Free VS Code Extension · No API key needed

Give your AI your entire
codebase. Not 20 files.

Bundle your errors and 100+ project files into one paste-ready block for Claude, ChatGPT, or any AI — then paste the reply back and apply the edits to your files. Full round trip, inside your editor.

⚡ Install Free on VS Code View Pro →
100+
files in one paste
4
output formats
0
data sent to us
$0
monthly — Pro is $9 once
bundle output — standard format
1================================================================
2PROJECT: my-saas-app
3FILES INCLUDED: 84 | FILES IGNORED: 1,204
4ESTIMATED TOKENS: 38,421 (~$0.038 Haiku · $0.115 Sonnet)
5================================================================
6 
7FILE TREE:
8📁 src/
9  📄 index.ts 📁 components/  📄 App.tsx ...
10 
11================================================================
12FILE: src/index.ts
13================================================================
14[ full file content … ]
works with →
Claude
ChatGPT
Gemini
Grok
Copilot
Any AI

Three steps.
Zero friction.

Open VS Code, press one shortcut, paste into any AI chat. That's the entire workflow.

01
📂
Open your project

Open any project in VS Code. SendToAI lives in the sidebar and auto-scans your file tree — ignoring node_modules, lock files, binaries, and anything in .gitignore.

02
Hit the shortcut

Press the keyboard shortcut to bundle. Select exactly which files to include with the visual file picker, choose your format, and add a prompt template.

Ctrl+Alt+A ⌘+Alt+A
03
🤖
Paste — then apply the reply

Your entire project is on the clipboard. Paste into Claude, ChatGPT, or any AI chat — then copy the reply and hit Apply AI Reply to write the edits back to your files. Reviewable, undoable with Ctrl+Z.

Everything you need
to give AI full context.

🐛
Bundle Errors

One click bundles every file VS Code is flagging plus the exact error messages, with a ready-to-paste "please fix these" prompt. Web bundlers can't see your Problems panel — this can.

📥
Apply AI Reply

Copy the AI's answer, run one command, and pick which edits to write back to your files. Reviewable in git diff, undoable with a single Ctrl+Z. No more hand-copying snippets.

🧠
Smart Trim PRO

When a bundle must shrink to fit, files are ranked by relevance to your prompt — and files they import survive the cut with them. Connected context, not orphaned snippets.

🗂️
Visual File Picker

Checkbox tree with tri-state directory selection. See token estimates per file and folder before you bundle. Select exactly what the AI needs.

📋
Named Presets PRO

Save your file selections as named presets. One click to reload "backend only", "frontend only", or any custom context you use repeatedly.

🔀
Git Diff Mode PRO

Bundle only modified and staged files from your current git diff. Perfect for asking AI to review or explain just what changed.

🎯
Fit to AI Window PRO

Select a target AI (ChatGPT Free 8K, ChatGPT Plus 32K, Claude 200K, Gemini 1M) and SendToAI keeps what actually matters for your task — ranking every file by your prompt and following the import graph so its dependencies survive the cut too. Dumb bundlers drop the biggest files; this drops the least relevant. Never crash your AI with an oversized paste again.

📊
4 Context Window Bars

After every bundle, see exactly how full you are against ChatGPT Free, ChatGPT Plus, Claude, and Gemini — color coded green/yellow/red so you know exactly what will work.

🏷️
4 Output Formats

Standard plain text, Claude XML (structured tags), Compact (strips comments, ~20% fewer tokens), or Minimal (max token savings). Pick what works for your AI.

📝
Project Notes

Persistent context memory per project. Save architecture notes, tech stack info, or key constraints and include them in every bundle automatically.

📄
Open Tabs Mode

Bundle only the files currently open in your editor. Great for focused sessions where you're only working in a few files.

🔒
100% Local

Your source code never leaves your machine. All bundling is local. We collect zero telemetry, zero analytics, zero file data. Ever.

Start free.
Upgrade when you need it.

The free tier is genuinely useful. Pro unlocks the power features for heavy users.

Free
$0
forever · no account needed
  • Up to 50 files per bundle
  • Bundle Errors + Apply AI Reply
  • All 4 output formats
  • Open Tabs mode
  • Project Notes
  • Token + cost estimator
  • 4 context window bars
  • Smart auto-ignore
  • Unlimited files
  • Named presets
  • Git diff mode
  • Fit to AI Window
Install from Marketplace →
FeatureFreePro
Files per bundleUp to 50Unlimited
Bundle Errors (from the Problems panel)
Apply AI Reply (write edits back, undoable)
Output formats (Standard, XML, Compact, Minimal)
Open Tabs mode
Visual file picker
Token + cost estimator
4 context window bars
Project notes / context memory
Named presets
Git diff mode
Fit to AI Window (smart relevance trim)
Pro license machines3
PriceFree$9 one-time

Common questions.

Install SendToAI in VS Code, open your project, and press Ctrl+Alt+B (⌘+Alt+B on Mac). It scans your file tree, skips node_modules, lock files, binaries and anything in .gitignore, and copies everything else to your clipboard as one structured text block — a file tree plus every file's contents, clearly labelled. Paste that single block into the ChatGPT or Claude chat box and the AI can see your whole project at once.
ChatGPT's upload limit (about 20 files per message) applies to file attachments. SendToAI sidesteps it by turning your project into one pasted text block instead — pasted text has no file count at all. The real constraint becomes the model's context window, which SendToAI shows you before you paste: color-coded bars for ChatGPT Free, ChatGPT Plus, Claude, and Gemini tell you whether your bundle fits.
The free tier bundles up to 50 files per bundle; Pro ($9 one-time) removes the cap entirely. In practice the binding limit is your AI's context window, not the file count — a 200-file project may fit Claude's 200K window easily while 30 huge files won't fit ChatGPT Free. The token estimator and context bars show this before you paste, and Pro's Fit to AI Window auto-trims the bundle to a chosen model's window.
Never. All file reading and bundling happens entirely on your local machine. The only network request the extension ever makes is to validate your Pro license key with Lemon Squeezy — and that's just a UUID, not your code. Your source code is only sent to wherever you paste it (i.e. Claude, ChatGPT, etc.), and that's entirely in your control.
Lemon Squeezy delivers your license key immediately by email upon payment. You'll also find it on your order page. Once you have it, open VS Code, open the Command Palette (Ctrl+Shift+P), and run "SendToAI: Enter License Key". Paste in the key and you're activated.
Yes — each Pro license allows activation on up to 3 machines. If you need more, contact us and we can accommodate team setups.
14-day full refund, no questions asked. If you're not happy for any reason within 14 days of purchase, email support@sendtoai.dev and we'll refund you immediately. See the full Refund Policy.
No. SendToAI Pro is a one-time payment of $9. You get a lifetime license with no recurring charges, and all future Pro features are included.
A Pro feature that automatically sizes your bundle to fit a specific AI's context window. Pick "ChatGPT Plus 32K" and SendToAI keeps the files most relevant to what you're working on — ranked by your prompt plus the import graph, so the dependencies of those files come along too — and drops the least relevant until it fits. Dumb bundlers cut the biggest files; this one cuts the least useful.
Any AI that accepts text input. It's been tested and optimized for Claude (with a dedicated XML format), ChatGPT, Gemini, Grok, GitHub Copilot Chat, and any other AI assistant or API that accepts text context.

Stop pasting files one by one.

Install free in 10 seconds. Works with every AI. Your code stays on your machine.

⚡ Install Free on VS Code View Pro →