BrowserOS

BrowserOS is an AI agent browser orchestrator and automation framework designed to manage browser state and execute complex web workflows. It functions as a local AI browser assistant and a Model Context Protocol controller, enabling the control of browser tabs, windows, and navigation through programmable AI agents and standardized context protocols.

The system distinguishes itself through a graph-based visual workflow builder for creating repeatable automation sequences and the use of markdown-based files to define agent personalities and task recipes. It supports multi-provider orchestration, allowing users to run multiple language models side-by-side for response comparison or utilize local model execution to ensure data privacy.

The platform covers a broad range of capabilities, including agentic web testing, contextual page analysis, and the programmatic interaction with page elements. It integrates with external software ecosystems via OAuth and standardized protocols, while providing a sandboxed local file system for persistent AI memory and document generation.

The browser includes standard utility features such as vertical tab management, advertisement and tracker blocking, and the synchronization of configuration settings.

Features

Agentic Browser Controllers - Acts as an orchestrator that enables AI agents to control browser tabs, windows, and navigation.
AI Agent Orchestrators - Functions as an AI agent orchestrator that manages browser state and executes complex web workflows.
Graph-Based Workflow Orchestrators - Features a graph-based engine to execute repeatable automation sequences defined as visual nodes and edges.
Agent Skill Definitions - Uses markdown files to define agent personalities, behavioral instructions, and reusable task recipes.
AI Chat Interfaces - Provides a conversational side panel that uses active page content and screenshots as context for AI interaction.
AI Workflow Automation - Provides an intelligent orchestrator for automating repetitive web tasks using natural language and visual workflows.
Browser Automation Builders - Features a canvas-based visual graph builder for designing and executing repeatable browser automation workflows.
LLM Orchestrators - Orchestrates requests across diverse cloud APIs and local runners to enable multi-model response comparison.
LLM Provider Integrations - Supports connecting to various cloud-based LLM providers and local model runners via configurable adapters.
Local Model Execution - Supports local execution of AI models to ensure that sensitive browsing data remains private.
Memory Persistence - Stores user facts and preferences in local files to maintain persistent context across AI conversations.
Model Context Protocol Implementations - Implements the Model Context Protocol to expose browser state and navigation to external AI agents and CLI tools.
Web Content AI Analysis - Analyzes web pages to summarize articles, translate text, and extract data using natural language queries.
Browser Assistants - Provides a privacy-focused local AI assistant integrated directly into the browser for page analysis.
Content Extraction - Extracts accessibility trees, structural snapshots, and raw DOM data from web pages for AI analysis.
Remote Browser Controllers - Exposes browser navigation and state controls via a programmatic API for agentic automation.
Local-First Privacy Tools - Ensures browsing data privacy by processing LLM tasks and maintaining memory on the local device.
Standardized Protocol-Based Integrations - Uses a standardized communication layer to interface with external agents and tools for capability exchange.
Web Automation Sequences - Defines reliable sequences of web actions with loops and conditionals to execute tasks across multiple pages.
Element Interaction - Provides high-level APIs for simulating user inputs like clicking, typing, and scrolling on web elements.
Browser Automation Frameworks - Provides a framework for programmatically controlling web browsers using natural language and LLMs.
Browser Control Protocols - Implements the Model Context Protocol to expose browser navigation and DOM interaction to external AI clients.
Browser Navigation - Programmatically controls navigation to URLs, tab creation, and window movement within the browsing session.
Browser Automation - Provides a framework for programmatic control of browser instances to automate tasks like form filling and navigation.
Recurring Agent Scheduling - Enables triggering autonomous agent tasks based on time-based intervals or recurring schedules.
Persona Configurations - Allows defining agent personalities, behavioral constraints, and tone using markdown configuration files.
Model Comparison Interfaces - Displays outputs from multiple language models side-by-side for quality and accuracy comparison on any web page.
LLM Comparison Interfaces - Enables simultaneous interaction with multiple language models to compare response quality side-by-side.
Window Management - Manages browser window lifecycles, including creating and activating hidden window instances.
Document Generation - Generates structured data files and web-ready content in HTML, markdown, and CSV formats.
Sandboxed File Systems - Manages persistent AI memory and document storage within a restricted sandboxed directory for data privacy.
Local File Operations - Performs basic CRUD operations on a sandboxed local file system to manage research data.
Accessibility Tree Exporting - Extracts structured semantic representations of the DOM to provide machine-readable UI views for LLMs.
Local File Accessors - Integrates browser-based data extraction with local file access to save reports and assets.
Web Page Screenshot and PDF Tools - Provides tools to generate screenshots and PDF exports of rendered web pages.
Model Context Protocol Integrations - Integrates with third-party services like calendars and email using the standardized Model Context Protocol.
End-to-End Testing - Performs agentic end-to-end testing by simulating user workflows and capturing console errors.
Agent Testing Suites - Includes agent-specific testing suites to validate the performance and correctness of agentic web workflows.
Third-Party API Integrations - Links with external software ecosystems, including email and project management tools, via API integrations.

