From a648a59c0ff0ae5475f9ba018515b0f28163d2d4 Mon Sep 17 00:00:00 2001
From: airent106 <airent106@users.noreply.github.com>
Date: Tue, 6 Oct 2026 17:55:41 -0600
Subject: [PATCH] Initial commit: Thread Ripper containerized application

---
 .dockerignore                   |  12 +
 .gitignore                      |  40 ++
 Dockerfile                      |  32 ++
 README.md                       | 157 ++++++++
 docker-compose.yml              |  20 +
 requirements.txt                |   8 +
 thread_ripper/__init__.py       |   2 +
 thread_ripper/cli.py            |  69 ++++
 thread_ripper/models.py         |  52 +++
 thread_ripper/scraper.py        | 228 +++++++++++
 thread_ripper/server.py         | 113 ++++++
 thread_ripper/static/app.js     | 329 ++++++++++++++++
 thread_ripper/static/index.html | 199 ++++++++++
 thread_ripper/static/style.css  | 643 ++++++++++++++++++++++++++++++++
 thread_ripper/stitcher.py       | 233 ++++++++++++
 thread_ripper/storage.py        |  76 ++++
 16 files changed, 2213 insertions(+)
 create mode 100644 .dockerignore
 create mode 100644 .gitignore
 create mode 100644 Dockerfile
 create mode 100644 README.md
 create mode 100644 docker-compose.yml
 create mode 100644 requirements.txt
 create mode 100644 thread_ripper/__init__.py
 create mode 100644 thread_ripper/cli.py
 create mode 100644 thread_ripper/models.py
 create mode 100644 thread_ripper/scraper.py
 create mode 100644 thread_ripper/server.py
 create mode 100644 thread_ripper/static/app.js
 create mode 100644 thread_ripper/static/index.html
 create mode 100644 thread_ripper/static/style.css
 create mode 100644 thread_ripper/stitcher.py
 create mode 100644 thread_ripper/storage.py

diff --git a/.dockerignore b/.dockerignore
new file mode 100644
index 0000000..24d6736
--- /dev/null
+++ b/.dockerignore
@@ -0,0 +1,12 @@
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
+env/
+venv/
+.venv/
+data/
+.git
+.gitignore
+.env
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..b56ad53
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,40 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+env/
+venv/
+.venv/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Thread Ripper runtime data
+data/threads/
+data/*.md
+data/*.txt
+data/*.html
+data/*.json
+
+# IDE / Editor
+.idea/
+.vscode/
+*.swp
+*.swo
+
+# Environment
+.env
diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..cd86d94
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,32 @@
+# syntax=docker/dockerfile:1
+FROM mcr.microsoft.com/playwright/python:v1.49.0-noble
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1 \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PORT=5000 \
+    DATA_DIR=/app/data
+
+# Working directory inside the container
+WORKDIR /app
+
+# Install Python requirements
+COPY requirements.txt .
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir -r requirements.txt && \
+    playwright install chromium
+
+# Copy application source code
+COPY thread_ripper/ ./thread_ripper/
+
+# Create persistent data directory
+RUN mkdir -p /app/data/threads
+
+# Expose server port
+EXPOSE 5000
+
+# Volume for persisting saved threads
+VOLUME ["/app/data"]
+
+# Run Thread Ripper server with uvicorn
+CMD ["uvicorn", "thread_ripper.server:app", "--host", "0.0.0.0", "--port", "5000"]
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..1fe3dd8
--- /dev/null
+++ b/README.md
@@ -0,0 +1,157 @@
+# 🧵 Thread Ripper
+
+**Thread Ripper** is a containerized application designed to unroll, extract, and stitch multi-part posts on Meta's Threads back into a single cohesive document.
+
+Paste any Threads link (including share links like `https://www.threads.com/share/BASy90mpUT/` or direct post URLs), and Thread Ripper automatically detects the author's continuation posts, merges them in chronological order, and lets you view, copy, or export them as **Markdown**, **Plain Text**, **Standalone HTML**, or **JSON**.
+
+---
+
+## ✨ Features
+
+- **Any Link Accepted:** Handles share links (`threads.com/share/...`), shortlinks, and direct URLs (`threads.net/@user/post/...`), resolving redirects automatically.
+- **Author Thread Stitching:** Detects the author's consecutive continuation replies and stitches them into a continuous long-form read, filtering out unrelated noise, likes, and reply counts.
+- **Media Preservation:** Retains attached images and photos embedded within thread posts.
+- **Multi-Format Export:**
+  - 📝 **Markdown (`.md`)** – with formatted headers, quotes, lists, and images.
+  - 📄 **Plain Text (`.txt`)** – clean, distraction-free text.
+  - 🌐 **Standalone HTML (`.html`)** – styled, responsive reader document ready to share or archive.
+  - 📦 **JSON (`.json`)** – structured data with individual segments, timestamps, author metadata, and URLs.
+  - 🖨️ **Print / PDF** – print-ready reader view.
+- **Modern Web Dashboard:** Clean, responsive UI with one-click clipboard copy, reader preview, segment breakdown, and saved threads library.
+- **REST API & CLI:** Includes an automated REST API (with Swagger docs at `/docs`) and a CLI command for batch scripting.
+- **Docker-First Architecture:** Built on Microsoft's official Playwright container with Chromium, optimized to run seamlessly on a server (e.g. `vloser`).
+
+---
+
+## 🚀 Quick Start with Docker (Deploying to `vloser`)
+
+### 1. Transfer Project to `vloser`
+Copy this project folder to your server:
+```bash
+# Example using scp or rsync:
+scp -r thread-ripper user@vloser:/opt/thread-ripper
+# Or rsync:
+rsync -avz thread-ripper/ user@vloser:/opt/thread-ripper/
+```
+
+### 2. Start with Docker Compose
+On `vloser`:
+```bash
+cd /opt/thread-ripper
+docker compose up -d --build
+```
+
+### 3. Open Web UI
+Navigate in your browser to:
+```
+http://vloser:5000
+# or
+http://<vloser-ip>:5000
+```
+
+---
+
+## 🖥️ Web UI Walkthrough
+
+1. **Paste Link:** Paste any Threads post or share URL (e.g. `https://www.threads.com/share/BASy90mpUT/`).
+2. **Click "Rip Thread":** The container resolves the URL in a headless browser, tracks author continuation replies, and stitches the pieces together.
+3. **View & Export:**
+   - **Reader View:** Read the full thread formatted as a clean article.
+   - **Markdown View:** View or copy the unrolled Markdown.
+   - **Segments:** Inspect each individual post segment.
+   - **Download:** Download `.md`, `.txt`, `.html`, or `.json`.
+   - **Library:** Access previously saved threads anytime from the persistent sidebar.
+
+---
+
+## ⚙️ REST API Endpoints
+
+Thread Ripper includes a complete REST API:
+
+| Endpoint | Method | Description |
+|---|---|---|
+| `/api/rip` | `POST` | Rip a thread by URL (`{"url": "...", "mode": "author_only"}`) |
+| `/api/history` | `GET` | List all saved threads |
+| `/api/history/{id}` | `GET` | Get full details of a saved thread |
+| `/api/history/{id}` | `DELETE` | Delete a saved thread |
+| `/api/download/{id}/{format}` | `GET` | Download in format (`md`, `txt`, `html`, `json`) |
+| `/api/health` | `GET` | Health check endpoint |
+| `/docs` | `GET` | Interactive Swagger API documentation |
+
+### Example cURL Request:
+```bash
+curl -X POST http://vloser:5000/api/rip \
+  -H "Content-Type: application/json" \
+  -d '{"url": "https://www.threads.com/share/BASy90mpUT/"}'
+```
+
+---
+
+## 💻 CLI Usage
+
+You can also use Thread Ripper directly from the command line:
+
+```bash
+# Run CLI and print output
+python -m thread_ripper.cli "https://www.threads.com/share/BASy90mpUT/"
+
+# Export directly to Markdown file
+python -m thread_ripper.cli "https://www.threads.com/share/BASy90mpUT/" -o unrolled.md
+
+# Export as Standalone HTML
+python -m thread_ripper.cli "https://www.threads.com/share/BASy90mpUT/" -f html -o unrolled.html
+```
+
+---
+
+## 📁 Project Structure
+
+```
+thread-ripper/
+├── Dockerfile                  # Container definition (Playwright + Python)
+├── docker-compose.yml          # Compose service configuration
+├── requirements.txt            # Python dependencies
+├── .dockerignore               # Docker build exclusions
+├── README.md                   # Documentation
+├── data/                       # Persistent volume for saved threads
+│   └── threads/                # Stored .json, .md, .html, and .txt files
+└── thread_ripper/
+    ├── __init__.py
+    ├── models.py               # Pydantic data schemas
+    ├── scraper.py              # Playwright browser engine & extractor
+    ├── stitcher.py             # Formatter (Markdown, Text, HTML)
+    ├── storage.py              # File-based persistence layer
+    ├── server.py               # FastAPI application
+    ├── cli.py                  # Command-line interface
+    └── static/                 # Modern web frontend
+        ├── index.html
+        ├── style.css
+        └── app.js
+```
+
+---
+
+## 📋 Tested Example
+
+Target URL: `https://www.threads.com/share/BASy90mpUT/`  
+Author: **Beth Parent McMillian (@bethmcmilliandesigns)**
+
+### Reconstructed Output:
+
+> # A GenX retirement community in a renovated shopping mall.
