Pasteguard

Visit Tool

Pasteguard is an AI Agents & Automation tool that acts as an open-source privacy proxy for LLMs. It automatically hides sensitive data like names, emails, and API keys before prompts are sent to AI, ensuring data privacy.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Yes

Skill level

Technical

About

What is pasteguard?

Pasteguard is an open-source privacy proxy designed for Large Language Models (LLMs), ensuring that sensitive information never leaves your machine. It automatically detects and masks over 30 types of sensitive data, including personal data like names, emails, phone numbers, and financial details, as well as secrets such as API keys and private keys, across 24 languages. This tool works by sitting between your applications and AI providers like OpenAI or Anthropic, replacing sensitive data with placeholders before it reaches the AI. It supports various use cases, from masking data in chat applications like ChatGPT and Claude to protecting codebase context in AI coding assistants like Cursor and Copilot. Pasteguard also offers a dashboard to log and review masking details, providing transparency on what was detected and what reached the provider.

Best used for

Ideal for developers and startup founders who need to ensure data privacy when using LLMs, protect sensitive information in AI coding assistants, and secure API integrations with AI providers. Especially valuable for maintaining compliance and preventing data leaks without compromising AI functionality.

Common actions

protect data privacy

mask sensitive information

secure AI interactions

proxy LLM requests

collaborationworkflowsopen-sourceface swappinggithub copilot"AI Agents"low-code/no-codedeepfakeautomated workflow

Capabilities

Key features

Sensitive data masking
Real-time PII detection
24-language support
Local proxy deployment
Browser extension
Dashboard logging

Target Audience

developerstartup foundersmall business owner

Integrations

openaianthropicollamavllmllama.cppchatgptclaudegemini+ 3 more

Pricing & Plans

Open Source

Free

FAQs

How does Pasteguard ensure my data privacy?

Pasteguard acts as a local proxy, detecting and masking sensitive data like PII and API keys before it leaves your machine and reaches the AI provider. Your original data never gets sent to the LLM, only placeholders, ensuring it remains private.

What types of sensitive data can Pasteguard detect?

Pasteguard can detect over 30 types of sensitive data, including personal information (names, emails, phone numbers, credit cards, IP addresses) and secrets (API keys for OpenAI, Anthropic, Stripe, AWS, GitHub, SSH keys, JWT tokens, passwords, connection strings).

Does Pasteguard support multiple languages for detection?

Yes, Pasteguard supports detection of sensitive data across 24 languages. Specific European languages like German, Spanish, French, Italian, Dutch, Polish, Portuguese, and Romanian are explicitly mentioned for enhanced detection capabilities.

Can Pasteguard be used with self-hosted AI models?

Yes, Pasteguard can be integrated with self-hosted AI setups like Open WebUI and LibreChat. It also offers a 'Route Mode' that can send requests containing sensitive data to local LLMs such as Ollama, vLLM, or llama.cpp.

Trending

Subcategories trending in AI Agents & Automation

AI Frameworks & Infra Chatbots & Conversational AI Workflow Agents Personal Assistants RAG & Document AI Voice Agents

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce