🎉 Now with Windows Hello Simple Mode

Secrets Manager for
Claude Code

Stop AI coding assistant secrets exposure. Encrypt your .env files on Windows with Windows Hello and let Claude Code deploy, test, and run commands—without ever seeing your API keys.

AES-256
Military-grade encryption
60 sec
Setup time
Zero
Secrets exposed to AI
PowerShell - Claude Code
# Claude writes this command:
curl -H "Authorization: Bearer $env:API_KEY" https://api.example.com
[Windows Hello] Verify your identity...
✓ Secret injected into subprocess
{"status": "success", "data": [...]}
# Claude never sees your API key 🔒

Secrets Flow Securely

Your secrets never leave your machine unencrypted. Claude Code gets access without visibility.

🔐 How It Works

  1. 1

    You add secrets to your .env file

    API keys, database URLs, tokens — anything sensitive goes here.

  2. 2

    LLM Secrets encrypts with Windows Hello

    AES-256-CBC encryption, hardware-backed master key via DPAPI.

  3. 3

    Claude Code sees only variable names

    CLAUDE.md tells Claude what secrets exist, never the values.

  4. 4

    Secrets inject at runtime only

    Values exist in subprocess memory, never logged or returned.

🛡️ Zero Knowledge

Secrets are decrypted in memory, used once, then discarded. Never written to disk or logs.

🔗 Hardware Bound

Master key protected by Windows Hello TPM. Encrypted vault is useless on another device.

🚫 No Return Path

Secret values flow one direction. Claude Code output is automatically sanitized.

Real-World Examples

See how developers use LLM Secrets with Claude Code for common workflows.

🔌 API Integration

Call external APIs with secure authentication

# Claude calls OpenAI API:
curl -X POST api.openai.com/v1/chat \
-H "Bearer $env:OPENAI_API_KEY"
✓ 200 OK - Response received
# API key never visible

🗄️ Database Operations

Run migrations and queries securely

# Claude runs database migration:
npx prisma migrate deploy \
--schema=./prisma/schema.prisma
# DATABASE_URL read from encrypted .env
✓ 3 migrations applied
# Connection string stays secret

📦 Package Publishing

Publish to npm with secure tokens

# Claude publishes package:
npm publish --access public \
--_authToken=$env:NPM_TOKEN
✓ Published my-pkg@1.0.0
# NPM token never exposed

☁️ Cloud Deployments

Deploy to AWS, GCP, or Azure securely

# Claude deploys to cloud:
aws s3 sync ./dist s3://my-bucket \
--profile $env:AWS_PROFILE
# AWS credentials from encrypted .env
✓ Upload complete: 24 files
# Credentials never in command history

🌐 Website & Domain Automation

Deploy to Vercel and configure DNS with GoDaddy API

# Claude deploys to Vercel:
vercel --token $env:VERCEL_TOKEN --prod
✓ Deployed to production
# Configure DNS via GoDaddy API:
curl api.godaddy.com/domains/... \
-H "sso-key $env:GODADDY_KEY"
✓ DNS configured!

⛓️ Blockchain & Web3 Deployments

Deploy smart contracts without exposing private keys

# Claude deploys with Foundry:
forge script script/Deploy.s.sol \
--rpc-url $env:ALCHEMY_RPC_URL \
--private-key $env:PRIVATE_KEY --broadcast
✓ Contract deployed: 0x7f3a...
# Private key never visible to AI
# (43% of crypto theft = key exposure)

Teach Claude How to Use Your Secrets

LLM Secrets generates a CLAUDE.md reference file that tells Claude Code exactly which secrets exist and how to use them—without revealing values.

  • 🎯

    Accurate Tool Calls

    Claude knows the exact variable names. No guessing, no hallucinated API keys.

  • 📖

    Context-Aware Commands

    Descriptions tell Claude when to use each secret. Database URL for migrations, API key for external calls.

  • Fewer Errors, Faster Workflows

    No more "secret not found" errors. Claude writes correct commands the first time.

  • 🔄

    Auto-Updated Documentation

    Add a secret, regenerate CLAUDE.md. Your AI always has the latest reference.

CLAUDE.md (auto-generated)
Available Secret
OPENAI_API_KEY — OpenAI API access
Usage: $env:OPENAI_API_KEY
Available Secret
DATABASE_URL — PostgreSQL connection string
Usage: $env:DATABASE_URL
Available Secret
AWS_ACCESS_KEY_ID — AWS credentials
Usage: $env:AWS_ACCESS_KEY_ID
// Claude sees names + descriptions
// Claude never sees values

Transparent & Auditable

The core encryption logic is open source. Review the code, verify the security, contribute improvements.

📄 CryptoService.ts
TypeScript
// AES-256-CBC encryption with Windows Hello
export class CryptoService {
  async encrypt(content: string): Promise<string> {
    // Get master key via Windows Hello
    const masterKey = await getMasterKey();

    // Generate random IV for each encryption
    const iv = randomBytes(16);

    // AES-256-CBC encryption
    const cipher = createCipheriv(
      'aes-256-cbc',
      masterKey,
      iv
    );

    // Encrypt and return base64
    return iv + cipher.update(content);
  }
}

What This Means For You

🔍
Fully Auditable

Every line of encryption code is visible. Security researchers can verify there are no backdoors.

🛡️
Industry Standard

AES-256-CBC is the same encryption used by governments and banks. Battle-tested and proven.

🤝
Community Driven

Found a vulnerability? Submit a PR. Improvements benefit everyone using LLM Secrets.

🔓
No Vendor Lock-in

Your encrypted files use standard formats. You own your data and can decrypt without us.

📜 Licensed under AGPL-3.0 — Free as in Freedom

Up and Running in 60 Seconds

1

Download

Get the CLI (free) or Desktop App. Run the installer and launch the setup wizard.

2

Create Vault

Authenticate with Windows Hello. Your encrypted vault is created automatically.

3

Add Secrets

Import your .env file or add secrets manually. They're encrypted immediately.

4

Work Securely

Claude Code can now use your secrets without ever seeing the actual values.

Manage Secrets Visually

The desktop app gives you a clean interface to manage, organize, and protect your secrets without touching the command line.

LLM Secrets v3.0.0
🔐 Secrets
☁️ Backup
📝 Claude MD
⚙️ Settings

Secret Manager

ENCRYPTED
OPENAI_API_KEY ••••••••••••
DATABASE_URL ••••••••••••
AWS_SECRET_KEY ••••••••••••
GITHUB_TOKEN ••••••••••••
  • One-Click Setup

    Setup wizard walks you through vault creation. Windows Hello authentication in seconds.

  • 🎨

    Visual Secret Editor

    Add, edit, and organize secrets with a clean interface. Syntax highlighting for .env format.

  • ☁️

    Cloud Backup Built-In

    Encrypted backup to Google Drive with one click. Restore on any Windows device.

  • ⏱️

    Auto-Lock Protection

    Configurable idle timeout. Step away and your secrets lock automatically.

Buy Desktop App — $10
Windows 10/11 + WSL Support

Get More From Your Tools.
Less Exposure of Your Secrets.

The CLI is free, open source, and gives you everything you need to work securely with Claude Code. Start encrypting your secrets today.

  • AES-256 encryption with Windows Hello
  • Automatic CLAUDE.md generation
  • WSL and PowerShell support
  • Zero secrets exposed to AI
  • Open source — audit the code yourself
Download Free CLI
PowerShell
PS> scrt init
Creating encrypted vault...
[Windows Hello] Verify your identity
✓ Vault created successfully
PS> scrt add API_KEY
Enter value: ********
✓ Secret encrypted and stored
PS> scrt generate-claude-md
✓ CLAUDE.md updated with 4 secrets
Ready for Claude Code! 🚀

Choose Your Plan

Start free with the CLI. Upgrade for the desktop experience and advanced features.

Open Source

CLI

$0 forever

Core encryption for the developer community. Full functionality, no limits.