Star 历史

browseros-aiBrowserOS

Name: browseros-ai/browseros
Author: browseros-ai

View on GitHub

9,401 星标901 分支C++agpl-3.08 次浏览BrowserOS.com

BrowserOS

The browser includes standard utility features such as vertical tab management, advertisement and tracker blocking, and the synchronization of configuration settings.

Features

Agentic Browser Controllers - Acts as an orchestrator that enables AI agents to control browser tabs, windows, and navigation.
AI Agent Orchestrators - Functions as an AI agent orchestrator that manages browser state and executes complex web workflows.
Graph-Based Workflow Orchestrators - Features a graph-based engine to execute repeatable automation sequences defined as visual nodes and edges.
Agent Skill Definitions - Uses markdown files to define agent personalities, behavioral instructions, and reusable task recipes.
AI Chat Interfaces - Provides a conversational side panel that uses active page content and screenshots as context for AI interaction.
AI Workflow Automation - Provides an intelligent orchestrator for automating repetitive web tasks using natural language and visual workflows.
Browser Automation Builders - Features a canvas-based visual graph builder for designing and executing repeatable browser automation workflows.
LLM Orchestrators - Orchestrates requests across diverse cloud APIs and local runners to enable multi-model response comparison.
LLM Provider Integrations - Supports connecting to various cloud-based LLM providers and local model runners via configurable adapters.
Local Model Execution - Supports local execution of AI models to ensure that sensitive browsing data remains private.
Memory Persistence - Stores user facts and preferences in local files to maintain persistent context across AI conversations.
Model Context Protocol Implementations - Implements the Model Context Protocol to expose browser state and navigation to external AI agents and CLI tools.
Web Content AI Analysis - Analyzes web pages to summarize articles, translate text, and extract data using natural language queries.
Browser Assistants - Provides a privacy-focused local AI assistant integrated directly into the browser for page analysis.
Content Extraction - Extracts accessibility trees, structural snapshots, and raw DOM data from web pages for AI analysis.
Remote Browser Controllers - Exposes browser navigation and state controls via a programmatic API for agentic automation.
Local-First Privacy Tools - Ensures browsing data privacy by processing LLM tasks and maintaining memory on the local device.
Standardized Protocol-Based Integrations - Uses a standardized communication layer to interface with external agents and tools for capability exchange.
Web Automation Sequences - Defines reliable sequences of web actions with loops and conditionals to execute tasks across multiple pages.
Element Interaction - Provides high-level APIs for simulating user inputs like clicking, typing, and scrolling on web elements.
Browser Automation Frameworks - Provides a framework for programmatically controlling web browsers using natural language and LLMs.
Browser Control Protocols - Implements the Model Context Protocol to expose browser navigation and DOM interaction to external AI clients.
Browser Navigation - Programmatically controls navigation to URLs, tab creation, and window movement within the browsing session.
Browser Automation - Provides a framework for programmatic control of browser instances to automate tasks like form filling and navigation.
Recurring Agent Scheduling - Enables triggering autonomous agent tasks based on time-based intervals or recurring schedules.
Persona Configurations - Allows defining agent personalities, behavioral constraints, and tone using markdown configuration files.
Model Comparison Interfaces - Displays outputs from multiple language models side-by-side for quality and accuracy comparison on any web page.
LLM Comparison Interfaces - Enables simultaneous interaction with multiple language models to compare response quality side-by-side.
Window Management - Manages browser window lifecycles, including creating and activating hidden window instances.
Document Generation - Generates structured data files and web-ready content in HTML, markdown, and CSV formats.
Sandboxed File Systems - Manages persistent AI memory and document storage within a restricted sandboxed directory for data privacy.
Local File Operations - Performs basic CRUD operations on a sandboxed local file system to manage research data.
Accessibility Tree Exporting - Extracts structured semantic representations of the DOM to provide machine-readable UI views for LLMs.
Local File Accessors - Integrates browser-based data extraction with local file access to save reports and assets.
Web Page Screenshot and PDF Tools - Provides tools to generate screenshots and PDF exports of rendered web pages.
Model Context Protocol Integrations - Integrates with third-party services like calendars and email using the standardized Model Context Protocol.
End-to-End Testing - Performs agentic end-to-end testing by simulating user workflows and capturing console errors.
Agent Testing Suites - Includes agent-specific testing suites to validate the performance and correctness of agentic web workflows.
Third-Party API Integrations - Links with external software ecosystems, including email and project management tools, via API integrations.