+> **Author:** Beth Parent McMillian (@bethmcmilliandesigns)  
+> **Original Post:** https://www.threads.com/@bethmcmilliandesigns/post/Dd717khDOk_  
+> **Thread Segments:** 2  
+> 
+> A GenX retirement community in a renovated shopping mall. Half the building is apartments. The other half *looks* like an 80s/90s mall, but:
+> - the Waldenbooks is a library
+> - all the food places are part of your meal plan, so you can get an Orange Julius, eat anywhere at the food court, or have a nice sit-down meal at Shoney’s
+> - there’s a movie theater and a free arcade with old-school game cabinets
+> 
+> - you can just sit in Sam Goody and listen to Bowie or The Ramones or whatever (they also DJ monthly dance parties)
+> - you can reserve a massage chair in the Sharper Image for an hour at a time
+> - the in-house pharmacy is an Eckerds
+> - you can rent movies and video games from Blockbuster
+> - there’s an aerobics studio where we do GenXercise, Tae-Bo, and MTV’s The Grind workouts
+> - there are fountains and a lazy river (because why not?)
+> - we all go mall walking daily
diff --git a/docker-compose.yml b/docker-compose.yml
new file mode 100644
index 0000000..fa35225
--- /dev/null
+++ b/docker-compose.yml
@@ -0,0 +1,20 @@
+services:
+  thread-ripper:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    container_name: thread-ripper
+    restart: unless-stopped
+    ports:
+      - "5000:5000"
+    environment:
+      - PORT=5000
+      - DATA_DIR=/app/data
+    volumes:
+      - ./data:/app/data
+    healthcheck:
+      test: ["CMD-SHELL", "python -c 'import urllib.request; urllib.request.urlopen(\"http://localhost:5000/api/health\")'"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 15s
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..b4da6fd
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,8 @@
+fastapi>=0.110.0
+uvicorn[standard]>=0.28.0
+playwright>=1.42.0
+pydantic>=2.6.0
+jinja2>=3.1.3
+python-multipart>=0.0.9
+markdown>=3.5.2
+httpx>=0.27.0
diff --git a/thread_ripper/__init__.py b/thread_ripper/__init__.py
new file mode 100644
index 0000000..932ef5d
--- /dev/null
+++ b/thread_ripper/__init__.py
@@ -0,0 +1,2 @@
+"""Thread Ripper package."""
+__version__ = "1.0.0"
diff --git a/thread_ripper/cli.py b/thread_ripper/cli.py
new file mode 100644
index 0000000..2781655
--- /dev/null
+++ b/thread_ripper/cli.py
@@ -0,0 +1,69 @@
+import argparse
+import asyncio
+import sys
+from pathlib import Path
+from .scraper import ThreadScraper
+from .storage import ThreadStorage
+
+def parse_args():
+    parser = argparse.ArgumentParser(description="Thread Ripper - Unroll and stitch Threads posts into a single post.")
+    parser.add_argument("url", help="Threads URL (e.g., https://www.threads.com/share/BASy90mpUT/ or https://www.threads.net/@user/post/...)")
+    parser.add_argument("-o", "--output", help="Output file path (e.g. output.md, output.txt, output.html)")
+    parser.add_argument("-f", "--format", choices=["markdown", "txt", "html", "json"], default="markdown", help="Output format (default: markdown)")
+    parser.add_argument("--mode", choices=["author_only", "all_replies"], default="author_only", help="Extraction mode (default: author_only)")
+    parser.add_argument("--scrolls", type=int, default=5, help="Number of lazy-load scrolls (default: 5)")
+    return parser.parse_args()
+
+async def main_async():
+    args = parse_args()
+    print(f"[*] Thread Ripper v1.0.0")
+    print(f"[*] Target URL: {args.url}")
+    print(f"[*] Mode: {args.mode}")
+
+    scraper = ThreadScraper(headless=True)
+    try:
+        print("[*] Fetching and parsing thread...")
+        result = await scraper.rip(url=args.url, mode=args.mode, max_scrolls=args.scrolls)
+
+        # Save to persistent storage as well
+        storage = ThreadStorage("data")
+        storage.save(result)
+
+        print(f"\n[+] Successfully ripped thread!")
+        print(f"    Author: {result.author_name} (@{result.author_handle})")
+        print(f"    Segments stitched: {result.segment_count}")
+        print(f"    Total words: {result.total_words}")
+        print(f"    Thread ID: {result.id}")
+
+        content = ""
+        if args.format == "markdown":
+            content = result.stitched_markdown
+        elif args.format == "txt":
+            content = result.stitched_text
+        elif args.format == "html":
+            content = result.stitched_html
+        elif args.format == "json":
+            content = result.model_dump_json(indent=2)
+
+        if args.output:
+            out_path = Path(args.output)
+            out_path.parent.mkdir(parents=True, exist_ok=True)
+            with open(out_path, "w", encoding="utf-8") as f:
+                f.write(content)
+            print(f"[+] Output saved to: {out_path.resolve()}")
+        else:
+            print("\n" + "=" * 40 + " RIPPED POST PREVIEW " + "=" * 40)
+            print(content[:1500] + ("\n... [truncated]" if len(content) > 1500 else ""))
+            print("=" * 102)
+
+    except Exception as e:
+        print(f"[-] Error: {e}", file=sys.stderr)
+        sys.exit(1)
+    finally:
+        await scraper.close()
+
+def main():
+    asyncio.run(main_async())
+
+if __name__ == "__main__":
+    main()
diff --git a/thread_ripper/models.py b/thread_ripper/models.py
new file mode 100644
index 0000000..8b72bad
--- /dev/null
+++ b/thread_ripper/models.py
@@ -0,0 +1,52 @@
+from typing import List, Optional, Dict, Any
+from pydantic import BaseModel, Field
+from datetime import datetime
+
+class MediaItem(BaseModel):
+    type: str = "image"
+    url: str
+    alt_text: Optional[str] = None
+
+class PostSegment(BaseModel):
+    index: int
+    author_handle: str
+    author_name: Optional[str] = None
+    author_avatar: Optional[str] = None
+    timestamp: Optional[str] = None
+    url: Optional[str] = None
+    text: str
+    is_author: bool = True
+    images: List[MediaItem] = Field(default_factory=list)
+    stats: Dict[str, str] = Field(default_factory=dict)
+
+class RippedThread(BaseModel):
+    id: str
+    original_url: str
+    canonical_url: str
+    author_handle: str
+    author_name: str
+    author_avatar: Optional[str] = None
+    created_at: str
+    title: str
+    segments: List[PostSegment]
+    stitched_markdown: str
+    stitched_text: str
+    stitched_html: str
+    segment_count: int
+    total_words: int
+    saved_at: datetime = Field(default_factory=datetime.utcnow)
+
+class RipRequest(BaseModel):
+    url: str
+    mode: str = "author_only"  # 'author_only' or 'all_replies'
+    max_scrolls: int = 6
+
+class HistorySummary(BaseModel):
+    id: str
+    title: str
+    author_handle: str
+    author_name: str
+    segment_count: int
+    total_words: int
+    saved_at: str
+    original_url: str
diff --git a/thread_ripper/scraper.py b/thread_ripper/scraper.py
new file mode 100644
index 0000000..2305ecb
--- /dev/null
+++ b/thread_ripper/scraper.py
@@ -0,0 +1,228 @@
+import asyncio
+import re
+import hashlib
+from typing import Tuple, List, Optional
+from playwright.async_api import async_playwright, Browser, BrowserContext, Page
+from .models import PostSegment, MediaItem, RippedThread
+from .stitcher import build_markdown, build_plain_text, build_standalone_html
+
+class ThreadScraper:
+    def __init__(self, headless: bool = True):
+        self.headless = headless
+        self._browser: Optional[Browser] = None
+        self._playwright = None
+
+    async def get_browser(self) -> Browser:
+        if self._browser is None or not self._browser.is_connected():
+            if self._playwright is None:
+                self._playwright = await async_playwright().start()
+            self._browser = await self._playwright.chromium.launch(
+                headless=self.headless,
+                args=[
+                    "--no-sandbox",
+                    "--disable-setuid-sandbox",
+                    "--disable-dev-shm-usage",
+                    "--disable-gpu",
+                ]
+            )
+        return self._browser
+
+    async def close(self):
+        if self._browser:
+            await self._browser.close()
+            self._browser = None
+        if self._playwright:
+            await self._playwright.stop()
+            self._playwright = None
+
+    async def rip(self, url: str, mode: str = "author_only", max_scrolls: int = 5) -> RippedThread:
+        """Scrapes and rips a Threads post and its chained continuation posts."""
+        browser = await self.get_browser()
+        context: BrowserContext = await browser.new_context(
+            user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
+            viewport={"width": 1280, "height": 900}
+        )
+        page: Page = await context.new_page()
+
+        try:
+            # Navigate and follow redirects
+            await page.goto(url, wait_until="networkidle", timeout=30000)
+            canonical_url = page.url
+
+            # Small delay for hydration
+            await page.wait_for_timeout(2500)
+
+            # Extract Open Graph metadata
+            og_title = await page.evaluate("() => document.querySelector('meta[property=\"og:title\"]')?.content || ''")
+            og_image = await page.evaluate("() => document.querySelector('meta[property=\"og:image\"]')?.content || ''")
+            og_desc = await page.evaluate("() => document.querySelector('meta[property=\"og:description\"]')?.content || ''")
+
+            # Determine original author handle from URL or title
+            author_handle = ""
+            author_name = ""
+
+            # Check canonical URL for /@username
+            match_handle = re.search(r"/@([a-zA-Z0-9_\.]+)", canonical_url)
+            if match_handle:
+                author_handle = match_handle.group(1)
+
+            # Check og:title e.g. "Beth Parent McMillian (@bethmcmilliandesigns) on Threads"
+            if og_title:
+                m_title = re.search(r"^(.*?)\s*\(@?([a-zA-Z0-9_\.]+)\)", og_title)
+                if m_title:
+                    author_name = m_title.group(1).strip()
+                    if not author_handle:
+                        author_handle = m_title.group(2).strip()
+
+            if not author_name:
+                author_name = author_handle or "Threads Author"
+
+            # Author profile avatar
+            author_avatar = og_image if og_image else None
+
+            # Progressively scroll to load dynamic replies in the thread
+            for _ in range(max_scrolls):
+                await page.evaluate("window.scrollBy(0, 1200)")
+                await page.wait_for_timeout(1000)
+
+            # Query all pressable post containers
+            containers = await page.query_selector_all("div[data-pressable-container='true']")
+
+            raw_segments: List[PostSegment] = []
+            seen_texts = set()
+
+            for idx, c in enumerate(containers):
+                # 1. Identify post author handle
+                user_links = await c.query_selector_all("a[href*='/@']")
+                post_handle = None
+                post_url = None
+
+                for ul in user_links:
+                    href = await ul.get_attribute("href")
+                    if href:
+                        if "/@" in href and not post_handle:
+                            parts = href.split("/@")
+                            if len(parts) > 1:
+                                post_handle = parts[1].split("/")[0].split("?")[0]
+                        if "/post/" in href and not post_url:
+                            post_url = href.split("?")[0]
+
+                # Check for "Author" badge
+                is_author_badge = False
+                badge = await c.query_selector("xpath=.//*[text()='Author']")
+                if badge:
+                    is_author_badge = True
+
+                # Determine if this segment belongs to the original author
+                is_author_post = False
+                if idx == 0:
+                    is_author_post = True
+                    if post_handle and not author_handle:
+                        author_handle = post_handle
+                elif is_author_badge:
+                    is_author_post = True
+                elif post_handle and author_handle and (post_handle.lower() == author_handle.lower()):
+                    is_author_post = True
+
+                # If author_only mode is on and this is not by the author, skip
+                if mode == "author_only" and not is_author_post:
+                    continue
+
+                # 2. Extract text with dir='auto'
+                dir_els = await c.query_selector_all("[dir='auto']")
+                segment_text_parts = []
+                for del_el in dir_els:
+                    txt = (await del_el.inner_text()).strip()
+                    if not txt:
+                        continue
+                    # Ignore handle, author badge, bullet dots, stats
+                    if txt == post_handle or txt == "Author" or txt == "·" or txt == author_handle:
+                        continue
+                    # Ignore pure stat numbers (e.g., '16.2K', '5d', '2K', '711')
+                    if re.match(r"^(\d+(\.\d+)?[KMkmdh]?|\d+)$", txt):
+                        continue
+                    if txt not in segment_text_parts:
+                        segment_text_parts.append(txt)
+
+                combined_text = "\n\n".join(segment_text_parts).strip()
+                if not combined_text and not is_author_post:
+                    continue
+
+                # Deduplicate identical consecutive segments
+                text_hash = hashlib.md5(combined_text.encode("utf-8")).hexdigest()
+                if text_hash in seen_texts and combined_text:
+                    continue
+                seen_texts.add(text_hash)
+
+                # 3. Extract media images inside post (exclude profile pictures)
+                imgs = await c.query_selector_all("img")
+                post_images: List[MediaItem] = []
+                for img in imgs:
+                    src = await img.get_attribute("src")
+                    alt = await img.get_attribute("alt") or ""
+                    if src:
+                        # Exclude small avatars or generic SVG icons
+                        if "profile_pic" in src or "scontent" in src and "206x206" in src:
+                            continue
+                        post_images.append(MediaItem(type="image", url=src, alt_text=alt))
+
+                raw_segments.append(
+                    PostSegment(
+                        index=len(raw_segments),
+                        author_handle=post_handle or author_handle,
+                        author_name=author_name if is_author_post else (post_handle or "User"),
+                        author_avatar=author_avatar if is_author_post else None,
+                        url=post_url,
+                        text=combined_text,
+                        is_author=is_author_post,
+                        images=post_images
+                    )
+                )
+
+            # If no segments could be extracted from containers, fallback to OG description
+            if not raw_segments and og_desc:
+                raw_segments.append(
+                    PostSegment(
+                        index=0,
+                        author_handle=author_handle,
+                        author_name=author_name,
+                        author_avatar=author_avatar,
+                        url=canonical_url,
+                        text=og_desc,
+                        is_author=True,
+                        images=[]
+                    )
+                )
+
+            # Construct stitched outputs
+            markdown_out = build_markdown(author_name, author_handle, canonical_url, raw_segments)
+            plain_text_out = build_plain_text(author_name, author_handle, canonical_url, raw_segments)
+            html_out = build_standalone_html(author_name, author_handle, author_avatar, canonical_url, raw_segments)
+
+            # Generate unique ID for this ripped thread
+            thread_id = hashlib.md5(canonical_url.split("?")[0].encode("utf-8")).hexdigest()[:12]
+            title = raw_segments[0].text.split("\n")[0] if raw_segments and raw_segments[0].text else f"Thread by @{author_handle}"
+            if len(title) > 90:
+                title = title[:87] + "..."
+
+            total_words = sum(len(s.text.split()) for s in raw_segments)
+
+            return RippedThread(
+                id=thread_id,
+                original_url=url,
+                canonical_url=canonical_url,
+                author_handle=author_handle,
+                author_name=author_name,
+                author_avatar=author_avatar,
+                created_at="Recent",
+                title=title,
+                segments=raw_segments,
+                stitched_markdown=markdown_out,
+                stitched_text=plain_text_out,
+                stitched_html=html_out,
+                segment_count=len(raw_segments),
+                total_words=total_words
+            )
+
+        finally:
+            await context.close()
diff --git a/thread_ripper/server.py b/thread_ripper/server.py
new file mode 100644
index 0000000..0408687
--- /dev/null
+++ b/thread_ripper/server.py
@@ -0,0 +1,113 @@
+import os
+from contextlib import asynccontextmanager
+from fastapi import FastAPI, HTTPException, Response
+from fastapi.staticfiles import StaticFiles
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import FileResponse, PlainTextResponse, HTMLResponse, JSONResponse
+from .models import RipRequest, RippedThread
+from .scraper import ThreadScraper
+from .storage import ThreadStorage
+
+DATA_DIR = os.environ.get("DATA_DIR", "data")
+storage = ThreadStorage(DATA_DIR)
+scraper = ThreadScraper(headless=True)
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    yield
+    await scraper.close()
+
+app = FastAPI(
+    title="Thread Ripper",
+    description="Containerized Thread Ripper for Meta Threads. Takes Threads links and stitches threads into single posts.",
+    version="1.0.0",
+    lifespan=lifespan
+)
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+@app.post("/api/rip", response_model=RippedThread)
+async def rip_endpoint(req: RipRequest):
+    """Rip a Threads post and its chained continuation posts."""
+    if not req.url or "threads." not in req.url:
+        raise HTTPException(status_code=400, detail="Invalid Threads URL. Please provide a valid threads.net or threads.com link.")
+
+    try:
+        ripped = await scraper.rip(url=req.url, mode=req.mode, max_scrolls=req.max_scrolls)
+        storage.save(ripped)
+        return ripped
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Failed to rip thread: {str(e)}")
+
+@app.get("/api/history")
+def get_history():
+    """Retrieve history of saved ripped threads."""
+    return storage.list_history()
+
+@app.get("/api/history/{thread_id}", response_model=RippedThread)
+def get_thread_by_id(thread_id: str):
+    """Get complete ripped thread by ID."""
+    thread = storage.get(thread_id)
+    if not thread:
+        raise HTTPException(status_code=404, detail="Thread not found")
+    return thread
+
+@app.delete("/api/history/{thread_id}")
+def delete_thread_by_id(thread_id: str):
+    """Delete thread from history."""
+    deleted = storage.delete(thread_id)
+    if not deleted:
+        raise HTTPException(status_code=404, detail="Thread not found")
+    return {"status": "success", "deleted_id": thread_id}
+
+@app.get("/api/download/{thread_id}/{format}")
+def download_thread(thread_id: str, format: str):
+    """Download thread in chosen format (.md, .txt, .html, .json)."""
