Does repoprep upload my code to a server?

No. All file processing happens entirely inside your browser using native Web APIs. Your files never leave your device.

What AI tools does repoprep work with?

repoprep generates a plain-text context file that works with any AI tool that accepts pasted text — including Claude, ChatGPT, Gemini, Cursor, and others.

Is the Pro plan a subscription?

No. The Pro plan is a one-time payment of $5 USD. There are no subscriptions or recurring charges. Your licence is perpetual.

What file types does repoprep support?

repoprep supports project folders, ZIP archives, individual code files, PDFs, and most plain-text documents.

Do I need an account to use repoprep?

No account is needed for the free plan. Pro users verify their licence with the purchase email — no sign-up or password required.

Free to start — $5 one-time for Pro

Turn your codebase into
AI-ready context

Upload a project folder, ZIP, or files — get a single structured context ready to paste into any AI tool. Private. Instant.

Upload project — it’s free See how it works

Works with

ClaudeChatGPTGeminiCursorCopilotMistral

Upload your files

Drop your project folder or files here

Supports ZIP archives, entire folders, PDFs, DOCX, and all code & text files. Sensitive files like .env are automatically blocked.

🔒 All processing is local — files never leave your browser

How it works

Three steps to AI-ready context

No signup. No server. Everything runs locally in your browser.

Upload your project

Drag & drop a folder, ZIP file, or individual files. Supports code, PDFs, DOCX, Markdown, and more.

Context is generated

Repoprep builds a clean directory tree and extracts all file contents into one structured document.

Paste into any AI tool

One click to copy. Paste directly into Claude, ChatGPT, Gemini, Copilot — any AI chat tool instantly.

Output format

Structured output AI
understands

Repoprep generates a clean project tree followed by each file’s content, labeled with its path — the structure AI models understand best.

Project tree shows AI the full structure

Each file clearly labelled with its path

Token count so you stay within limits

context_output.txt

===== PROJECT STRUCTURE =====

my-app/

├── src/

│ ├── App.tsx

│ └── index.ts

├── package.json

└── README.md

===== FILE CONTENTS =====

--- src/App.tsx ---

import React from 'react';

export default function App() {

return <div>Hello</div>

}

// ~2,400 tokens estimated

Features

Everything your AI context needs

Built for developers who want results, not complexity.

Core

Folder & ZIP support

Upload entire project directories or zip files. repoprep extracts the full structure automatically.

Core

All major file types

JS, TS, PY, GO, PDF, DOCX, MD, JSON, YAML, HTML, CSS — if it has text, we read it.

Privacy

100% private

All processing happens in your browser. Nothing is ever sent to any server. Zero telemetry.

Pro

Token estimator

See the estimated token count before pasting so you never blow your context window.

Core

Smart filtering

Auto-skips node_modules, .git, dist and other noise. Only what matters gets packaged.

Core

AI-ready format

Output is structured with a project tree + file contents — exactly how AI models read best.

Pricing

Simple, honest pricing

Free for small projects. Upgrade once — use forever.

Free

$0forever

Up to 10 files per package

Up to 2 MB total size

All supported file types

Copy & download output

Start for free

Pro

Common questions

Everything you need to know before you start. Something missing? Ask us.

What exactly is repoprep?

repoprep is a browser-based tool that bundles your entire codebase — or any collection of files — into a single structured text file that AI models can actually read. Instead of pasting files one by one into Claude, ChatGPT, or Gemini, you upload your project once and get a clean, AI-ready context file in seconds.

Is my code ever uploaded to a server?

Never. All processing happens entirely inside your browser using Web APIs. Your files are read locally, processed locally, and the output is generated locally. Nothing leaves your machine. repoprep has no backend, no database, and zero telemetry — your code stays yours.

Which AI tools does the output work with?

Any AI that accepts text input: Claude (Anthropic), ChatGPT (OpenAI), Gemini (Google), Cursor, GitHub Copilot, Mistral, and any other model with a context window. The output is plain text with a project tree header followed by each file's content — a format all major models handle well.

What file types are supported?

repoprep reads virtually every developer file type: JavaScript, TypeScript, Python, Go, Rust, Ruby, Java, C/C++, Markdown, JSON, YAML, TOML, HTML, CSS, SQL, shell scripts, and more. It also extracts text from PDF and DOCX files. Binary files like images are automatically skipped.

What's the difference between the free plan and Pro?

The free plan supports up to 10 files and 2 MB of total input — plenty for small components, bug reports, or quick questions. Pro ($5 one-time, no subscription) raises those limits to 200 files and 100 MB, covering full-scale monorepos and large projects. You pay once and own it permanently.

How do I use the output file with Claude or ChatGPT?

Once repoprep generates your context file, click 'Copy to clipboard' and paste it directly into Claude, ChatGPT, or any other AI chat. For models that support file uploads (like Claude Projects or the ChatGPT file tool), you can also download the .txt file and attach it. Either way, the AI instantly has full awareness of your entire project.

Does it handle large projects with node_modules or .git folders?

Yes — repoprep automatically skips common noise directories like node_modules, .git, dist, build, .next, __pycache__, and others. You get only the source files that matter. The Pro plan handles projects up to 100 MB and 200 files, covering most real-world monorepos.

How accurate is the token count estimate?

The token estimator uses a character-based heuristic (approximately 4 characters per token) that is accurate to within about 10–15% for typical source code. It is intentionally shown as an estimate, not a guarantee — context window limits vary by model and version, so treat it as a guide rather than a hard number.

Built for developers