An open-source, local-first AI learning workbench
264
stars
1,785
commits
TypeScript
primary language
Sep 12, 2026
updated
README
简体中文 | English
An open-source, local-first AI learning workbench
It's not that learning is hard — it's that learning tools are too scattered.
Study materials, note-taking, mind maps, quizzes, translation, and flashcard review — all in one unified learning workbench.
Think of it as: research notebook + knowledge workspace + mind mapping + practice + translation but they all share the same learning data and workflow.
Website · Download · Quick Start · User Guide · Report Issues · Contributing
Why DeepStudent
Learning workflows are spread across too many tools — read here, take notes there, build mind maps elsewhere, review in yet another app. PDF readers, mind-mapping tools, translation apps, note-taking tools, LMS platforms, arXiv, flashcard apps, AI assistants… every tool is its own silo. Once your learning data is scattered, you spend more energy shuttling between tools than actually learning.
DeepStudent's answer: give AI native read-write access to all your learning data. One sentence from you, and it generates a mind map from your textbook, creates questions from your materials, turns key points into flashcards, searches and downloads papers, or researches the web and writes conclusions into your notes — all without leaving the workbench.
What You Get
| Capability | DeepStudent |
|---|---|
| AI Q&A over materials | ✓ 12 providers |
| Cross-platform out-of-box | ✓ Win/Mac/Linux/Android |
| Smart memory system | ✓ AI-driven persistent |
| Note-taking system | ✓ rich text + tags + AI |
| AI-generated mind maps | ✓ |
| AI quiz + practice modes | ✓ |
| Flashcards + SRS | ✓ APKG / FSRS |
| Translation + close reading | ✓ 7 domain presets |
| Cross-module data flow | ✓ unified data layer |
The core idea isn't "more features" — it's the unified data layer. The same material can be read, queried, turned into a mind map, used to generate quizzes, made into flashcards, researched, and written back — no data shuttling between apps.
📊 More dimensions (infrastructure · ecosystem · collaboration)
| Capability | DeepStudent |
|---|---|
| Local-first storage | ✓ |
| Cloud sync | △ experimental (backup-style, not real-time collab) |
| Open source / self-host | ✓ AGPL-3.0 |
| Unified data layer (VFS) | ✓ |
| Auto-index on import | ✓ incl. OCR |
| Mind map ↔ outline mode | ✓ |
| Deep research + papers | ✓ multi-engine + arXiv |
| AI essay correction | ✓ multi-scenario |
| MCP ecosystem / skills | ✓ native + presets1 |
| Real-time collaboration | ✗ |
| Community & ecosystem | △ new project |
1 agent browser automation: Windows + macOS only（Linux has WebKitGTK eval bridge code, but Agent tool surface remains closed）
Core Capabilities
1. Study with AI Chat
Study around your materials, not just general chat.
- Multi-modal input (drag & drop images / PDF / Word) with multi-turn conversation
- Reference panel for injecting knowledge base notes or textbooks into context, with real-time token estimation
- Deep reasoning mode (chain-of-thought), showing the full thinking process
- Multi-tab sessions & session branching — explore different approaches
- Authority modes Ask / Plan / Craft (default Craft): read-only · plan-then-approve · execute with tool approvals
- Learning desktop (OS / Workbench mode): multi-window study shell around chat and resources
- Multi-model comparison (experimental): side-by-side answers from multiple models
- Session grouping, group-level System Prompt, default skill configuration
- Sub-agent execution (experimental): automatic task decomposition, background completion
📸 View Screenshots
2. Learning Hub
Organize materials, notes, questions, mind maps, translations, and flashcards in one place.
- Full-format management: notes / textbooks / question banks / mind maps
- Auto-vectorization pipeline on import (OCR → chunking → embedding → indexing), with real-time status
- Built-in PDF / DOCX reader with dual-page view and bookmarks
- Reading mode toggle — prevents keyboard popup on mobile during scrolling
- Content search across sessions and resources with session tagging
- Resource export with format-specific adapters
- Unified data source for downstream Q&A, mind maps, question generation, and flashcards
📸 View Screenshots
3. Knowledge Mind Maps
Structure your knowledge, not just get answers.
- Generate a complete knowledge structure from a single sentence (e.g., "generate a high school biology mind map")
- Multi-round conversational editing of nodes
- Toggle between outline view and mind map view, right-click menu editing
- Node masking for recitation practice
📸 View Screenshots
4. Question Sets & Practice
Turn textbooks and exam papers into practice-ready question banks.