+    thread = storage.get(thread_id)
+    if not thread:
+        raise HTTPException(status_code=404, detail="Thread not found")
+
+    safe_title = "".join(c for c in thread.author_handle if c.isalnum() or c in "-_")
+    filename_base = f"thread_{safe_title}_{thread_id}"
+
+    if format == "md" or format == "markdown":
+        return Response(
+            content=thread.stitched_markdown,
+            media_type="text/markdown; charset=utf-8",
+            headers={"Content-Disposition": f'attachment; filename="{filename_base}.md"'}
+        )
+    elif format == "txt" or format == "text":
+        return Response(
+            content=thread.stitched_text,
+            media_type="text/plain; charset=utf-8",
+            headers={"Content-Disposition": f'attachment; filename="{filename_base}.txt"'}
+        )
+    elif format == "html":
+        return Response(
+            content=thread.stitched_html,
+            media_type="text/html; charset=utf-8",
+            headers={"Content-Disposition": f'attachment; filename="{filename_base}.html"'}
+        )
+    elif format == "json":
+        return Response(
+            content=thread.model_dump_json(indent=2),
+            media_type="application/json; charset=utf-8",
+            headers={"Content-Disposition": f'attachment; filename="{filename_base}.json"'}
+        )
+    else:
+        raise HTTPException(status_code=400, detail="Supported formats: md, txt, html, json")
+
+@app.get("/api/health")
+def health_check():
+    return {"status": "ok", "app": "Thread Ripper", "version": "1.0.0"}
+
+# Mount static frontend directory
+static_dir = os.path.join(os.path.dirname(__file__), "static")
+if os.path.exists(static_dir):
+    app.mount("/", StaticFiles(directory=static_dir, html=True), name="static")
diff --git a/thread_ripper/static/app.js b/thread_ripper/static/app.js
new file mode 100644
index 0000000..ba72900
--- /dev/null
+++ b/thread_ripper/static/app.js
@@ -0,0 +1,329 @@
+document.addEventListener("DOMContentLoaded", () => {
+  const threadUrlInput = document.getElementById("thread-url");
+  const pasteBtn = document.getElementById("paste-btn");
+  const ripBtn = document.getElementById("rip-btn");
+  const sampleMallBtn = document.getElementById("sample-mall-btn");
+  const statusBanner = document.getElementById("status-banner");
+  const statusTitle = document.getElementById("status-title");
+  const statusDesc = document.getElementById("status-desc");
+  const resultSection = document.getElementById("result-section");
+  
+  // Results elements
+  const resAvatar = document.getElementById("res-avatar");
+  const resAuthorName = document.getElementById("res-author-name");
+  const resAuthorLink = document.getElementById("res-author-link");
+  const resSegmentCount = document.getElementById("res-segment-count");
+  const resWordCount = document.getElementById("res-word-count");
+  const tabSegmentCount = document.getElementById("tab-segment-count");
+  const readerContent = document.getElementById("reader-content");
+  const markdownContent = document.getElementById("markdown-content");
+  const segmentsContainer = document.getElementById("segments-container");
+  
+  // Export buttons
+  const copyMdBtn = document.getElementById("copy-md-btn");
+  const copyTxtBtn = document.getElementById("copy-txt-btn");
+  const downloadDropdownBtn = document.getElementById("download-dropdown-btn");
+  const downloadMenu = document.getElementById("download-menu");
+  const dlMd = document.getElementById("dl-md");
+  const dlTxt = document.getElementById("dl-txt");
+  const dlHtml = document.getElementById("dl-html");
+  const dlJson = document.getElementById("dl-json");
+  const printBtn = document.getElementById("print-btn");
+
+  // Library / History elements
+  const toggleHistoryBtn = document.getElementById("toggle-history-btn");
+  const librarySidebar = document.getElementById("library-sidebar");
+  const closeLibraryBtn = document.getElementById("close-library-btn");
+  const libraryList = document.getElementById("library-list");
+  const libraryCount = document.getElementById("history-count");
+  const librarySearch = document.getElementById("library-search");
+
+  // Toast
+  const toast = document.getElementById("toast");
+
+  let currentThread = null;
+  let allHistory = [];
+
+  // Initialize history
+  fetchHistory();
+
+  // Paste button
+  pasteBtn.addEventListener("click", async () => {
+    try {
+      const text = await navigator.clipboard.readText();
+      if (text) {
+        threadUrlInput.value = text.trim();
+      }
+    } catch (e) {
+      showToast("Clipboard access denied or unavailable", true);
+    }
+  });
+
+  // Example button
+  sampleMallBtn.addEventListener("click", () => {
+    threadUrlInput.value = sampleMallBtn.getAttribute("data-url");
+    triggerRip();
+  });
+
+  // Rip button
+  ripBtn.addEventListener("click", () => {
+    triggerRip();
+  });
+
+  threadUrlInput.addEventListener("keydown", (e) => {
+    if (e.key === "Enter") {
+      triggerRip();
+    }
+  });
+
+  async function triggerRip() {
+    const url = threadUrlInput.value.trim();
+    if (!url) {
+      showToast("Please paste a Threads URL", true);
+      return;
+    }
+
+    const mode = document.querySelector('input[name="rip-mode"]:checked').value;
+
+    setLoading(true);
+    statusTitle.textContent = "Connecting to Threads...";
+    statusDesc.textContent = "Launching headless browser and resolving URL...";
+
+    try {
+      const response = await fetch("/api/rip", {
+        method: "POST",
+        headers: { "Content-Type": "application/json" },
+        body: JSON.stringify({ url, mode, max_scrolls: 5 })
+      });
+
+      if (!response.ok) {
+        const err = await response.json();
+        throw new Error(err.detail || "Failed to rip thread");
+      }
+
+      const data = await response.json();
+      currentThread = data;
+      renderThread(data);
+      fetchHistory();
+      showToast("Thread successfully ripped & saved!");
+    } catch (err) {
+      console.error(err);
+      showToast(`Error: ${err.message}`, true);
+    } finally {
+      setLoading(false);
+    }
+  }
+
+  function setLoading(isLoading) {
+    const btnText = ripBtn.querySelector(".btn-text");
+    const spinner = ripBtn.querySelector(".btn-spinner");
+    if (isLoading) {
+      ripBtn.disabled = true;
+      btnText.textContent = "Ripping...";
+      spinner.classList.remove("hidden");
+      statusBanner.classList.remove("hidden");
+      resultSection.classList.add("hidden");
+    } else {
+      ripBtn.disabled = false;
+      btnText.textContent = "Rip Thread";
+      spinner.classList.add("hidden");
+      statusBanner.classList.add("hidden");
+    }
+  }
+
+  function renderThread(thread) {
+    resultSection.classList.remove("hidden");
+
+    // Header info
+    resAuthorName.textContent = thread.author_name;
+    resAuthorLink.textContent = `@${thread.author_handle}`;
+    resAuthorLink.href = thread.canonical_url;
+    if (thread.author_avatar) {
+      resAvatar.src = thread.author_avatar;
+      resAvatar.classList.remove("hidden");
+    } else {
+      resAvatar.classList.add("hidden");
+    }
+
+    resSegmentCount.textContent = thread.segment_count;
+    resWordCount.textContent = thread.total_words;
+    tabSegmentCount.textContent = thread.segment_count;
+
+    // Render Markdown view
+    markdownContent.textContent = thread.stitched_markdown;
+
+    // Render Reader view (using marked.js parser)
+    if (window.marked) {
+      readerContent.innerHTML = marked.parse(thread.stitched_markdown);
+    } else {
+      readerContent.innerHTML = thread.stitched_html;
+    }
+
+    // Render Segments breakdown view
+    segmentsContainer.innerHTML = "";
+    thread.segments.forEach((seg, idx) => {
+      const segEl = document.createElement("div");
+      segEl.className = "segment-item";
+      segEl.innerHTML = `
+        <div class="segment-header">
+          <span class="segment-num">Segment #${idx + 1} ${seg.is_author ? "(Author)" : "(Reply)"}</span>
+          <span>${seg.author_handle ? "@" + seg.author_handle : ""}</span>
+        </div>
+        <div class="segment-text">${escapeHtml(seg.text)}</div>
+      `;
+      segmentsContainer.appendChild(segEl);
+    });
+
+    // Setup download links
+    dlMd.href = `/api/download/${thread.id}/md`;
+    dlTxt.href = `/api/download/${thread.id}/txt`;
+    dlHtml.href = `/api/download/${thread.id}/html`;
+    dlJson.href = `/api/download/${thread.id}/json`;
+
+    // Switch to reader view
+    switchTab("reader");
+  }
+
+  // Tabs switching
+  document.querySelectorAll(".tab-btn").forEach((btn) => {
+    btn.addEventListener("click", () => {