View on GitHub
  • AES-256-CBC encryption
  • Windows Hello authentication
  • Basic CLAUDE.md generation
  • WSL secret injection
  • PowerShell commands
  • Open source (AGPL-3.0)
Best Value
Lifetime Access

Pro

$100 lifetime

Maximum security + all future updates. Early adopter pricing.

Get Pro — $100
  • Everything in Starter Desktop app + all features
  • Lifetime updates included
  • Priority support
  • Early access to new features
  • Multi-vault support Coming Soon
  • OneDrive & Dropbox backup Coming Soon
  • Team sharing Coming Soon
💡 Price increases as features launch. Lock in lifetime access now.

Your Secrets Stay Yours

LLM Secrets uses a zero-knowledge architecture. Secrets are decrypted in memory only when needed, injected directly into subprocess environments, and automatically redacted from output.

Even if someone steals your encrypted vault file, it's completely useless without your Windows Hello authentication. The master key is protected by hardware-backed security on your device.

🔒

Encrypted at Rest

AES-256-CBC with random IVs. No plaintext files ever written to disk.

🔐

Hardware-Backed Keys

Windows Hello + DPAPI protection. Keys bound to your device.

👁️

AI Never Sees Values

Secrets injected into subprocesses. Never returned to Claude.

⏱️

Auto-Lock on Idle

Configurable inactivity timeout. Secrets re-encrypted automatically.

Frequently Asked Questions

Everything you need to know about protecting your secrets from AI coding assistants.

Does Claude Code read my .env file?

Yes. Research shows Claude Code automatically loads .env files without asking permission. Your API keys, database passwords, and tokens are silently loaded into memory. LLM Secrets encrypts these files so Claude can use secrets without ever seeing the actual values.

How do I protect API keys from AI assistants?

Traditional approaches like separate user accounts or deny rules are complex and error-prone. LLM Secrets provides env file encryption for Windows using Windows Hello—your secrets are encrypted at rest and only decrypted in isolated subprocesses at runtime.

Is Windows Hello encryption secure?

Yes. LLM Secrets uses AES-256-CBC encryption with a master key protected by Windows Hello and DPAPI. Your encryption keys are hardware-backed by your device's TPM chip. Even if someone steals your encrypted vault file, it's useless without biometric authentication on your specific device.

Can I use this with Cursor, Copilot, or other AI tools?

Absolutely. While LLM Secrets is optimized for Claude Code with automatic CLAUDE.md generation, the encryption works with any AI coding assistant. Your .env file stays encrypted—no AI tool can read the plaintext values. The CLI injects secrets at runtime for any command.

What platforms does LLM Secrets support?

LLM Secrets currently supports Windows 10/11 with Windows Hello enabled. This includes full WSL (Windows Subsystem for Linux) support for developers working in Linux environments. macOS and Linux native support are on the roadmap.

Windows 10/11 + WSL

How does AI coding assistant secrets exposure happen?

AI assistants read files in your project directory, including .env files. These values can appear in prompts, error messages, logs, and even be transmitted to cloud servers. LLM Secrets prevents this exposure by ensuring the AI only sees encrypted content or variable names—never actual secret values.

Is it safe to put my crypto private key in a .env file?

Plain text .env files are risky—43.8% of crypto theft in 2024 came from private key compromise. LLM Secrets encrypts your .env with AES-256 + Windows Hello. Keys are decrypted only at runtime in isolated subprocesses. Safer than Foundry keystores or Hardhat keystore plugins—encryption is automatic and biometric-protected.

Can Claude Code deploy smart contracts with Foundry/Hardhat?

Yes. Claude can run forge script or hardhat deploy commands using your encrypted private key via $env:PRIVATE_KEY. Your key is injected at runtime but never visible to the AI. Deploy to mainnet, testnets, or L2s—your wallet stays secure while Claude handles the deployment workflow.

Ready to Secure Your Secrets?

Join developers who trust LLM Secrets to keep their API keys and credentials safe while working with AI coding assistants.