- Upload textbooks / exam papers, AI auto-extracts or generates question sets
- Daily practice, timed practice, mock exams with auto-grading
- Question history view — review past practice sessions and track progress over time
- AI deep analysis of knowledge points and problem-solving approaches
- Mastery tracking by knowledge point (feeds weak-point profile & bounded FSRS review bias)
📸 View Screenshots
5. Anki Smart Flashcards
Push understanding into long-term memory.
- Trigger card creation via natural language in chat (e.g., "turn this document into flashcards"), with batch generation
- Visual template editor (HTML / CSS / Mustache) with real-time preview
- Task board for batch card creation progress tracking with checkpoint resume
- 3D flip preview, one-click sync to Anki
📸 View Screenshots
6. PDF / DOCX Smart Reader
Study around your documents, not just open them.
- Full format support: PDF, DOCX
- Split-screen: chat on the left, read on the right
- Select pages or passages to auto-inject into chat context
- AI responses can include page number references
📸 View Screenshots
📋 More capabilities (Translation · Essay · Research · Papers · Memory · Skills · Data Governance)
7. Translation Workbench
Translation as part of your learning chain.
- Full-text translation with synchronized left-right scrolling
- Paragraph-level bilingual comparison, ideal for close reading
- 7 domain presets: general / academic / technical / literary / legal / medical / casual
- Custom prompts and terminology preferences
📸 View Screenshots
8. AI Essay Grading
Chinese and English essay grading and polishing.
- Multi-scenario: Gaokao / IELTS / TOEFL / CET-4/6 / Postgraduate entrance exam
- Multi-dimensional AI scoring (vocabulary, grammar, coherence, etc.) with iterative grading
- Revision suggestions with highlights
- Sentence-by-sentence polish comparison
- Customizable scoring dimensions and grading settings
📸 View Screenshots
9. Deep Research
Multi-step, long-chain research agent.
- Interactive confirmation of research depth and format preferences before starting
- Automatic task decomposition: define objectives → web search → local retrieval → analysis → report generation
- 7 search engines supported (Google CSE / SerpAPI / Tavily / Brave / SearXNG / Zhipu / Bocha)
- Reports auto-saved as notes
📸 View Screenshots
10. Academic Paper Search & Management
One-stop paper retrieval, download, and citation.
- Search via arXiv / OpenAlex with structured metadata
- Batch PDF download, auto-saved to VFS, multi-source fallback (arXiv → Export mirror → Unpaywall)
- SHA256 deduplication
- BibTeX, GB/T 7714, APA citation formats
- DOI auto-resolution to open-access links
📸 View Screenshots
11. Smart Memory
Gets smarter the more you use it.
Inspired by mem0 and memU, implementing a complete memory lifecycle on desktop.
- Auto-extracts user facts after each conversation (identity / preferences / goals / subject status)
- Vector comparison of new vs. existing memories, LLM decides ADD / UPDATE / APPEND / DELETE / NONE
- Batch memory write with write idempotency for data integrity
- Aggregated into user profile, auto-injected into subsequent conversations
- Tag system: 90-day inactivity → downweight; frequent hits → upweight; search hits auto-rehabilitate
- Browse, edit, batch delete, export
- Privacy mode: one-click disable of all external API calls
📸 View Screenshots
12. Skill System & MCP Extensions
An extensible workbench, not a closed feature set.
- Skills load AI capabilities on demand — tools only loaded when activated, saving tokens
- 40+ built-in skills/tool groups: Cards · Research · Paper · Tutor · Literature Review · Exam Analysis · Mind Map · Q-Bank · Memory · Session Manager · Office Suite · Todo · Canvas Notes · Image Generation · Web Fetch · Subagent Workspace, and more
- community skill marketplace skill marketplace: browse / verify / install community skills with risk scan
- Three-tier loading (Built-in → Global → Project-level), custom skills via SKILL.md
- MCP protocol compatible (OAuth for supported presets), connecting external tools like Arxiv, Context7
- 12 built-in provider templates (incl. Gemini), plus custom multi-protocol endpoints (Anthropic / Grok / Ollama, etc.)
- Adapted for Gemini 3, GPT-5.5 / GPT-5.2 Pro, GLM-5, DeepSeek V4, Seed 2.0, Kimi K2.5, and more
📸 View Screenshots
13. Local-First & Data Governance
Your learning data stays under your control.
- All data stored locally (SQLite + LanceDB + Blob)
- Full ZIP backup & recovery (incremental backup retired), data import/export
- AES-256-GCM encryption for sensitive data, dual-slot A/B switching
- Audit logs for full traceability
- Cloud sync (experimental): desktop WebDAV / S3-compatible / experimental FTP; Android is WebDAV only. Whole-package backup is a full ZIP single-object PUT (no incremental transfer, dedup, or CDC). The default cloud ZIP is a portable archive and cannot slot-restore. When a cloud E2EE password is configured, Backup to Cloud Now exports an encrypted full-fidelity ZIP; if that password cannot be read, export is refused instead of silently writing a portable archive. Not real-time collaboration.
Installation
Download the latest version from GitHub Releases:
| Platform | Package | Architecture |
|---|---|---|
| macOS | .dmg | Apple Silicon / Intel |
| Windows | .exe | x86_64 |
| Linux | .deb / .AppImage | x86_64 / arm64 |
| Android | .apk | arm64 |
iOS: local source build only via Xcode (no App Store package). See Build Configuration Guide.
Getting Started
After your first launch, try this path:
- Import a PDF / textbook / paper
- Start a conversation around the material
- Generate a mind map
- Create a question set or flashcards
- Use translation / close reading to deepen understanding
This path best demonstrates DeepStudent's core value: not isolated features, but a complete learning chain.
What Makes It Different Technically
If you're a developer, this section is for you.
- Unified learning data layer — One material can be read, searched, structured, practiced, memorized; upper-layer apps are different views of the same data
- Local-first — Metadata (SQLite), vector indices (LanceDB), file content (Blob) all stored locally
- Skill-driven architecture — Capabilities load on demand, combined with MCP protocol and multi-search-engine integration
- End-to-end loop — Import → understand → research → structure → practice → flashcards → memory
Architecture Overview
DeepStudent
├── Learning Materials: PDF / DOCX / textbooks / questions / notes / mind maps / translations
├── Unified Data Layer: VFS + SQLite metadata + LanceDB vector index + Blob file storage
├── Workflow Layer: chat / research / mind map / question sets / translation / essay / memory
├── Extension Layer: Skills / MCP / multi-search engines / custom model providers
└── Interface Layer: Desktop (macOS · Windows · Linux) & Mobile (Android; iOS source-build only)
View Code Structure
DeepStudent
├── src/ # React Frontend
│ ├── features/ # Feature modules (19: chat / learning-hub / mindmap / notes / pdf / practice / settings / todo / workbench / voice-input, etc.)
│ │ └── chat/ # Chat V2 Conversation Engine
│ │ ├── core/ # Store / Types / Registries
│ │ ├── skills/ # Skill System (builtin / builtin-tools / loader)
│ │ ├── components/ # Chat UI Components
│ │ └── plugins/ # Plugins (event handling, block rendering)
│ ├── components/ # Shared UI Components
│ ├── stores/ # Zustand State Management
│ ├── mcp/ # MCP Client & Built-in Tool Definitions
│ ├── essay-grading/ # Essay Grading Frontend
│ ├── translation/ # Translation Workbench Frontend
│ ├── command-palette/ # Command Palette (shortcuts / favorites / pinyin search)
│ ├── dstu/ # DSTU Resource Protocol & VFS API
│ ├── api/ # Frontend API Layer (Tauri invoke wrappers)
│ ├── hooks/ # React Hooks (theme, hotkeys, platform detection, etc.)
│ ├── services/ # Service Layer (update checker, audit, logging, etc.)
│ ├── engines/ # Rendering Engines (Markdown, code highlighting, etc.)
│ ├── debug-panel/ # Debug Panel & Dev Tools
│ └── locales/ # i18n Internationalization (CN / EN)
├── src-tauri/ # Tauri / Rust Backend
│ └── src/
│ ├── chat_v2/ # Chat Pipeline & Tool Executor
│ ├── llm_manager/ # Multi-Model Management & Adaptation (12 built-in providers)
│ ├── vfs/ # Virtual File System & Vectorized Indexing
│ ├── dstu/ # DSTU Resource Protocol Backend
│ ├── tools/ # Web Search Engine Adapters (7 engines)
│ ├── memory/ # Smart Memory (self-evolving profile / 3-layer arch / LLM decision)
│ ├── mcp/ # MCP Protocol Implementation
│ ├── translation/ # Translation Pipeline Backend
│ ├── cloud_storage/ # Cloud Sync (S3 / WebDAV; FTP experimental)
│ ├── data_governance/ # Backup, Audit, Migration
│ ├── essay_grading/ # Essay Grading Backend
│ ├── qbank_grading/ # Question Bank AI Grading
│ ├── crypto/ # Encryption & Secure Storage (AES-256-GCM)
│ ├── multimodal/ # Multimodal Processing
│ ├── ocr_adapters/ # OCR Adapters (6 engines)
│ └── llm_usage/ # LLM Usage Tracking
├── docs/ # User Docs & Design Docs
├── tests/ # Vitest Unit Tests & Playwright CT
└── .github/workflows/ # CI / Release Automation
Tech Stack
| Area | Technology |
|---|---|
| Frontend Framework | React 18 + TypeScript 5.6 + Vite 6 |
| UI Components | Tailwind CSS 3 + Radix UI + Phosphor Icons |
| Desktop / Mobile | Tauri 2 (Rust) — macOS · Windows · Linux · Android · iOS |
| Data Storage | SQLite (Rusqlite) + LanceDB (Vector Search) + Local Blob |