+      const tabName = btn.getAttribute("data-tab");
+      switchTab(tabName);
+    });
+  });
+
+  function switchTab(tabName) {
+    document.querySelectorAll(".tab-btn").forEach((b) => b.classList.remove("active"));
+    document.querySelector(`.tab-btn[data-tab="${tabName}"]`)?.classList.add("active");
+
+    document.querySelectorAll(".tab-view").forEach((v) => {
+      v.classList.add("hidden");
+      v.classList.remove("active");
+    });
+
+    const targetView = document.getElementById(`view-${tabName}`);
+    if (targetView) {
+      targetView.classList.remove("hidden");
+      targetView.classList.add("active");
+    }
+  }
+
+  // Copy buttons
+  copyMdBtn.addEventListener("click", () => {
+    if (!currentThread) return;
+    navigator.clipboard.writeText(currentThread.stitched_markdown);
+    showToast("Copied Markdown to clipboard!");
+  });
+
+  copyTxtBtn.addEventListener("click", () => {
+    if (!currentThread) return;
+    navigator.clipboard.writeText(currentThread.stitched_text);
+    showToast("Copied Plain Text to clipboard!");
+  });
+
+  // Download dropdown toggle
+  downloadDropdownBtn.addEventListener("click", (e) => {
+    e.stopPropagation();
+    downloadMenu.classList.toggle("show");
+  });
+
+  document.addEventListener("click", () => {
+    downloadMenu.classList.remove("show");
+  });
+
+  // Print button
+  printBtn.addEventListener("click", () => {
+    if (!currentThread) return;
+    const printWindow = window.open("", "_blank");
+    printWindow.document.write(currentThread.stitched_html);
+    printWindow.document.close();
+    printWindow.focus();
+    setTimeout(() => {
+      printWindow.print();
+    }, 500);
+  });
+
+  // Library / History
+  toggleHistoryBtn.addEventListener("click", () => {
+    librarySidebar.classList.toggle("open");
+  });
+
+  closeLibraryBtn.addEventListener("click", () => {
+    librarySidebar.classList.remove("open");
+  });
+
+  async function fetchHistory() {
+    try {
+      const res = await fetch("/api/history");
+      if (res.ok) {
+        allHistory = await res.json();
+        libraryCount.textContent = allHistory.length;
+        renderHistoryList(allHistory);
+      }
+    } catch (e) {
+      console.warn("Could not load history", e);
+    }
+  }
+
+  function renderHistoryList(items) {
+    if (!items || items.length === 0) {
+      libraryList.innerHTML = '<p class="empty-state">No threads ripped yet.</p>';
+      return;
+    }
+
+    libraryList.innerHTML = "";
+    items.forEach((item) => {
+      const div = document.createElement("div");
+      div.className = "history-item";
+      div.innerHTML = `
+        <div class="history-item-title">${escapeHtml(item.title)}</div>
+        <div class="history-item-meta">
+          <span>@${escapeHtml(item.author_handle)} (${item.segment_count} posts)</span>
+          <span>${item.saved_at.split("T")[0] || ""}</span>
+        </div>
+      `;
+      div.addEventListener("click", async () => {
+        try {
+          const res = await fetch(`/api/history/${item.id}`);
+          if (res.ok) {
+            currentThread = await res.json();
+            renderThread(currentThread);
+            librarySidebar.classList.remove("open");
+          }
+        } catch (e) {
+          showToast("Failed to load thread", true);
+        }
+      });
+      libraryList.appendChild(div);
+    });
+  }
+
+  librarySearch.addEventListener("input", (e) => {
+    const q = e.target.value.toLowerCase();
+    const filtered = allHistory.filter(
+      (item) =>
+        item.title.toLowerCase().includes(q) ||
+        item.author_handle.toLowerCase().includes(q)
+    );
+    renderHistoryList(filtered);
+  });
+
+  function showToast(msg, isError = false) {
+    toast.textContent = msg;
+    toast.style.background = isError ? "#da3633" : "#238636";
+    toast.classList.remove("hidden");
+    setTimeout(() => {
+      toast.classList.add("hidden");
+    }, 3500);
+  }
+
+  function escapeHtml(str) {
+    if (!str) return "";
+    return str
+      .replace(/&/g, "&amp;")
+      .replace(/</g, "&lt;")
+      .replace(/>/g, "&gt;")
+      .replace(/"/g, "&quot;")
+      .replace(/'/g, "&#039;");
+  }
+});
diff --git a/thread_ripper/static/index.html b/thread_ripper/static/index.html
new file mode 100644
index 0000000..f7c49ea
--- /dev/null
+++ b/thread_ripper/static/index.html
@@ -0,0 +1,199 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  <title>Thread Ripper - Stitch Threads into Single Posts</title>
+  <link rel="stylesheet" href="style.css">
+  <link rel="preconnect" href="https://fonts.googleapis.com">
+  <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
+  <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700&family=JetBrains+Mono:wght@400;500&display=swap" rel="stylesheet">
+  <!-- Markdown parser for preview -->
+  <script src="https://cdn.jsdelivr.net/npm/marked/marked.min.js"></script>
+</head>
+<body>
+  <div class="app-layout">
+    <!-- Main Content Area -->
+    <main class="main-content">
+      <header class="app-header">
+        <div class="logo-group">
+          <div class="logo-icon">
+            <svg width="28" height="28" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2.2" stroke-linecap="round" stroke-linejoin="round">
+              <path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"/>
+              <path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"/>
+            </svg>
+          </div>
+          <div>
+            <h1>Thread Ripper</h1>
+            <p class="subtitle">Extract and stitch multi-part Threads into a single cohesive post</p>
+          </div>
+        </div>
+        <div class="header-badges">
+          <span class="badge docker-badge">
+            <svg width="14" height="14" viewBox="0 0 24 24" fill="currentColor">
+              <path d="M4.5 10.5h2v2h-2zm3 0h2v2h-2zm3 0h2v2h-2zm3 0h2v2h-2zm-6-3h2v2h-2zm3 0h2v2h-2zm3 0h2v2h-2zm-3-3h2v2h-2zm12 5.5c-.3-.2-1.5-.7-2.3-.2-.2-.8-.7-1.4-1.4-1.8l-.5-.3-.4.4c-.6.7-.8 1.6-.7 2.4-.9.2-1.8.8-2.2 1.6H2.5c-.8 0-1.5.7-1.5 1.5 0 3.3 2.1 6.3 5.4 7.4 3.7 1.3 7.8.4 10.7-2.2 2.3-2.1 3.5-5.2 3.4-8.3-.1-.3-.3-.5-.5-.5z"/>
+            </svg>
+            Docker Container
+          </span>
+          <button id="toggle-history-btn" class="btn btn-ghost" title="Toggle Saved Library">
+            <svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2">
+              <path d="M12 8v4l3 3"/>
+              <circle cx="12" cy="12" r="9"/>
+            </svg>
+            Library (<span id="history-count">0</span>)
+          </button>
+        </div>
+      </header>
+
+      <!-- Input Form Card -->
+      <section class="card input-card">
+        <div class="url-input-container">
+          <div class="input-prefix">
+            <svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2">
+              <path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"/>
+              <path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"/>
+            </svg>
+          </div>
+          <input 
+            type="url" 
+            id="thread-url" 
+            placeholder="Paste any Threads link (e.g. https://www.threads.com/share/BASy90mpUT/ or https://www.threads.net/@user/post/...)" 
+            autocomplete="off"
+            spellcheck="false"
+          />
+          <button id="paste-btn" class="btn btn-secondary btn-sm" title="Paste from clipboard">Paste</button>
+          <button id="rip-btn" class="btn btn-primary">
+            <span class="btn-text">Rip Thread</span>
+            <span class="btn-spinner hidden"></span>
+          </button>
+        </div>
+
+        <div class="input-controls">
+          <div class="sample-links">
+            <span class="sample-label">Try example:</span>
+            <button class="pill-btn" id="sample-mall-btn" data-url="https://www.threads.com/share/BASy90mpUT/">
+              GenX Mall Retirement Community (@bethmcmilliandesigns)
+            </button>
+          </div>
+
+          <div class="mode-selector">
+            <label class="radio-label">
+              <input type="radio" name="rip-mode" value="author_only" checked />
+              <span>Author Thread Only</span>
+            </label>
+            <label class="radio-label">
+              <input type="radio" name="rip-mode" value="all_replies" />
+              <span>Include Community Replies</span>
+            </label>
+          </div>
+        </div>
+      </section>
+
+      <!-- Status Banner -->
+      <div id="status-banner" class="status-banner hidden">
+        <div class="status-spinner"></div>
+        <div class="status-content">
+          <p class="status-title" id="status-title">Ripping thread...</p>
