tarzi 0.0.12

Rust-native lite search for AI applications

tarzi.rs

🐒 Tarzi

Tarzi is a unified search interface designed for Retrieval-Augmented Generation (RAG) and agentic systems built on large language models. Search is a core functionality in these systems, yet most search engine providers (SEPs) impose API paywalls or strict rate limits. Tarzi, empowered by browser automation and web crawling technologies, removes these barriers by supporting token-free queries across multiple search engines. With a single dependency, you can integrate and switch between different SEPs as needed—seamlessly and efficiently.

⚙️ Core Capabilities

• 🦀 Dual Implementation: Native Rust library and Python wrapper with CLI tools
• 🔄 Content Conversion: Convert raw HTML into Markdown, JSON, or YAML, which is ready for LLMs
• 🔍 Search Integration: Fetch fully rendered result pages with a unified interface for both browser (token-free) and API (token-required) modes
• 🧠 Multi-Engine Support: Works with Bing, Google, DuckDuckGo, Brave Search, Tavily, and more
• 🛡️ Proxy Support: Bypass network bans using proxy support to access global SEPs
• 🚀 End-to-End Workflow: Full pipeline from search to content extraction for AI and automation use cases

🧪 Advanced Features (Supports required)

• 🖥️ Custom Browser Controls: Set screen size, viewport, and locale for realistic behavior
• 🕵️‍♂️ Anti-Bot Evasion: Use fingerprint spoofing, proxy rotation, and human-like actions to avoid detection
• 🧠 Smarter Queries: Improve search results with prompt rewriting and intent-aware queries
• 🔗 Workflow Automation: Chain steps like search, click, form fill, and scraping into automated flows
• 🤖 Agent Integration (MCP): Connect with agent frameworks for context-aware, distributed task execution
• 📊 Observability: Monitor success rate, latency, CAPTCHA frequency, and export logs for analysis

Install

pip install tarzi

Usage Examples

• Examples in Python and Rust: examples

Alternatives

• LangChain PlayWrightBrowserToolkit

Contributors

Thank you ❤ all human and non-human contributors.