| State Management | Zustand 5 + Immer |
| Editors | Milkdown (Markdown) + CodeMirror (Code) |
| Document Processing | PDF.js + pdfium-render + Multi-engine OCR |
| Search Engines | Google CSE · SerpAPI · Tavily · Brave · SearXNG · Zhipu · Bocha |
| CI / CD | GitHub Actions — lint · type-check · build · Release Please |
Development
Prerequisites
| Tool | Version | Description |
|---|---|---|
| Node.js | v20+ | Frontend build |
| Rust | Stable | Backend compilation (recommended via rustup) |
| npm | — | Package manager (do not mix with pnpm / yarn) |
Local Development
git clone https://github.com/helixnow/deep-student.git
cd deep-student
npm ci
npm run tauri dev
For more build and packaging info, see BUILD-CONFIG.md
Documentation
| Document | Description |
|---|---|
| Quick Start | 10-minute getting started guide (Chinese, online version) |
| User Guide | Complete feature documentation for desktop & mobile (Chinese, online version) |
| Build Configuration | Cross-platform build & packaging |
| Changelog | Version change history |
| Security Policy | Vulnerability reporting process |
Roadmap
On the way to v1.0. Near-term focus:
- User experience & stability improvements
- Desktop & mobile UI/UX optimization
- Cloud sync & backup enhancements
- Resource full lifecycle management optimization
- Skill & workflow expansion
- More model integrations & adaptations
Project History
DeepStudent started as a Python demo in March 2025 and has evolved through nearly a year of continuous iteration:
| Date | Milestone |
|---|---|
| 2025.03 | 🌱 Project Genesis — Python demo prototype, validating AI-assisted learning |
| 2025.05 | 🔄 Tech Stack Migration — Transitioned to Tauri + React + Rust architecture |
| 2025.08 | 🎨 Major UI Overhaul — Migrated to shadcn-ui, introduced Chat architecture & knowledge base vectorization |
| 2025.09 | 📝 Note System & Templates — Milkdown editor integration, Anki template batch import |
| 2025.10 | 🌐 i18n & E2E Testing — Full i18n coverage, Playwright testing, Lance vector storage migration |
| 2025.11 | 💬 Chat V2 Architecture — New conversation engine (multi-model comparison, tool event system, snapshot monitoring) |
| 2025.12 | ⚡ Performance — Parallel session loading, config caching, DSTU resource protocol |
| 2026.01 | 🧩 Skill System & VFS — File-based skill loading, unified Virtual File System |
| 2026.02 | 🚀 Open Source Release — Renamed to DeepStudent, released v0.9.23; added Translation Workbench, Cloud Sync, Session Branching, Smart Memory enhancements, and more |
| 2026.03 | 🐧 Linux & Hardening — Linux build support (deb/AppImage); Todo & Pomodoro system; question history view; model capability auto-detection; reading mode for mobile; content search & session tagging; resource export; memory batch write & idempotency; cross-session permission checks; released v0.9.30–v0.9.35 |
| 2026.04–06 | 🧱 Architecture & Stability — DeepSeek V4 / V3.2 adapter family; frontend features/ modular refactor and Phosphor icon migration; real-environment multi-instance E2E test system; cloud sync convergence remediation; released v0.9.36–v0.9.40 |
Contributing
Help make DeepStudent better.
- Read CONTRIBUTING.md for development workflow
- Ensure
npm run lintand type checks pass before submitting a PR - Bugs & suggestions via Issues
License
Acknowledgments
DeepStudent would not be possible without these outstanding open-source projects:
Frameworks & Runtimes Tauri · React · Vite · TypeScript · Rust · Tokio
Editors & Content Rendering Milkdown · ProseMirror · CodeMirror · KaTeX · Mermaid · react-markdown
UI & Styling Tailwind CSS · Radix UI · Phosphor Icons · Framer Motion · Recharts · React Flow
Data & State LanceDB · SQLite / rusqlite · Apache Arrow · Zustand · Immer · Serde
Document Processing PDF.js · pdfium-render · docx-preview · docx-rs · umya-spreadsheet · Mustache · DOMPurify
Internationalization & Toolchain i18next · date-fns · Vitest · Playwright · ESLint · Sentry
Made with ❤️ for Lifelong Learners
Contributors
Similar repos
Languages
TypeScript
50.3%
Rust
46.1%
CSS
2.3%
An open-source, local-first AI learning workbench
264
stars
1,785
commits
TypeScript
primary language
Sep 12, 2026
updated
README
简体中文 | English
An open-source, local-first AI learning workbench
It's not that learning is hard — it's that learning tools are too scattered.
