📦 ContextPack

ContextPack is a streamlined tool designed to bundle your programming projects into a single, well-structured Markdown file. It provides an ideal way to feed your entire codebase as context into Large Language Models (LLMs) like GPT-4o, Claude 3.5, or Gemini 1.5 Pro.

✨ Key Features

• Smart Bundling: Automatically merges project files into one context.md file.
• Integrated Ignore System: Uses .gitignore logic to filter out noise, logs, and dependencies.
• Client-Side Optimization: Folders are compressed into ZIP format directly in the browser using JSZip to reduce server load.
• Safety Constraints:
  • Maximum File Count: 5,000 files.
  • Maximum Total Size: 700 MB.
• Language Templates: Built-in exclusion presets for popular languages including Python, JavaScript, Go, Rust, and more.

🚀 Tech Stack

• Backend: FastAPI (Python) for high-performance processing.
• Frontend: Vanilla JavaScript + JSZip for efficient client-side archiving.
• Containerization: Docker for seamless deployment.

🛠 Installation & Deployment (Docker)

The project is fully containerized for easy setup. Follow these steps to get started:

1. Clone the Repository:

   git clone https://github.com/TalonProbeite/context-pack.git
   cd contextpack

2. Build the Docker Image:

   docker build -t contextpack .

3. Run the Container:

   docker run -p 8000:8000 contextpack

4. Access the App: Open http://localhost:8000 in your browser.

📖 How to Use

1. Select Source: Upload a .zip file or select a project folder (which will be zipped automatically).
2. Apply Filters: Choose a language template (e.g., Python or JavaScript) or manually edit the Ignore List.
3. Generate: Click "Generate context.md". After processing, the file will download automatically.

📊 LLM Context Limits (Reference)

Model	Context Window	Approx. Code Capacity
GPT-4o	128k tokens	~10k - 15k lines
Claude 3.5	200k tokens	~20k - 25k lines
Gemini 1.5 Pro	2M tokens	150k+ lines

---

© 2026 ContextPack - Project Context Packager