Does MashuPack upload my code to a server?

No. MashuPack is a static browser application with no backend server. It reads your files using the browser's built-in File System Access API. All processing, including building the file tree and creating the export, happens entirely client-side in your browser. No data is uploaded to any server by MashuPack. If you choose to upload the resulting text file to an AI tool, that action is governed by that AI tool's privacy policy, not MashuPack's.

How does the exported file help AI tools like ChatGPT?

The exported file uses explicit START/END markers with full file paths. This structure allows AI tools with internal environments (like ChatGPT and Claude) to treat the export as a virtual project. Instead of reading a wall of text, the model can "grep" or search for specific files, read them individually, trace imports, and navigate the codebase efficiently, which is more effective than a naive context dump.

Can MashuPack handle very large repositories?

Yes. While the initial filesystem scan for a very large repo (e.g., tens of thousands of files) can take 10-20 seconds due to browser-level enumeration, subsequent operations are fast. MashuPack uses a virtualized tree renderer and a high-performance Rust/WebAssembly engine in a Web Worker to handle large projects smoothly. Tests on the kubernetes/kubernetes repository (28,481 files) showed a total visible load time of ~20.9 seconds.

How do I estimate the size of my export for an AI model's context window?

In the right-hand statistics panel, click the "Size" stat to toggle it from bytes to an estimated token count. The tool uses an approximation of ~4 characters per token, consistent with GPT and Claude tokenizers for typical code. This allows you to check if your selection will fit within your AI tool's context limit before exporting.

What technology stack is MashuPack built with?

MashuPack is a static site built with TypeScript for UI logic and Vite as the build tool. Its key performance feature is the indexing and selection logic written in Rust, compiled to WebAssembly (WASM) and run in a Web Worker to avoid blocking the browser's main thread. It uses the File System Access API for local folder access, virtualized tree rendering for smooth scrolling, and CodeMirror for syntax-highlighted file previews.

MashuPack: Convert Repos to Structured Text for ChatGPT & Claude

MashuPack Overview

MashuPack is a client-side web application designed to prepare local code repositories for use with large language models (LLMs) such as ChatGPT and Claude. It solves the problem of naive context dumps by generating a structured export file with clear file path headers and boundaries, allowing AI tools to grep, search, and navigate the code efficiently, much like a developer would in a terminal. All operations run entirely within the user's browser, with no data uploaded to any server, ensuring complete privacy.

How to use MashuPack

1. Load your project by either dragging and dropping a folder onto the application or clicking "Browse for folder" to use the native file picker. 2. Use the interactive file tree to browse, filter (press `/` to focus search), and select specific files or folders for inclusion. Ticking a folder selects all its contents. 3. Check the project statistics in the right panel, especially the token count estimate (toggle by clicking the Size stat) to ensure it fits within your AI model's context window. 4. Export the selection using one of the options: "Export combined text" to download a `.txt` file for AI upload, "Copy to clipboard" for direct pasting into a chat, or "Save as .txt".

Core Features of MashuPack

Structured Export Format: Generates a plain text file with a directory tree header and each file wrapped in explicit START/END path markers, enabling reliable navigation by AI models.
Complete Browser-Based Processing: Uses the File System Access API to read local folders without uploading content. All indexing and computation happens client-side.
High-Performance Engine: Indexing and selection math run in Rust compiled to WebAssembly, offloaded to a Web Worker to keep the UI smooth even with massive repositories (e.g., 28,000+ files).
Intelligent File Selection & Filtering: Supports selection by checkbox, file-type pills, or the right-panel file types table. Provides live stats (files, folders, size, token estimate).
Built-in File Viewer: Preview files with syntax highlighting (powered by CodeMirror) without affecting the export selection.
Multiple Export Options: Export combined text as a file, copy report to clipboard, or download the project as a ZIP archive.

Use Cases for MashuPack

MashuPack is ideal for developers and teams looking to leverage AI for code analysis, review, documentation, or debugging. It allows you to provide an entire codebase structure to an AI, enabling it to trace dependencies, locate specific functions, and understand project layout without being overwhelmed by a single context dump. It's particularly useful for onboarding new projects, generating summaries, or asking complex, cross-file questions about a repository.

