4ff4302a8cda7e1f88c5edd325974ab9b4ee9046
5 SDD batches archived: - Batch 1: UI Polish (10 features, 14 tasks) - Batch 2: Study System (8 features, 23 tasks) - Batch 3: Infrastructure (5 features, 22 tasks) - Batch 4: AI Advanced (5 features, 30 tasks) — RAG with @xenova/transformers - Batch 5: Core Features (5 features, 19 tasks) 37 bugs fixed from comprehensive code review (11 CRITICAL, 12 HIGH, 14 MEDIUM/LOW): - SSE streaming now works (event.token check) - API keys no longer exposed via GET /api/models - FTS5 injection sanitized - DB backup/restore with admin auth - Buddy mode wired (buddy_meta column) - Exam auto-submit stale closure fixed - CSS variables aligned with design tokens - Progress data corruption fixed - WebSocket protocol auto-detection - Tests infrastructure completed (vitest + node:test)
StudyOS
Plataforma de estudio personal con IA. Chat con streaming, seguimiento de progreso, procesamiento de PDFs, y micro-chats temáticos (fork/merge).
Stack
- Backend: Node.js + Express + SQLite (sql.js, WASM — sin compilación nativa)
- Frontend: React 18 + Vite
- Streaming: Server-Sent Events (SSE)
Requisitos
- Node.js 18+
Instalación
cd studyos/server && npm install
cd studyos/client && npm install
Desarrollo
# Terminal 1 — Backend
cd studyos/server
node index.js
# Terminal 2 — Frontend
cd studyos/client
npm run dev
Abrí http://localhost:5173 en el navegador.
Producción
cd studyos/client && npm run build
cd studyos/server && node index.js
Todo se sirve desde http://localhost:3001.
Estructura
studyos/
├── server/ # Backend Express
│ ├── index.js # Servidor principal + init async
│ ├── db.js # Schema SQLite vía sql.js (WASM) + seed
│ ├── lib/llm.js # Adaptador SSE (Anthropic + OpenAI)
│ ├── routes/ # Endpoints REST
│ └── systemPromptBuilder.js
├── client/ # Frontend React + Vite
│ └── src/
│ ├── components/ # Sidebar, MainChat, ForkPanel, etc.
│ ├── hooks/ # useChat, usePdfs, useProgress
│ ├── pages/ # Settings
│ └── lib/ # API client
└── data/ # SQLite database (auto-creado)
Configuración Inicial
- La base de datos se crea automáticamente en
data/studyos.db - El modelo por defecto es
claude-sonnet-4(Anthropic) - Configurá tus API keys en Settings → Modelos
- El endpoint VLM por defecto es
http://localhost:8080/vlm
Features
- 💬 Chat con streaming SSE (Anthropic + OpenAI-compatible)
- 📄 Subida y procesamiento de PDFs
- 📊 Seguimiento de progreso por tema
- 🔀 Micro-chats temáticos (fork/merge)
- 🎨 Tema oscuro con diseño pulido
- ⚙️ Configuración de modelos y VLM
Description
StudyOS - AI-powered study platform with streaming chat, PDF processing, fork/merge conversations, LaTeX rendering, and progress tracking
Languages
JavaScript
88.8%
CSS
10.7%
HTML
0.5%