webpuppet
Browser automation library for AI chat web interfaces.
This library provides programmatic control of Chrome/Chromium browsers to interact with AI chat providers through their web UIs. It handles authentication, session management, and response extraction for research and development workflows.
⚠️ Important: This automates third-party web interfaces. Users must comply with provider terms of service and applicable laws.
Overview
webpuppet enables automated interactions with AI chat interfaces when API access is unavailable, restricted, or when specific web-only features are needed. The library handles:
- Browser session management and authentication
- Rate limiting and anti-detection measures
- Response extraction and content sanitization
- Multi-provider workflow orchestration
Features
- Multi-Provider Support: Claude, Grok, Gemini, ChatGPT, Perplexity, NotebookLM, Kaggle
- Browser Automation: CDP automation for Chromium-based browsers (Brave, Chrome, Chromium, Edge, Opera, Vivaldi)
- Browser Detection: Cross-platform detection (Linux, macOS, Windows) with Flatpak/Snap support
- Session Persistence: Secure credential and cookie storage using OS keyring with AES-256-GCM encryption
- Rate Limiting: Configurable request throttling with exponential backoff
- Content Security: Response screening for common security threats
- Permission Controls: Domain allowlisting and operation restrictions
Installation
Add to your Cargo.toml:
[]
= { = "0.1.0-alpha.3", = ["all-providers"] }
Note: This is pre-release software. APIs may change between versions.
Feature Flags
| Feature | Description |
|---|---|
chromium (default) |
CDP automation for Chromium-based browsers (Brave, Chrome, Chromium, Edge, Opera, Vivaldi) |
firefox |
Firefox detection support (automation requires geckodriver - planned) |
grok |
Enable Grok (X.ai) provider |
claude |
Enable Claude (Anthropic) provider |
gemini |
Enable Gemini (Google) provider |
chatgpt |
Enable ChatGPT (OpenAI) provider |
perplexity |
Enable Perplexity provider |
notebooklm |
Enable NotebookLM provider |
kaggle |
Enable Kaggle dataset search tool |
all-providers |
Enable all AI providers |
Usage
Basic Prompt
use ;
async
Multi-Provider Query
use ;
async
Conversation Mode
use ;
async
Authentication Flow
On first use with each provider:
- Browser opens to provider's login page
- Complete manual login (supports 2FA)
- Cookies are saved to OS keyring
- Subsequent runs use saved session
// Headless mode only works after initial authentication
let puppet = builder
.with_provider
.headless // Must be false for first login
.build
.await?;
puppet.authenticate.await?;
// Browser window opens, complete login manually
// After success, cookies are persisted
// Future runs can use headless mode
Configuration
use ;
use Duration;
let config = builder
.headless
.timeout
.rate_limit // requests per minute
.no_sandbox // Required for containers
.build;
let puppet = builder
.with_config
.with_all_providers
.build
.await?;
Provider Capabilities
Capabilities are declared per provider in code (not runtime UI detection yet). For programmatic access, use WebPuppet::provider_capabilities().
| Provider | Conversation | File Upload | Notes |
|---|---|---|---|
| Claude | ✅ | ✅ | Anthropic's Claude models |
| Grok | ✅ | ❌ | X.ai's Grok models |
| Gemini | ✅ | ✅ | Google's Gemini models |
| ChatGPT | ✅ | ✅ | OpenAI's GPT models |
| Perplexity | ✅ | ✅ | Perplexity AI search |
| NotebookLM | ✅ | ✅ | Google's NotebookLM |
Security
- Credentials: Stored in OS keyring, never in plaintext files
- Browser profiles: Sandboxed per-provider in local data directory
- Rate limiting: Prevents abuse detection with humanized delays
- Session isolation: Each provider has independent browser context
- Response screening: Automatic filtering of security threats
Limitations
- Pre-release software: APIs may change without notice
- Provider UI Dependencies: Changes to provider web interfaces may break functionality
- Feature Parity: Not all provider-specific features are supported uniformly
- Authentication: Requires manual login for initial setup
- Rate Limits: Subject to provider-imposed usage restrictions
Content Security Screening
The library includes built-in security screening for AI responses:
use ;
async
Detected Security Issues
| Issue Type | Description | Risk Level |
|---|---|---|
InvisibleText |
1pt fonts, zero-opacity text | High |
BackgroundMatchingText |
Same color as background | High |
ZeroWidthCharacters |
U+200B, U+FEFF, etc. | Medium |
HomoglyphAttack |
Unicode lookalikes | Medium |
PromptInjection |
"Ignore previous instructions" | Critical |
EncodedPayload |
Base64/hex encoded content | Medium |
HiddenElement |
CSS display:none, visibility:hidden | High |
CodeInjection |
Script injection attempts | Critical |
Custom Screening Configuration
use ;
let config = ScreeningConfig ;
let puppet = builder
.with_screening_config
.build
.await?;
Architecture
webpuppet/
├── src/
│ ├── lib.rs # Main exports
│ ├── config.rs # Configuration types
│ ├── credentials.rs # Keyring credential storage
│ ├── error.rs # Error types
│ ├── puppet.rs # Main orchestrator
│ ├── ratelimit.rs # Rate limiting
│ ├── security.rs # Content screening & prompt injection filtering
│ ├── session.rs # Browser session management
│ └── providers/
│ ├── mod.rs # Provider exports
│ ├── traits.rs # ProviderTrait definition
│ ├── claude.rs # Claude implementation
│ ├── gemini.rs # Gemini implementation
│ └── grok.rs # Grok implementation
System Requirements
- Rust: 1.75.0 or newer (latest stable recommended)
- Browser: Chrome 120+, Chromium 120+, or Brave 1.60+ (auto-detected)
- Operating Systems:
- Linux: Modern distributions (Ubuntu 22.04+, Fedora 38+, Arch Linux current)
- macOS: 13.0 Ventura or newer (Intel/Apple Silicon)
- Windows: Windows 11 22H2 or newer
- Keyring: OS-native credential storage (keyring, Keychain, Windows Credential Manager)
- Container Support: Available with
--no-sandboxconfiguration
Troubleshooting
Session Expired
// Force re-authentication
puppet.authenticate.await?;
Rate Limited
The library automatically handles rate limits with exponential backoff. If you're consistently hitting limits, increase the delay:
let config = builder
.rate_limit // Lower requests/minute
.build;
Browser Not Found
use PathBuf;
let config = builder
.executable_path
.build;
License
MIT License - See LICENSE for details.
Disclaimer
This tool is for educational and research purposes only. Use of this tool to automate web interfaces may violate the terms of service of the respective providers. Users are responsible for ensuring their use complies with all applicable terms and laws.