Study materials, note-taking, mind maps, quizzes, translation, and flashcard review — all in one unified learning workbench.
Think of it as: research notebook + knowledge workspace + mind mapping + practice + translation but they all share the same learning data and workflow.
Website · Download · Quick Start · User Guide · Report Issues · Contributing
Why DeepStudent
Learning workflows are spread across too many tools — read here, take notes there, build mind maps elsewhere, review in yet another app. PDF readers, mind-mapping tools, translation apps, note-taking tools, LMS platforms, arXiv, flashcard apps, AI assistants… every tool is its own silo. Once your learning data is scattered, you spend more energy shuttling between tools than actually learning.
DeepStudent's answer: give AI native read-write access to all your learning data. One sentence from you, and it generates a mind map from your textbook, creates questions from your materials, turns key points into flashcards, searches and downloads papers, or researches the web and writes conclusions into your notes — all without leaving the workbench.
What You Get
| Capability | DeepStudent |
|---|---|
| AI Q&A over materials | ✓ 12 providers |
| Cross-platform out-of-box | ✓ Win/Mac/Linux/Android |
| Smart memory system | ✓ AI-driven persistent |
| Note-taking system | ✓ rich text + tags + AI |
| AI-generated mind maps | ✓ |
| AI quiz + practice modes | ✓ |
| Flashcards + SRS | ✓ APKG / FSRS |
| Translation + close reading | ✓ 7 domain presets |
| Cross-module data flow | ✓ unified data layer |
The core idea isn't "more features" — it's the unified data layer. The same material can be read, queried, turned into a mind map, used to generate quizzes, made into flashcards, researched, and written back — no data shuttling between apps.
📊 More dimensions (infrastructure · ecosystem · collaboration)
| Capability | DeepStudent |
|---|---|
| Local-first storage | ✓ |
| Cloud sync | △ experimental (backup-style, not real-time collab) |
| Open source / self-host | ✓ AGPL-3.0 |
| Unified data layer (VFS) | ✓ |
| Auto-index on import | ✓ incl. OCR |
| Mind map ↔ outline mode | ✓ |
| Deep research + papers | ✓ multi-engine + arXiv |
| AI essay correction | ✓ multi-scenario |
| MCP ecosystem / skills | ✓ native + presets1 |
| Real-time collaboration | ✗ |
| Community & ecosystem | △ new project |
1 agent browser automation: Windows + macOS only（Linux has WebKitGTK eval bridge code, but Agent tool surface remains closed）
Core Capabilities
1. Study with AI Chat
Study around your materials, not just general chat.
- Multi-modal input (drag & drop images / PDF / Word) with multi-turn conversation
- Reference panel for injecting knowledge base notes or textbooks into context, with real-time token estimation
- Deep reasoning mode (chain-of-thought), showing the full thinking process
- Multi-tab sessions & session branching — explore different approaches
- Authority modes Ask / Plan / Craft (default Craft): read-only · plan-then-approve · execute with tool approvals
- Learning desktop (OS / Workbench mode): multi-window study shell around chat and resources
- Multi-model comparison (experimental): side-by-side answers from multiple models
- Session grouping, group-level System Prompt, default skill configuration
- Sub-agent execution (experimental): automatic task decomposition, background completion
📸 View Screenshots
2. Learning Hub
Organize materials, notes, questions, mind maps, translations, and flashcards in one place.
- Full-format management: notes / textbooks / question banks / mind maps
- Auto-vectorization pipeline on import (OCR → chunking → embedding → indexing), with real-time status
- Built-in PDF / DOCX reader with dual-page view and bookmarks
- Reading mode toggle — prevents keyboard popup on mobile during scrolling
- Content search across sessions and resources with session tagging
- Resource export with format-specific adapters
- Unified data source for downstream Q&A, mind maps, question generation, and flashcards
📸 View Screenshots
3. Knowledge Mind Maps
Structure your knowledge, not just get answers.
- Generate a complete knowledge structure from a single sentence (e.g., "generate a high school biology mind map")
- Multi-round conversational editing of nodes
- Toggle between outline view and mind map view, right-click menu editing
- Node masking for recitation practice
📸 View Screenshots
4. Question Sets & Practice
Turn textbooks and exam papers into practice-ready question banks.
- Upload textbooks / exam papers, AI auto-extracts or generates question sets
- Daily practice, timed practice, mock exams with auto-grading
- Question history view — review past practice sessions and track progress over time
- AI deep analysis of knowledge points and problem-solving approaches
- Mastery tracking by knowledge point (feeds weak-point profile & bounded FSRS review bias)
📸 View Screenshots
5. Anki Smart Flashcards
Push understanding into long-term memory.
- Trigger card creation via natural language in chat (e.g., "turn this document into flashcards"), with batch generation
- Visual template editor (HTML / CSS / Mustache) with real-time preview
- Task board for batch card creation progress tracking with checkpoint resume
- 3D flip preview, one-click sync to Anki
📸 View Screenshots
6. PDF / DOCX Smart Reader
Study around your documents, not just open them.
- Full format support: PDF, DOCX
- Split-screen: chat on the left, read on the right
- Select pages or passages to auto-inject into chat context
- AI responses can include page number references
📸 View Screenshots
📋 More capabilities (Translation · Essay · Research · Papers · Memory · Skills · Data Governance)
7. Translation Workbench
Translation as part of your learning chain.
- Full-text translation with synchronized left-right scrolling
- Paragraph-level bilingual comparison, ideal for close reading
- 7 domain presets: general / academic / technical / literary / legal / medical / casual
- Custom prompts and terminology preferences
📸 View Screenshots
8. AI Essay Grading
Chinese and English essay grading and polishing.
- Multi-scenario: Gaokao / IELTS / TOEFL / CET-4/6 / Postgraduate entrance exam
- Multi-dimensional AI scoring (vocabulary, grammar, coherence, etc.) with iterative grading
- Revision suggestions with highlights
- Sentence-by-sentence polish comparison
- Customizable scoring dimensions and grading settings
📸 View Screenshots
9. Deep Research
Multi-step, long-chain research agent.
- Interactive confirmation of research depth and format preferences before starting
- Automatic task decomposition: define objectives → web search → local retrieval → analysis → report generation
- 7 search engines supported (Google CSE / SerpAPI / Tavily / Brave / SearXNG / Zhipu / Bocha)
- Reports auto-saved as notes
📸 View Screenshots
10. Academic Paper Search & Management
One-stop paper retrieval, download, and citation.
- Search via arXiv / OpenAlex with structured metadata
- Batch PDF download, auto-saved to VFS, multi-source fallback (arXiv → Export mirror → Unpaywall)
- SHA256 deduplication
- BibTeX, GB/T 7714, APA citation formats
- DOI auto-resolution to open-access links
📸 View Screenshots
11. Smart Memory
Gets smarter the more you use it.
Inspired by mem0 and memU, implementing a complete memory lifecycle on desktop.
- Auto-extracts user facts after each conversation (identity / preferences / goals / subject status)
- Vector comparison of new vs. existing memories, LLM decides ADD / UPDATE / APPEND / DELETE / NONE
- Batch memory write with write idempotency for data integrity
- Aggregated into user profile, auto-injected into subsequent conversations
- Tag system: 90-day inactivity → downweight; frequent hits → upweight; search hits auto-rehabilitate
- Browse, edit, batch delete, export
- Privacy mode: one-click disable of all external API calls
📸 View Screenshots
12. Skill System & MCP Extensions
An extensible workbench, not a closed feature set.
- Skills load AI capabilities on demand — tools only loaded when activated, saving tokens
- 40+ built-in skills/tool groups: Cards · Research · Paper · Tutor · Literature Review · Exam Analysis · Mind Map · Q-Bank · Memory · Session Manager · Office Suite · Todo · Canvas Notes · Image Generation · Web Fetch · Subagent Workspace, and more
- community skill marketplace skill marketplace: browse / verify / install community skills with risk scan
- Three-tier loading (Built-in → Global → Project-level), custom skills via SKILL.md
- MCP protocol compatible (OAuth for supported presets), connecting external tools like Arxiv, Context7
- 12 built-in provider templates (incl. Gemini), plus custom multi-protocol endpoints (Anthropic / Grok / Ollama, etc.)
- Adapted for Gemini 3, GPT-5.5 / GPT-5.2 Pro, GLM-5, DeepSeek V4, Seed 2.0, Kimi K2.5, and more
📸 View Screenshots
13. Local-First & Data Governance
Your learning data stays under your control.
- All data stored locally (SQLite + LanceDB + Blob)
- Full ZIP backup & recovery (incremental backup retired), data import/export
- AES-256-GCM encryption for sensitive data, dual-slot A/B switching
- Audit logs for full traceability
- Cloud sync (experimental): desktop WebDAV / S3-compatible / experimental FTP; Android is WebDAV only. Whole-package backup is a full ZIP single-object PUT (no incremental transfer, dedup, or CDC). The default cloud ZIP is a portable archive and cannot slot-restore. When a cloud E2EE password is configured, Backup to Cloud Now exports an encrypted full-fidelity ZIP; if that password cannot be read, export is refused instead of silently writing a portable archive. Not real-time collaboration.