+          <p class="status-desc" id="status-desc">Launching headless browser, following redirect, and collecting chained posts...</p>
+        </div>
+      </div>
+
+      <!-- Result Card -->
+      <section id="result-section" class="result-section hidden">
+        <!-- Thread Info Header -->
+        <div class="card meta-card">
+          <div class="author-profile">
+            <img id="res-avatar" class="author-avatar" src="" alt="Avatar" />
+            <div class="author-meta">
+              <h2 id="res-author-name">Author Name</h2>
+              <a id="res-author-link" href="#" target="_blank" class="author-handle">@username</a>
+            </div>
+          </div>
+          <div class="thread-stats">
+            <div class="stat-box">
+              <span class="stat-number" id="res-segment-count">0</span>
+              <span class="stat-label">Segments Merged</span>
+            </div>
+            <div class="stat-box">
+              <span class="stat-number" id="res-word-count">0</span>
+              <span class="stat-label">Total Words</span>
+            </div>
+          </div>
+        </div>
+
+        <!-- Action Bar -->
+        <div class="action-bar">
+          <div class="tab-group">
+            <button class="tab-btn active" data-tab="reader">Reader View</button>
+            <button class="tab-btn" data-tab="markdown">Markdown</button>
+            <button class="tab-btn" data-tab="segments">Segments (<span id="tab-segment-count">0</span>)</button>
+          </div>
+
+          <div class="export-group">
+            <button id="copy-md-btn" class="btn btn-secondary btn-sm" title="Copy as Markdown">
+              <svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2"><rect x="9" y="9" width="13" height="13" rx="2" ry="2"/><path d="M5 15H4a2 2 0 0 1-2-2V4a2 2 0 0 1 2-2h9a2 2 0 0 1 2 2v1"/></svg>
+              Copy MD
+            </button>
+            <button id="copy-txt-btn" class="btn btn-secondary btn-sm" title="Copy Plain Text">
+              Copy Text
+            </button>
+            <div class="dropdown">
+              <button id="download-dropdown-btn" class="btn btn-primary btn-sm">
+                <svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2"><path d="M21 15v4a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2v-4"/><polyline points="7 10 12 15 17 10"/><line x1="12" y1="15" x2="12" y2="3"/></svg>
+                Download ▼
+              </button>
+              <div class="dropdown-menu" id="download-menu">
+                <a href="#" id="dl-md" class="dropdown-item">Download .md (Markdown)</a>
+                <a href="#" id="dl-txt" class="dropdown-item">Download .txt (Plain Text)</a>
+                <a href="#" id="dl-html" class="dropdown-item">Download .html (Standalone Page)</a>
+                <a href="#" id="dl-json" class="dropdown-item">Download .json (Raw Data)</a>
+              </div>
+            </div>
+            <button id="print-btn" class="btn btn-ghost btn-sm" title="Print or save as PDF">
+              <svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2"><polyline points="6 9 6 2 18 2 18 9"/><path d="M6 18H4a2 2 0 0 1-2-2v-5a2 2 0 0 1 2-2h16a2 2 0 0 1 2 2v5a2 2 0 0 1-2 2h-2"/><rect x="6" y="14" width="12" height="8"/></svg>
+            </button>
+          </div>
+        </div>
+
+        <!-- Tab Views -->
+        <div class="card view-card">
+          <!-- Reader View -->
+          <div id="view-reader" class="tab-view active">
+            <div id="reader-content" class="reader-typography"></div>
+          </div>
+
+          <!-- Markdown View -->
+          <div id="view-markdown" class="tab-view hidden">
+            <pre><code id="markdown-content"></code></pre>
+          </div>
+
+          <!-- Segments View -->
+          <div id="view-segments" class="tab-view hidden">
+            <div id="segments-container" class="segments-list"></div>
+          </div>
+        </div>
+      </section>
+    </main>
+
+    <!-- Slide-out Library Sidebar -->
+    <aside id="library-sidebar" class="library-sidebar">
+      <div class="sidebar-header">
+        <h3>Saved Threads</h3>
+        <button id="close-library-btn" class="btn btn-ghost btn-icon">✕</button>
+      </div>
+      <div class="sidebar-search">
+        <input type="text" id="library-search" placeholder="Search saved threads..." />
+      </div>
+      <div class="sidebar-list" id="library-list">
+        <!-- Rendered dynamically -->
+        <p class="empty-state">No threads ripped yet.</p>
+      </div>
+    </aside>
+  </div>
+
+  <!-- Toast Notification -->
+  <div id="toast" class="toast hidden"></div>
+
+  <script src="app.js"></script>
+</body>
+</html>
diff --git a/thread_ripper/static/style.css b/thread_ripper/static/style.css
new file mode 100644
index 0000000..814ddb8
--- /dev/null
+++ b/thread_ripper/static/style.css
@@ -0,0 +1,643 @@
+:root {
+  --bg-main: #0d1117;
+  --bg-card: #161b22;
+  --bg-input: #21262d;
+  --bg-hover: #30363d;
+  --border: #30363d;
+  --border-focus: #58a6ff;
+  --text-main: #f0f6fc;
+  --text-muted: #8b949e;
+  --accent: #2f81f7;
+  --accent-hover: #388bfd;
+  --accent-light: rgba(56, 139, 253, 0.15);
+  --success: #238636;
+  --danger: #da3633;
+  --radius: 12px;
+  --shadow: 0 8px 24px rgba(0, 0, 0, 0.25);
+  --font: "Inter", -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif;
+  --font-mono: "JetBrains Mono", Consolas, Monaco, monospace;
+}
+
+* {
+  box-sizing: border-box;
+  margin: 0;
+  padding: 0;
+}
+
+body {
+  font-family: var(--font);
+  background-color: var(--bg-main);
+  color: var(--text-main);
+  min-height: 100vh;
+  display: flex;
+  flex-direction: column;
+}
+
+.app-layout {
+  display: flex;
+  min-height: 100vh;
+  position: relative;
+  overflow-x: hidden;
+}
+
+.main-content {
+  flex: 1;
+  max-width: 900px;
+  margin: 0 auto;
+  padding: 40px 20px;
+  width: 100%;
+}
+
+/* Header */
+.app-header {
+  display: flex;
+  justify-content: space-between;
+  align-items: center;
+  margin-bottom: 32px;
+}
+
+.logo-group {
+  display: flex;
+  align-items: center;
+  gap: 16px;
+}
+
+.logo-icon {
+  width: 48px;
+  height: 48px;
+  border-radius: 14px;
+  background: linear-gradient(135deg, #1f6feb 0%, #8957e5 100%);
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  color: #fff;
+  box-shadow: 0 4px 16px rgba(31, 111, 235, 0.35);
+}
+
+.app-header h1 {
+  font-size: 1.6rem;
+  font-weight: 700;
+  letter-spacing: -0.02em;
+}
+
+.subtitle {
+  font-size: 0.9rem;
+  color: var(--text-muted);
+}
+
+.header-badges {
+  display: flex;
+  align-items: center;
+  gap: 12px;
+}
+
+.badge {
+  display: inline-flex;
+  align-items: center;
+  gap: 6px;
+  padding: 6px 12px;
+  border-radius: 20px;
+  font-size: 0.8rem;
+  font-weight: 500;
+}
+
+.docker-badge {
+  background: rgba(36, 150, 237, 0.15);
+  color: #58a6ff;
+  border: 1px solid rgba(56, 139, 253, 0.3);
+}
+
+/* Cards */
+.card {
+  background-color: var(--bg-card);
+  border: 1px solid var(--border);
+  border-radius: var(--radius);
+  padding: 24px;
+  box-shadow: var(--shadow);
+}
+
+/* Input Card */
+.input-card {
+  margin-bottom: 24px;
+}
+
+.url-input-container {
+  display: flex;
+  align-items: center;
+  background-color: var(--bg-input);
+  border: 1px solid var(--border);
+  border-radius: 10px;
+  padding: 6px 10px;
+  gap: 10px;
+  transition: border-color 0.2s, box-shadow 0.2s;
+}
+
+.url-input-container:focus-within {
+  border-color: var(--border-focus);
+  box-shadow: 0 0 0 3px rgba(88, 166, 255, 0.2);
+}
+
+.input-prefix {
+  color: var(--text-muted);
+  display: flex;
+  align-items: center;
+}
+
+.url-input-container input {
+  flex: 1;
+  background: transparent;
+  border: none;
+  outline: none;
+  color: var(--text-main);
+  font-size: 0.95rem;
+  font-family: var(--font);
+}
+
+.input-controls {
+  display: flex;
+  justify-content: space-between;
+  align-items: center;
+  margin-top: 16px;
+  flex-wrap: wrap;
+  gap: 12px;
+}
+
+.sample-links {
+  display: flex;
+  align-items: center;
+  gap: 8px;
+  font-size: 0.85rem;
+}
+
+.sample-label {
+  color: var(--text-muted);
+}
+
+.pill-btn {
+  background: var(--bg-input);
+  border: 1px solid var(--border);
+  color: var(--text-main);
+  padding: 4px 10px;
+  border-radius: 14px;
+  font-size: 0.8rem;
+  cursor: pointer;
+  transition: all 0.2s;
+}
+
+.pill-btn:hover {
+  background: var(--bg-hover);
+  border-color: var(--border-focus);
+}
+
+.mode-selector {
+  display: flex;
+  gap: 16px;
+  font-size: 0.85rem;
+}
+
+.radio-label {
+  display: flex;
+  align-items: center;
+  gap: 6px;
+  cursor: pointer;
+  color: var(--text-muted);
+}
+
+.radio-label input:checked + span {
+  color: var(--text-main);
