> For the complete documentation index, see [llms.txt](https://airas.gitbook.io/airas/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://airas.gitbook.io/airas/products/airas-agent.md). # Airas Agent {% embed url="" %} Airas Agent booking a flight from Toronto to Dubai by autonomously browsing the web {% endembed %} ### Overview Airas Agent is our AI-driven automation tool that interacts with websites, performs complex tasks, and even handles multi-step processes. Built with a focus on real-world assets (RWA), it’s ideal for gathering data on tokenized real estate, monitoring market trends, or automating repetitive tasks in the DeFi and NFT space. ### Key Features * **AI-Enhanced Navigation**\ Interprets page layouts and elements using AI vision, so it can handle even dynamic or complex UIs. * **Multiple AI Providers**\ Switch between OpenAI or Ollama for different performance or cost needs. * **Autonomous Workflow**\ Give it a goal (e.g., “Find the latest tokenized property listings”) and watch it plan and execute the steps. * **Browser-Based Automation**\ Uses Playwright under the hood for stable, reliable multi-tab handling. ### Installation ``` git clone https://github.com/airas-network/airas-agent.git cd airas-agent npm install cp .env.example .env ``` Update your .env file with your preferred AI provider and credentials. ### Configuration ``` AI_PROVIDER=openai OPENAI_API_KEY=YOUR_API_KEY OPENAI_MODEL=gpt-4o-mini # For Ollama OLLAMA_BASE_URL=http://localhost:11434 OLLAMA_MODEL=llama3.1 ``` Use timeouts, logging, and screenshot options to suit your workflow. ### Usage 1. **Start the Agent**\ Run:\ npm run dev\ Then open in your browser. 2. **Set a Goal**\ For example: “Monitor real estate listings and find anything under $500k.” 3. **Observe Automation**\ Watch Airas Agent open new tabs, click through listings, and gather data. ### Use Cases * **Real Estate Scouting**\ Automate scanning of multiple listing sites for undervalued properties. * **DeFi Tasks**\ Farm yields or claim rewards across various protocols. * **NFT Market Analysis**\ Compare prices, traits, or trading volumes on multiple marketplaces. * **Compliance Checks**\ Scrape KYC/AML data across relevant platforms. ### Best Practices * **Set Clear Goals**\ The more specific your instructions, the better the results. * **Use Logging**\ Enable logs to debug or optimize workflows. * **Stay Updated**\ Pull the latest changes from GitHub for new features and improvements. ### Next Steps * Integrate with **Airas Cloud** to handle large-scale data scraping. * Use **Airas Assistant** to interpret findings and generate insights. * Explore advanced custom actions for specialized real-world asset workflows. ### Check out GitHub Check out Airas Agent on GitHub: --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://airas.gitbook.io/airas/products/airas-agent.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.