BrowserOS 的开源替代方案

相似的开源项目，按与 BrowserOS 的功能重合度排序。

vercel-labs/agent-browser
vercel-labs/agent-browser
36,203在 GitHub 上查看
This project is an agentic framework designed to enable autonomous web navigation and browser automation. It functions as a controller that translates natural language instructions into deterministic browser actions, allowing agents to interact with websites, perform data extraction, and manage complex authentication flows. By leveraging accessibility trees and semantic element resolution, the framework mimics human-like navigation, moving beyond brittle DOM selectors to interact reliably with modern web interfaces. The framework distinguishes itself through its focus on secure, scalable exec
Rust
在 GitHub 上查看36,203
microsoft/playwright-python
microsoft/playwright-python
14,279在 GitHub 上查看
Playwright for Python is a browser automation framework designed for end-to-end testing, web scraping, and user interaction simulation. It functions as a headless browser controller that enables programmatic navigation, data extraction, and the execution of complex workflows across multiple rendering engines. The framework distinguishes itself through an actionability-aware interaction engine that automatically verifies element readiness before performing actions, significantly reducing test flakiness. It utilizes isolated browser contexts to maintain separate storage and cookies for parallel
Pythonchromiumfirefoxplaywright
在 GitHub 上查看14,279
webdriverio/webdriverio
webdriverio/webdriverio
9,795在 GitHub 上查看
WebDriverIO is a Node.js test automation framework used for automating functional tests across web browsers and mobile applications. It acts as a WebDriver protocol client that manages remote browser sessions and executes commands against WebDriver and Appium servers to perform end-to-end testing. The framework is distinguished by its ability to control both native and hybrid mobile applications and its support for running automated suites across local machines, remote grids, and cloud device providers. It includes specialized capabilities for coordinating multi-browser interactions and estab
TypeScript
在 GitHub 上查看9,795
langchain-ai/deepagents
langchain-ai/deepagents
25,006在 GitHub 上查看
Deepagents is an LLM agent orchestration platform and stateful application server designed for deploying and managing AI agents built with computational graphs. It provides a containerized runtime environment that handles agent execution, state persistence, and the versioning of AI assistants. The platform distinguishes itself through deep integration with the Model Context Protocol, allowing agents to function as servers that expose tools and capabilities to external clients. It features a sophisticated observability suite for capturing execution traces, performing LLM-based evaluations agai
Pythonagentsdeepagentslangchain
在 GitHub 上查看25,006

查看 BrowserOS 的所有 30 个替代方案

常见问题解答

browseros-ai/browseros 是做什么的？

browseros-ai/browseros 的主要功能有哪些？

browseros-ai/browseros 的主要功能包括：Agentic Browser Controllers, AI Agent Orchestrators, Graph-Based Workflow Orchestrators, Agent Skill Definitions, AI Chat Interfaces, AI Workflow Automation, Browser Automation Builders, LLM Orchestrators。

browseros-ai/browseros 有哪些开源替代品？

browseros-ai/browseros 的开源替代品包括： vercel-labs/agent-browser — This project is an agentic framework designed to enable autonomous web navigation and browser automation. It functions… microsoft/playwright-python — Playwright for Python is a browser automation framework designed for end-to-end testing, web scraping, and user… webdriverio/webdriverio — WebDriverIO is a Node.js test automation framework used for automating functional tests across web browsers and mobile… langchain-ai/deepagents — Deepagents is an LLM agent orchestration platform and stateful application server designed for deploying and managing… letta-ai/letta — Letta is a framework for building, deploying, and managing autonomous AI agents that maintain persistent state across… langchain-ai/langchainjs — LangChain.js is a framework for building, executing, and monitoring stateful agentic applications. It provides an…