+  font-weight: 500;
+}
+
+/* Buttons */
+.btn {
+  display: inline-flex;
+  align-items: center;
+  justify-content: center;
+  gap: 8px;
+  padding: 8px 16px;
+  font-size: 0.9rem;
+  font-weight: 500;
+  border-radius: 8px;
+  cursor: pointer;
+  border: 1px solid transparent;
+  transition: all 0.2s;
+  font-family: var(--font);
+}
+
+.btn-primary {
+  background-color: var(--accent);
+  color: #fff;
+}
+
+.btn-primary:hover {
+  background-color: var(--accent-hover);
+}
+
+.btn-secondary {
+  background-color: var(--bg-input);
+  border-color: var(--border);
+  color: var(--text-main);
+}
+
+.btn-secondary:hover {
+  background-color: var(--bg-hover);
+}
+
+.btn-ghost {
+  background: transparent;
+  color: var(--text-muted);
+}
+
+.btn-ghost:hover {
+  color: var(--text-main);
+  background: var(--bg-hover);
+}
+
+.btn-sm {
+  padding: 6px 12px;
+  font-size: 0.8rem;
+}
+
+.btn-icon {
+  padding: 6px;
+  border-radius: 6px;
+}
+
+/* Status Banner */
+.status-banner {
+  display: flex;
+  align-items: center;
+  gap: 16px;
+  background: var(--accent-light);
+  border: 1px solid var(--accent);
+  border-radius: var(--radius);
+  padding: 16px 20px;
+  margin-bottom: 24px;
+}
+
+.status-spinner {
+  width: 24px;
+  height: 24px;
+  border: 3px solid rgba(88, 166, 255, 0.3);
+  border-top-color: var(--accent);
+  border-radius: 50%;
+  animation: spin 1s infinite linear;
+}
+
+.btn-spinner {
+  width: 14px;
+  height: 14px;
+  border: 2px solid rgba(255, 255, 255, 0.3);
+  border-top-color: #fff;
+  border-radius: 50%;
+  animation: spin 1s infinite linear;
+}
+
+@keyframes spin {
+  to { transform: rotate(360deg); }
+}
+
+.status-title {
+  font-weight: 600;
+  font-size: 0.95rem;
+}
+
+.status-desc {
+  font-size: 0.85rem;
+  color: var(--text-muted);
+}
+
+/* Meta Card */
+.meta-card {
+  display: flex;
+  justify-content: space-between;
+  align-items: center;
+  padding: 16px 24px;
+  margin-bottom: 20px;
+}
+
+.author-profile {
+  display: flex;
+  align-items: center;
+  gap: 14px;
+}
+
+.author-avatar {
+  width: 48px;
+  height: 48px;
+  border-radius: 50%;
+  object-fit: cover;
+  border: 2px solid var(--border);
+}
+
+.author-meta h2 {
+  font-size: 1.1rem;
+  font-weight: 600;
+}
+
+.author-handle {
+  color: var(--accent);
+  text-decoration: none;
+  font-size: 0.85rem;
+}
+
+.author-handle:hover {
+  text-decoration: underline;
+}
+
+.thread-stats {
+  display: flex;
+  gap: 20px;
+}
+
+.stat-box {
+  display: flex;
+  flex-direction: column;
+  align-items: flex-end;
+}
+
+.stat-number {
+  font-size: 1.2rem;
+  font-weight: 700;
+  color: var(--text-main);
+}
+
+.stat-label {
+  font-size: 0.75rem;
+  color: var(--text-muted);
+  text-transform: uppercase;
+  letter-spacing: 0.05em;
+}
+
+/* Action Bar */
+.action-bar {
+  display: flex;
+  justify-content: space-between;
+  align-items: center;
+  margin-bottom: 16px;
+  flex-wrap: wrap;
+  gap: 12px;
+}
+
+.tab-group {
+  display: flex;
+  gap: 4px;
+  background: var(--bg-card);
+  border: 1px solid var(--border);
+  padding: 4px;
+  border-radius: 8px;
+}
+
+.tab-btn {
+  background: transparent;
+  border: none;
+  color: var(--text-muted);
+  padding: 6px 14px;
+  font-size: 0.85rem;
+  font-weight: 500;
+  border-radius: 6px;
+  cursor: pointer;
+  transition: all 0.2s;
+  font-family: var(--font);
+}
+
+.tab-btn.active {
+  background: var(--bg-hover);
+  color: var(--text-main);
+}
+
+.export-group {
+  display: flex;
+  align-items: center;
+  gap: 8px;
+  position: relative;
+}
+
+/* Dropdown */
+.dropdown {
+  position: relative;
+}
+
+.dropdown-menu {
+  position: absolute;
+  top: 100%;
+  right: 0;
+  margin-top: 6px;
+  background: var(--bg-card);
+  border: 1px solid var(--border);
+  border-radius: 8px;
+  box-shadow: var(--shadow);
+  display: none;
+  flex-direction: column;
+  min-width: 220px;
+  z-index: 100;
+  overflow: hidden;
+}
+
+.dropdown-menu.show {
+  display: flex;
+}
+
+.dropdown-item {
+  padding: 10px 14px;
+  color: var(--text-main);
+  text-decoration: none;
+  font-size: 0.85rem;
+  transition: background 0.2s;
+}
+
+.dropdown-item:hover {
+  background: var(--bg-hover);
+}
+
+/* Views */
+.view-card {
+  min-height: 400px;
+}
+
+.reader-typography {
+  font-size: 1.1rem;
+  line-height: 1.7;
+  color: #e6edf3;
+}
+
+.reader-typography h1, 
+.reader-typography h2 {
+  margin: 1.5rem 0 1rem;
+  font-weight: 600;
+}
+
+.reader-typography p {
+  margin-bottom: 1.25rem;
+}
+
+.reader-typography ul {
+  margin-bottom: 1.25rem;
+  padding-left: 1.5rem;
+}
+
+.reader-typography li {
+  margin-bottom: 0.5rem;
+}
+
+.reader-typography hr {
+  border: 0;
+  border-top: 1px solid var(--border);
+  margin: 2rem 0;
+}
+
+.reader-typography img {
+  max-width: 100%;
+  border-radius: 10px;
+  margin: 1rem 0;
+}
+
+/* Markdown view */
+#view-markdown pre {
+  background: var(--bg-input);
+  padding: 18px;
+  border-radius: 8px;
+  overflow-x: auto;
+  font-family: var(--font-mono);
+  font-size: 0.88rem;
+  line-height: 1.5;
+  color: #c9d1d9;
+}
+
+/* Segments breakdown */
+.segment-item {
+  border: 1px solid var(--border);
+  border-radius: 8px;
+  padding: 16px;
+  margin-bottom: 14px;
+  background: var(--bg-input);
+}
+
+.segment-header {
+  display: flex;
+  justify-content: space-between;
+  margin-bottom: 8px;
+  font-size: 0.8rem;
+  color: var(--text-muted);
+}
+
+.segment-num {
+  font-weight: 600;
+  color: var(--accent);
+}
+
+.segment-text {
+  font-size: 0.95rem;
+  line-height: 1.5;
+  white-space: pre-wrap;
+}
+
+/* Library Sidebar */
+.library-sidebar {
+  position: fixed;
+  top: 0;
+  right: -360px;
+  width: 340px;
+  height: 100vh;
+  background: var(--bg-card);
+  border-left: 1px solid var(--border);
+  box-shadow: -4px 0 24px rgba(0,0,0,0.4);
+  transition: right 0.3s ease;
+  z-index: 200;
+  display: flex;
+  flex-direction: column;
+}
+
+.library-sidebar.open {
+  right: 0;
+}
+
+.sidebar-header {
+  display: flex;
+  justify-content: space-between;
+  align-items: center;
+  padding: 20px;
+  border-bottom: 1px solid var(--border);
+}
+
+.sidebar-search {
+  padding: 12px 20px;
+  border-bottom: 1px solid var(--border);
+}
+
+.sidebar-search input {
+  width: 100%;
+  background: var(--bg-input);
+  border: 1px solid var(--border);
+  color: var(--text-main);
+  padding: 8px 12px;
+  border-radius: 6px;
+  font-size: 0.85rem;
+  outline: none;
+}
+
+.sidebar-list {
+  flex: 1;
+  overflow-y: auto;
+  padding: 16px;
+}
+
+.history-item {
+  background: var(--bg-input);
+  border: 1px solid var(--border);
+  border-radius: 8px;
+  padding: 12px;
+  margin-bottom: 10px;
+  cursor: pointer;
+  transition: border-color 0.2s, background 0.2s;
+}
+
+.history-item:hover {
+  border-color: var(--border-focus);
+  background: var(--bg-hover);
+}
+
+.history-item-title {
+  font-size: 0.9rem;
+  font-weight: 600;
+  margin-bottom: 4px;
+  display: -webkit-box;
+  -webkit-line-clamp: 2;
+  -webkit-box-orient: vertical;
+  overflow: hidden;
+}
+
+.history-item-meta {
+  font-size: 0.75rem;
+  color: var(--text-muted);
+  display: flex;
+  justify-content: space-between;
+}
+
+.empty-state {
+  text-align: center;
+  color: var(--text-muted);
+  font-size: 0.85rem;
+  padding: 30px 0;
+}
+
+/* Toast */
+.toast {
+  position: fixed;
+  bottom: 24px;
+  left: 50%;
+  transform: translateX(-50%);
+  background: #238636;
+  color: #fff;
+  padding: 10px 20px;
+  border-radius: 8px;
+  font-size: 0.9rem;
+  font-weight: 500;
+  box-shadow: 0 6px 20px rgba(0,0,0,0.3);
+  z-index: 999;
+  transition: opacity 0.3s;
+}
+
+.hidden {
+  display: none !important;
+}
diff --git a/thread_ripper/stitcher.py b/thread_ripper/stitcher.py
new file mode 100644
index 0000000..971a38b
--- /dev/null
+++ b/thread_ripper/stitcher.py
@@ -0,0 +1,233 @@
+import re
+from typing import List
+from .models import PostSegment
+
+def clean_segment_text(text: str) -> str:
+    """Clean up whitespace and trailing artifacts from text."""
+    lines = [l.strip() for l in text.split("\n")]
+    # Remove empty lines while preserving deliberate paragraph breaks
+    cleaned_lines = []
+    prev_blank = False
+    for line in lines:
+        if line:
+            cleaned_lines.append(line)
+            prev_blank = False
+        elif not prev_blank:
+            cleaned_lines.append("")
+            prev_blank = True
+    return "\n".join(cleaned_lines).strip()
+
+def build_markdown(author_name: str, author_handle: str, canonical_url: str, segments: List[PostSegment]) -> str:
+    """Stitches segments into a single cohesive Markdown document."""
+    lines = []
+    title = segments[0].text.split("\n")[0] if segments and segments[0].text else "Threads Post"
+    if len(title) > 80:
+        title = title[:77] + "..."
