‑in LSP/inline‑completion. It also offers an experimental “next‑edit prediction” (Duet) mode. Install via lazy.nvim or LuaRocks, configure the provider, API key and UI preferences, then trigger completions with the supplied keymaps.

  • Project
    Miaotofu01/Study-Mate

    StudyMate is a Node.js‑based AI tutoring system for math and CS, delivered as a DeepSeek Harness plugin (and also as Antigravity, Codex, or ChatGPT plugins). It builds curriculum roadmaps, renders markdown lessons, saves progress in a local workspace, and can export offline HTML. Install via `npx @yunmiao/studymate@latest install`, then converse with the AI to pick subjects, get lessons, practice, and assess.

  • Project
    dream-num/univer-workspace

    Univer Workspace is an open‑source, self‑hosted office suite (Sheets, Docs, Slides, tables, boards) that integrates AI agents via a local desktop app and a CLI. Agents edit documents in isolated “Worktrees,” then humans review and merge the changes. The system consists of a Browser UI, a central Server (OpenAPI‑driven), an Agent app built on DeepSeek Harness, and a CLI for automation. It supports fine‑grained access control, custom auth, and can be run with Node 24+ and pnpm 11.

  • Project
    plinder-org/plinder

    PLINDER is a large, curated protein‑ligand interaction dataset (400k+ complexes) with rich annotations and a Python library for easy download, querying, and evaluation of ML models in structural biology.