Introduction

FileConcat is a privacy-first tool that packs the files you pick into a single LLM-ready blob. The output is one XML or Markdown document you can paste into Claude, ChatGPT, Gemini, or any other assistant that takes long-form context.

What it gives you

• A workbench at fileconcat.com for drag, drop, filter, and copy.
• A published npm CLI (pnpm add -g @fileconcat/cli, or npx @fileconcat/cli) for the same flow from a shell.
• Live token counting against the tokenizer most modern LLMs use, so you know how much of your context window the output consumes before you paste it.

How it works

Everything runs in your browser. There is no upload step, no intermediate server, and no telemetry on the files you process. The core library (@fileconcat/core) is the same in the web app and the CLI; what differs is the surface you drive it from.

Supported sources

You can feed the workbench from any of these:

• Local files and folders, by drag-and-drop or file picker
• GitHub repositories, including subdirectories
• GitHub Gists
• GitLab repositories, including nested groups
• GitLab Snippets
• Bitbucket repositories
• Any other public URL via the URL fallback adapter

Next steps

• Quick start walks through the first import.
• File filtering covers the glob patterns and preset chips that narrow the output.
• Token estimation explains the counter and the model selector.