+
+    lines.append(f"# {title}")
+    lines.append("")
+    lines.append(f"**Author:** [{author_name} (@{author_handle})](https://www.threads.net/@{author_handle})  ")
+    lines.append(f"**Original Post:** [{canonical_url}]({canonical_url})  ")
+    lines.append(f"**Thread Segments:** {len(segments)}")
+    lines.append("")
+    lines.append("---")
+    lines.append("")
+
+    for idx, seg in enumerate(segments):
+        cleaned_text = clean_segment_text(seg.text)
+        if not cleaned_text and not seg.images:
+            continue
+
+        if cleaned_text:
+            lines.append(cleaned_text)
+            lines.append("")
+
+        # Include media images if any
+        for img in seg.images:
+            alt = img.alt_text or f"Thread Image {idx + 1}"
+            lines.append(f"![{alt}]({img.url})")
+            lines.append("")
+
+    lines.append("---")
+    lines.append(f"*Ripped with Thread Ripper from [Threads]({canonical_url})*")
+    return "\n".join(lines).strip()
+
+def build_plain_text(author_name: str, author_handle: str, canonical_url: str, segments: List[PostSegment]) -> str:
+    """Stitches segments into clean plain text."""
+    output = []
+    output.append(f"{author_name} (@{author_handle})")
+    output.append(f"Source: {canonical_url}")
+    output.append("=" * 60)
+    output.append("")
+
+    for seg in segments:
+        cleaned_text = clean_segment_text(seg.text)
+        if cleaned_text:
+            output.append(cleaned_text)
+            output.append("")
+
+    output.append("=" * 60)
+    return "\n".join(output).strip()
+
+def build_standalone_html(author_name: str, author_handle: str, author_avatar: str, canonical_url: str, segments: List[PostSegment]) -> str:
+    """Generates an elegant, responsive standalone HTML file."""
+    title = segments[0].text.split("\n")[0] if segments and segments[0].text else f"Thread by @{author_handle}"
+    if len(title) > 80:
+        title = title[:77] + "..."
+
+    content_sections = []
+    for idx, seg in enumerate(segments):
+        cleaned_text = clean_segment_text(seg.text)
+        paragraphs = cleaned_text.split("\n")
+        section_html = "<div class='thread-segment'>"
+        
+        # Render bullet points or paragraphs cleanly
+        in_list = False
+        for p in paragraphs:
+            p = p.strip()
+            if not p:
+                continue
+            if p.startswith("- ") or p.startswith("• "):
+                if not in_list:
+                    section_html += "<ul>"
+                    in_list = True
+                section_html += f"<li>{p[2:]}</li>"
+            else:
+                if in_list:
+                    section_html += "</ul>"
+                    in_list = False
+                section_html += f"<p>{p}</p>"
+        if in_list:
+            section_html += "</ul>"
+
+        # Attached images
+        for img in seg.images:
+            section_html += f"<div class='segment-image'><img src='{img.url}' alt='{img.alt_text or ''}' loading='lazy' /></div>"
+
+        section_html += "</div>"
+        content_sections.append(section_html)
+
+    body_content = "\n".join(content_sections)
+    avatar_tag = f"<img class='avatar' src='{author_avatar}' alt='{author_handle}' />" if author_avatar else ""
+
+    html = f"""<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width, initial-scale=1.0">
+<title>{title} - Thread Ripper</title>
+<style>
+  :root {{
+    --bg: #0e1117;
+    --card: #161b22;
+    --text: #e6edf3;
+    --text-muted: #8b949e;
+    --border: #30363d;
+    --accent: #58a6ff;
+  }}
+  @media (prefers-color-scheme: light) {{
+    :root {{
+      --bg: #f6f8fa;
+      --card: #ffffff;
+      --text: #1f2328;
+      --text-muted: #656d76;
+      --border: #d0d7de;
+      --accent: #0969da;
+    }}
+  }}
+  body {{
+    font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Helvetica, Arial, sans-serif;
+    background: var(--bg);
+    color: var(--text);
+    line-height: 1.65;
+    margin: 0;
+    padding: 32px 16px;
+    display: flex;
+    justify-content: center;
+  }}
+  .article {{
+    max-width: 680px;
+    width: 100%;
+    background: var(--card);
+    border: 1px solid var(--border);
+    border-radius: 16px;
+    padding: 40px;
+    box-shadow: 0 8px 30px rgba(0,0,0,0.12);
+  }}
+  .header {{
+    display: flex;
+    align-items: center;
+    gap: 16px;
+    margin-bottom: 28px;
+    padding-bottom: 20px;
+    border-bottom: 1px solid var(--border);
+  }}
+  .avatar {{
+    width: 54px;
+    height: 54px;
+    border-radius: 50%;
+    object-fit: cover;
+  }}
+  .author-info h2 {{
+    margin: 0;
+    font-size: 1.25rem;
+  }}
+  .author-info a {{
+    color: var(--accent);
+    text-decoration: none;
+    font-size: 0.95rem;
+  }}
+  .thread-segment {{
+    margin-bottom: 24px;
+    font-size: 1.1rem;
+  }}
+  .thread-segment p {{
+    margin: 0 0 16px 0;
+  }}
+  .thread-segment ul {{
+    margin: 0 0 16px 0;
+    padding-left: 24px;
+  }}
+  .thread-segment li {{
+    margin-bottom: 8px;
+  }}
+  .segment-image img {{
+    max-width: 100%;
+    border-radius: 12px;
+    margin-top: 12px;
+  }}
+  .footer {{
+    margin-top: 36px;
+    padding-top: 20px;
+    border-top: 1px solid var(--border);
+    font-size: 0.85rem;
+    color: var(--text-muted);
+    display: flex;
+    justify-content: space-between;
+  }}
+  .footer a {{
+    color: var(--accent);
+    text-decoration: none;
+  }}
+</style>
+</head>
+<body>
+  <article class="article">
+    <div class="header">
+      {avatar_tag}
+      <div class="author-info">
+        <h2>{author_name}</h2>
+        <a href="{canonical_url}" target="_blank">@{author_handle} on Threads</a>
+      </div>
+    </div>
+    <div class="thread-body">
+      {body_content}
+    </div>
+    <div class="footer">
+      <span>Reconstructed as 1 single post ({len(segments)} segments)</span>
+      <a href="{canonical_url}" target="_blank">View Original Post ↗</a>
+    </div>
+  </article>
+</body>
+</html>"""
+    return html
diff --git a/thread_ripper/storage.py b/thread_ripper/storage.py
new file mode 100644
index 0000000..9586677
--- /dev/null
+++ b/thread_ripper/storage.py
@@ -0,0 +1,76 @@
+import os
+import json
+from typing import List, Optional
+from pathlib import Path
+from .models import RippedThread, HistorySummary
+
+class ThreadStorage:
+    def __init__(self, data_dir: str = "data"):
+        self.data_dir = Path(data_dir)
+        self.threads_dir = self.data_dir / "threads"
+        self.threads_dir.mkdir(parents=True, exist_ok=True)
+
+    def save(self, thread: RippedThread) -> str:
+        """Saves a ripped thread to disk in JSON, MD, and HTML formats."""
+        file_path = self.threads_dir / f"{thread.id}.json"
+        with open(file_path, "w", encoding="utf-8") as f:
+            f.write(thread.model_dump_json(indent=2))
+
+        # Also save standalone .md and .html files for direct browsing
+        md_path = self.threads_dir / f"{thread.id}.md"
+        with open(md_path, "w", encoding="utf-8") as f:
+            f.write(thread.stitched_markdown)
+
+        html_path = self.threads_dir / f"{thread.id}.html"
+        with open(html_path, "w", encoding="utf-8") as f:
+            f.write(thread.stitched_html)
+
+        txt_path = self.threads_dir / f"{thread.id}.txt"
+        with open(txt_path, "w", encoding="utf-8") as f:
+            f.write(thread.stitched_text)
+
+        return thread.id
+
+    def get(self, thread_id: str) -> Optional[RippedThread]:
+        """Loads a saved ripped thread by ID."""
+        file_path = self.threads_dir / f"{thread_id}.json"
+        if not file_path.exists():
+            return None
+        with open(file_path, "r", encoding="utf-8") as f:
+            data = json.load(f)
+            return RippedThread(**data)
+
+    def list_history(self) -> List[HistorySummary]:
+        """Lists summaries of all previously ripped threads, newest first."""
+        history = []
+        for file in self.threads_dir.glob("*.json"):
+            try:
+                with open(file, "r", encoding="utf-8") as f:
+                    data = json.load(f)
+                    history.append(
+                        HistorySummary(
+                            id=data["id"],
+                            title=data.get("title", "Untitled Thread"),
+                            author_handle=data.get("author_handle", "unknown"),
+                            author_name=data.get("author_name", "Unknown"),
+                            segment_count=data.get("segment_count", len(data.get("segments", []))),
+                            total_words=data.get("total_words", 0),
+                            saved_at=str(data.get("saved_at", ""))[:19],
+                            original_url=data.get("original_url", "")
+                        )
+                    )
+            except Exception:
+                continue
+        # Sort by saved_at descending
+        history.sort(key=lambda x: x.saved_at, reverse=True)
+        return history
+
+    def delete(self, thread_id: str) -> bool:
+        """Deletes a saved thread and all associated format files."""
+        deleted = False
+        for ext in [".json", ".md", ".html", ".txt"]:
+            f = self.threads_dir / f"{thread_id}{ext}"
+            if f.exists():
+                f.unlink()
+                deleted = True
+        return deleted