{#
#}
Let AI see your code.
Not sensitive data.
Mask confidential information locally
before Cursor or Claude Code sends it to OpenAI/Anthropic
Your Code
db = connect('prod-db')
users = db.query('payments',
{api_key: 'sk-live-123'})
fetch('api.internal.com')
Exposed secrets
sheathe
Self-hosted proxy
What code assistant sends
db = connect('[DB_1]')
users = db.query('[TABLE_1]',
{api_key: '[API_KEY_1]'})
fetch('[INTERNAL_URL_1]')
Sheathed
Catch 99.7% of sensitive info
And 100% of what you define with custom regular expressions
0.3%
False negatives
100%
Self-hosted
~90ms
Added latency
Control what data to mask
20+ data types covered by default.
Add new ones or remove unneeded via a JSON config easily
- API keys
- Database passwords
- OAuth tokens
- JWT secrets
- AWS credentials
- Service account keys
- Webhook URLs
- Connection strings
- Email addresses
- Phone numbers
- Credit card numbers
- SSNs
- Personal information (PII)
- User IDs
- Internal URLs
- Company names
- Project codenames
- Employee names
- Server hostnames
- IP addresses
- Docker registry URLs
- Internal endpoints
- Environment variables
- Anything else you configure :]
Host our privacy layer on your premises
Deploy via a Bash one-liner
Configure your sensitive data types
Let it index your codebase, docs and tickets
Done - Sheathe is ready to process requests
Then change the endpoint in your favorite assistant
|
Plan, search, build anything. Ask anything about your code
More integrations are coming soon