Nanobrowser - An AI-powered web page automation tool that autonomously completes complex web page tasks.

What is Nanobrowser?

Nanobrowser is an open-source Chrome extension focused on AI-driven web page automation. It utilizes a multi-agent system to handle complex web page tasks such as information extraction and automated operations. Users can flexibly choose different models to support various agents using their own LLM API keys. Completely free, Nanobrowser serves as an open-source alternative to OpenAI Operator, runs locally in the browser, prioritizes privacy, and does not involve cloud services. Nanobrowser makes AI more intelligent and efficient within the browser.

Main functions of Nanobrowser

• Multi-agent System):
  • Planner: Responsible for formulating and adjusting task strategies.
  • Navigator: Perform webpage navigation and operations.
  • ValidatorCheck if the task was completed successfully.
• Interactive sidebarIt provides an intuitive chat interface that displays task status in real time, allowing users to interact with the intelligent agent using natural language.
• Task automationAutomating repetitive web page tasks, such as information extraction and data organization, saves time and effort.
• Multiple LLM supportIt supports connection to multiple large language model (LLM) providers, allowing users to select different models for different agents according to their needs.

Nanobrowser's technical principles

• LLM-based agent architectureThe core of Nanobrowser is a multi-agent system, with each agent driven by a large language model (LLM). Agents collaborate and divide tasks to efficiently complete complex tasks. For example, the Planner formulates the task strategy, the Navigator performs webpage operations, and the Validator confirms the task results.
• Dynamic task adjustment and adaptabilityWhen encountering obstacles or task failures, the Planner agent automatically adjusts its strategy and replans the task path to ensure successful task completion.
• Integrating multiple LLM providersIt supports connection to mainstream LLM providers such as OpenAI and Anthropic, allowing users to select different models according to their needs and assign the most suitable model to different agents.

Nanobrowser project address

• GitHub repository:https://github.com/nanobrowser/nanobrowser

Application scenarios of Nanobrowser

• Information gathering and researchQuickly extract information such as news, academic papers, and market data.
• E-commerce and shoppingCompare product prices, generate shopping lists, and monitor promotional information.
• Content creation: Assists in generating copy, blog posts, and social media content.
• Enterprise AutomationData organization, automation of repetitive tasks, and customer service support.
• Personal efficiency improvement: Managing schedules, aiding learning, and organizing personal finances.