Installation
Download the latest version from GitHub Releases:
| Platform | Package | Architecture |
|---|---|---|
| macOS | .dmg | Apple Silicon / Intel |
| Windows | .exe | x86_64 |
| Linux | .deb / .AppImage | x86_64 / arm64 |
| Android | .apk | arm64 |
iOS: local source build only via Xcode (no App Store package). See Build Configuration Guide.
Getting Started
After your first launch, try this path:
- Import a PDF / textbook / paper
- Start a conversation around the material
- Generate a mind map
- Create a question set or flashcards
- Use translation / close reading to deepen understanding
This path best demonstrates DeepStudent's core value: not isolated features, but a complete learning chain.
What Makes It Different Technically
If you're a developer, this section is for you.
- Unified learning data layer — One material can be read, searched, structured, practiced, memorized; upper-layer apps are different views of the same data
- Local-first — Metadata (SQLite), vector indices (LanceDB), file content (Blob) all stored locally
- Skill-driven architecture — Capabilities load on demand, combined with MCP protocol and multi-search-engine integration
- End-to-end loop — Import → understand → research → structure → practice → flashcards → memory
Architecture Overview
DeepStudent
├── Learning Materials: PDF / DOCX / textbooks / questions / notes / mind maps / translations
├── Unified Data Layer: VFS + SQLite metadata + LanceDB vector index + Blob file storage
├── Workflow Layer: chat / research / mind map / question sets / translation / essay / memory
├── Extension Layer: Skills / MCP / multi-search engines / custom model providers
└── Interface Layer: Desktop (macOS · Windows · Linux) & Mobile (Android; iOS source-build only)
View Code Structure
DeepStudent
├── src/ # React Frontend
│ ├── features/ # Feature modules (19: chat / learning-hub / mindmap / notes / pdf / practice / settings / todo / workbench / voice-input, etc.)
│ │ └── chat/ # Chat V2 Conversation Engine
│ │ ├── core/ # Store / Types / Registries
│ │ ├── skills/ # Skill System (builtin / builtin-tools / loader)
│ │ ├── components/ # Chat UI Components
│ │ └── plugins/ # Plugins (event handling, block rendering)
│ ├── components/ # Shared UI Components
│ ├── stores/ # Zustand State Management
│ ├── mcp/ # MCP Client & Built-in Tool Definitions
│ ├── essay-grading/ # Essay Grading Frontend
│ ├── translation/ # Translation Workbench Frontend
│ ├── command-palette/ # Command Palette (shortcuts / favorites / pinyin search)
│ ├── dstu/ # DSTU Resource Protocol & VFS API
│ ├── api/ # Frontend API Layer (Tauri invoke wrappers)
│ ├── hooks/ # React Hooks (theme, hotkeys, platform detection, etc.)
│ ├── services/ # Service Layer (update checker, audit, logging, etc.)
│ ├── engines/ # Rendering Engines (Markdown, code highlighting, etc.)
│ ├── debug-panel/ # Debug Panel & Dev Tools
│ └── locales/ # i18n Internationalization (CN / EN)
├── src-tauri/ # Tauri / Rust Backend
│ └── src/
│ ├── chat_v2/ # Chat Pipeline & Tool Executor
│ ├── llm_manager/ # Multi-Model Management & Adaptation (12 built-in providers)
│ ├── vfs/ # Virtual File System & Vectorized Indexing
│ ├── dstu/ # DSTU Resource Protocol Backend
│ ├── tools/ # Web Search Engine Adapters (7 engines)
│ ├── memory/ # Smart Memory (self-evolving profile / 3-layer arch / LLM decision)
│ ├── mcp/ # MCP Protocol Implementation
│ ├── translation/ # Translation Pipeline Backend
│ ├── cloud_storage/ # Cloud Sync (S3 / WebDAV; FTP experimental)
│ ├── data_governance/ # Backup, Audit, Migration
│ ├── essay_grading/ # Essay Grading Backend
│ ├── qbank_grading/ # Question Bank AI Grading
│ ├── crypto/ # Encryption & Secure Storage (AES-256-GCM)
│ ├── multimodal/ # Multimodal Processing
│ ├── ocr_adapters/ # OCR Adapters (6 engines)
│ └── llm_usage/ # LLM Usage Tracking
├── docs/ # User Docs & Design Docs
├── tests/ # Vitest Unit Tests & Playwright CT
└── .github/workflows/ # CI / Release Automation
Tech Stack
| Area | Technology |
|---|---|
| Frontend Framework | React 18 + TypeScript 5.6 + Vite 6 |
| UI Components | Tailwind CSS 3 + Radix UI + Phosphor Icons |