Advantages of MashuPack

The primary advantage is significantly enhancing the utility of AI for code by providing a structured, navigable context rather than a flat text dump. This respects the internal mechanisms of modern LLMs that can parse structured data. Furthermore, it offers robust privacy by keeping all data local, and delivers exceptional performance through its Rust/WASM architecture, making it practical for real-world, large-scale projects. The user interface is intuitive, with powerful selection and filtering tools to refine the exact context sent to the AI.

MashuPack FAQ

MashuPack Comments (0)

No comments yet.

MashuPack Alternatives

Freemium

ContextStrata

ContextStrata is an LLM rules and knowledge base platform designed to empower AI assistants with comprehensive context. It centralizes LLM rules and creates a searchable knowledge base from GitHub repositories, ensuring real-time updates and secure encryption for sensitive information.

Llm Management

6.4K94113

Freemium

Cosmicup

Cosmicup is an all-in-one AI platform offering unlimited access to a wide array of advanced AI models like ChatGPT 5, Claude 4.5, Gemini 2.5, and Grok 4 through a single subscription. It streamlines workflows with features including multi-model interaction, code assistance, document analysis, real-time web search, deep research, and AI image generation, eliminating the need for multiple subscriptions.

Multimodal Ai

20.6K113127

Command Center

Command Center is a "Post-IDE" designed for AI agents, enabling developers to maintain high code quality, understand AI-generated changes, and efficiently refactor code. It provides real-time diff viewing, one-click extension installation, and tools to make any codebase agent-native, ensuring AI contributions are clean and comprehensible.

Code Generation

9.9K117128

Free

Markdown Studio

Markdown Studio is a free, AI-powered Markdown editor designed for developers and prompt engineers. It streamlines AI workflows with features like real-time token counting for LLMs (GPT-4, Claude, Gemini), AI prompt templates, and smart copy formats, all within a feature-rich, multi-tab editing environment that requires no login.

Text Generation

6.4K121123

Freemium

Apistack

Apistack is an enterprise API marketplace and AI integration hub, offering over 100 production-ready REST APIs. It features a developer-first platform with tools for real-time testing, usage analytics, and seamless integration with AI agents like ChatGPT and Claude via Model Context Protocol (MCP) servers.

Integration

6.3K132124

MashuPack Categories

Ai Workflow Enhancements Code Repository Tools Developer Tools

MashuPack Tags

AI context browser app chatgpt Claude codebase analysis code packaging developer tools privacy-focused repository converter WebAssembly

MashuPack Jobs

AI Engineer Code Reviewer DevOps Engineer Project Manager Software Developer Systems Architect Technical Lead

MashuPack Embed Widget

Copy this embed code to place the badge on your blog, article, or product site and send readers directly to this ToolMage detail page.

ToolMageFOLLOW US ON▲ 16

<a href="https://www.toolmage.com/en/tool/mashupack/" target="_blank" rel="noopener noreferrer" style="text-decoration: none; display: inline-block;"><div style="box-sizing: border-box; width: 280px; height: 75px; background: white; border: 2px solid #dbeafe; border-radius: 12px; box-shadow: 0 4px 12px rgba(0,0,0,0.15); padding: 16px; display: flex; align-items: center; justify-content: space-between; font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;"><div style="display: flex; align-items: center; gap: 12px;"><img src="https://www.toolmage.com/media/site/favicon.ico" alt="ToolMage" style="width: 32px; height: 32px;"><div><div style="font-size: 14px; font-weight: 600; color: #111827; margin: 0; line-height: 1.2;">ToolMage</div><div style="font-size: 12px; color: #6b7280; margin: 0; line-height: 1.2;">FOLLOW US ON</div></div></div><div style="display: flex; align-items: center; gap: 8px; background: #fef2f2; border-radius: 8px; padding: 8px 12px;"><svg style="width: 16px; height: 16px; color: #ef4444;" fill="currentColor" viewBox="0 0 24 24" aria-hidden="true"><path d="M12 2L22 20H2L12 2Z"/></svg><img src="https://www.toolmage.com/embed/tool/mashupack/likes.svg?theme=light" alt="likes" style="height: 16px; display: block;"></div></div></a>