| Desktop / Mobile | Tauri 2 (Rust) — macOS · Windows · Linux · Android · iOS |
| Data Storage | SQLite (Rusqlite) + LanceDB (Vector Search) + Local Blob |
| State Management | Zustand 5 + Immer |
| Editors | Milkdown (Markdown) + CodeMirror (Code) |
| Document Processing | PDF.js + pdfium-render + Multi-engine OCR |
| Search Engines | Google CSE · SerpAPI · Tavily · Brave · SearXNG · Zhipu · Bocha |
| CI / CD | GitHub Actions — lint · type-check · build · Release Please |
Development
Prerequisites
| Tool | Version | Description |
|---|---|---|
| Node.js | v20+ | Frontend build |
| Rust | Stable | Backend compilation (recommended via rustup) |
| npm | — | Package manager (do not mix with pnpm / yarn) |
Local Development
git clone https://github.com/helixnow/deep-student.git
cd deep-student
npm ci
npm run tauri dev
For more build and packaging info, see BUILD-CONFIG.md
Documentation
| Document | Description |
|---|---|
| Quick Start | 10-minute getting started guide (Chinese, online version) |
| User Guide | Complete feature documentation for desktop & mobile (Chinese, online version) |
| Build Configuration | Cross-platform build & packaging |
| Changelog | Version change history |
| Security Policy | Vulnerability reporting process |
Roadmap
On the way to v1.0. Near-term focus:
- User experience & stability improvements
- Desktop & mobile UI/UX optimization
- Cloud sync & backup enhancements
- Resource full lifecycle management optimization
- Skill & workflow expansion
- More model integrations & adaptations
Project History
DeepStudent started as a Python demo in March 2025 and has evolved through nearly a year of continuous iteration:
| Date | Milestone |
|---|---|
| 2025.03 | 🌱 Project Genesis — Python demo prototype, validating AI-assisted learning |
| 2025.05 | 🔄 Tech Stack Migration — Transitioned to Tauri + React + Rust architecture |
| 2025.08 | 🎨 Major UI Overhaul — Migrated to shadcn-ui, introduced Chat architecture & knowledge base vectorization |
| 2025.09 | 📝 Note System & Templates — Milkdown editor integration, Anki template batch import |
| 2025.10 | 🌐 i18n & E2E Testing — Full i18n coverage, Playwright testing, Lance vector storage migration |
| 2025.11 | 💬 Chat V2 Architecture — New conversation engine (multi-model comparison, tool event system, snapshot monitoring) |
| 2025.12 | ⚡ Performance — Parallel session loading, config caching, DSTU resource protocol |
| 2026.01 | 🧩 Skill System & VFS — File-based skill loading, unified Virtual File System |
| 2026.02 | 🚀 Open Source Release — Renamed to DeepStudent, released v0.9.23; added Translation Workbench, Cloud Sync, Session Branching, Smart Memory enhancements, and more |
| 2026.03 | 🐧 Linux & Hardening — Linux build support (deb/AppImage); Todo & Pomodoro system; question history view; model capability auto-detection; reading mode for mobile; content search & session tagging; resource export; memory batch write & idempotency; cross-session permission checks; released v0.9.30–v0.9.35 |
| 2026.04–06 | 🧱 Architecture & Stability — DeepSeek V4 / V3.2 adapter family; frontend features/ modular refactor and Phosphor icon migration; real-environment multi-instance E2E test system; cloud sync convergence remediation; released v0.9.36–v0.9.40 |
Contributing
Help make DeepStudent better.
- Read CONTRIBUTING.md for development workflow
- Ensure
npm run lintand type checks pass before submitting a PR - Bugs & suggestions via Issues
License
Acknowledgments
DeepStudent would not be possible without these outstanding open-source projects:
Frameworks & Runtimes Tauri · React · Vite · TypeScript · Rust · Tokio
Editors & Content Rendering Milkdown · ProseMirror · CodeMirror · KaTeX · Mermaid · react-markdown
UI & Styling Tailwind CSS · Radix UI · Phosphor Icons · Framer Motion · Recharts · React Flow
Data & State LanceDB · SQLite / rusqlite · Apache Arrow · Zustand · Immer · Serde
Document Processing PDF.js · pdfium-render · docx-preview · docx-rs · umya-spreadsheet · Mustache · DOMPurify
Internationalization & Toolchain i18next · date-fns · Vitest · Playwright · ESLint · Sentry
Made with ❤️ for Lifelong Learners
Similar repos
Contributors
Languages
TypeScript
50.3%
Rust
46.1%
CSS
2.3%