awesome-repositories.com
Blog
awesome-repositories.com

Entdecke die besten Open-Source-Repositories mit KI-gestützter Suche.

EntdeckenKuratierte SuchenOpen-Source-AlternativenSelf-hosted SoftwareBlogSitemap
ProjektÜber unsRanking-MethodikPresseMCP-Server
RechtlichesDatenschutzAGB
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
browser-use avatar

browser-use/browser-harness

0
View on GitHub↗
15,265 Stars·1,424 Forks·Python·MIT·12 Aufrufebrowser-harness.com↗

Browser Harness

This project is an automation framework that connects large language models to web browsers via the Chrome DevTools Protocol for autonomous task execution. It functions as a bridge between intelligent agents and browser engines, allowing for the direct control of browser sessions and profiles.

The framework features a self-healing agent capable of generating and executing custom scripts during runtime to resolve failures and optimize browser tasks. It supports stealthy deployment through the use of integrated proxies and captcha solvers to bypass bot detection and security mitigations.

The system covers a wide range of capabilities including cloud-based headless browser management, remote session orchestration via authentication keys, and page state inspection through combined visual and DOM analysis. It also provides mechanisms for integrating site-specific logic and pre-defined skills from local workspaces to increase task reliability.

Features

  • Agentic Browser Controllers - Functions as the primary bridge between an intelligent agent and a web browser for autonomous task completion.
  • LLM-Driven Automation - Connects large language models to web browsers for autonomous navigation and complex task execution.
  • Dynamic Helper Generation - Generates and executes custom scripts during runtime to overcome failures and optimize browser automation tasks.
  • Browser Automation Agents - Acts as an intelligent agent capable of interacting with web browsers to complete autonomous tasks.
  • Self-Improving Automation Code - Enables a self-healing agent to write and execute new code to resolve failures and improve future task success.
  • DOM State Inspection - Combines coordinate-based screenshots with DOM analysis to extract real-time page data and interface layouts.
  • Dynamic Automation Helper Generation - Synthesizes new automation functions during runtime to overcome complex browser task requirements.
  • Dynamic Automation Helper Generation - Allows the system to create and execute custom scripts at runtime to resolve failures and optimize browser tasks.
  • Element Interaction - Simulates user actions including coordinate-based clicks, iframe management, and page scrolling.
  • Page State Analysis - Analyzes the current DOM and visual state of a page to inform autonomous agent decision-making.
  • LLM-Driven Frameworks - Provides a framework where large language models determine the interaction sequences for browser automation.
  • Browser Automation - Provides a comprehensive framework for controlling headless browsers to perform autonomous web interactions.
  • LLM Browser Connectivity - Provides the essential connectivity layer that allows language models to execute tasks via direct browser control.
  • Chrome DevTools Protocols - Utilizes the Chrome DevTools Protocol for bidirectional communication and low-level control of the browser engine.
  • DevTools Protocol Clients - Functions as a DevTools Protocol client to manage browser sessions, profiles, and page interactions.
  • Skill Directory Configurations - Loads site-specific logic and pre-defined automation primitives from local directories to increase task reliability.
  • Browser Protocol Controllers - Allows the direct transmission of low-level CDP commands to the browser engine for advanced control.
  • Stealth Headless Instance Management - Deploys invisible browser sessions with integrated proxy support and automated captcha solving to avoid detection.
  • Bot Detection Bypass - Employs techniques to mimic legitimate human behavior and bypass automated bot detection systems.
  • Site-Specific Skill Integration - Increases task reliability by loading site-specific logic and pre-defined skills from local workspaces.
  • Stealth Configurations - Deploys browser sessions with integrated proxies and captcha solvers to bypass bot detection and security mitigations.
  • Remote Browser Infrastructure Management - Orchestrates the deployment and scaling of headless browser instances in cloud environments.
  • Session Orchestration Tools - Manages the lifecycle and isolation of concurrent headless browser sessions on cloud servers.
  • Custom Automation Primitive Extensions - Supports the development of custom scripts in local workspaces to build new browser automation primitives.
  • Cloud Browser Integrations - Bridges local LLM environments to remote cloud-hosted browser sessions using authentication keys.
  • Headless Browser Orchestrators - Orchestrates isolated headless browser instances on cloud servers for background tasks and data extraction.
  • Remote Browser Connections - Implements interfaces to initialize and connect to remote cloud-hosted browser instances using authentication keys.

Star-Verlauf

Star-Verlauf für browser-use/browser-harnessStar-Verlauf für browser-use/browser-harness

KI-Suche

Entdecke weitere awesome Repositories

Beschreibe in einfachen Worten, was du brauchst — die KI bewertet tausende kuratierte Open-Source-Projekte nach Relevanz.

Start searching with AI

Kuratierte Suchen mit Browser Harness

Handverlesene Sammlungen, in denen Browser Harness vorkommt.
  • Frameworks für End-to-End-Webtests
  • Bibliotheken für Headless-Browser-Automatisierung

Häufig gestellte Fragen

Was macht browser-use/browser-harness?

This project is an automation framework that connects large language models to web browsers via the Chrome DevTools Protocol for autonomous task execution. It functions as a bridge between intelligent agents and browser engines, allowing for the direct control of browser sessions and profiles.

Was sind die Hauptfunktionen von browser-use/browser-harness?

Die Hauptfunktionen von browser-use/browser-harness sind: Agentic Browser Controllers, LLM-Driven Automation, Dynamic Helper Generation, Browser Automation Agents, Self-Improving Automation Code, DOM State Inspection, Dynamic Automation Helper Generation, Element Interaction.

Welche Open-Source-Alternativen gibt es zu browser-use/browser-harness?

Open-Source-Alternativen zu browser-use/browser-harness sind unter anderem: vercel-labs/agent-browser — This project is an agentic framework designed to enable autonomous web navigation and browser automation. It functions… lavague-ai/lavague — LaVague is an LLM web agent framework and large action model designed to translate natural language instructions into… browser-use/workflow-use — This project is an LLM browser automation framework and AI agent browser interface. It serves as a control layer that… chromedp/chromedp — chromedp is a browser automation framework and driver that controls web browsers via the Chrome DevTools Protocol. It… autoscrape-labs/pydoll — pydoll is a Chrome DevTools Protocol automation library and headless browser controller used for web data extraction… ultrafunkamsterdam/nodriver — nodriver is an asynchronous Chromium browser automation framework that provides headless control and web scraping…

Open-Source-Alternativen zu Browser Harness

Ähnliche Open-Source-Projekte, sortiert nach der Anzahl der gemeinsamen Funktionen mit Browser Harness.
  • vercel-labs/agent-browserAvatar von vercel-labs

    vercel-labs/agent-browser

    36,203Auf GitHub ansehen↗

    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
    Auf GitHub ansehen↗36,203
  • lavague-ai/lavagueAvatar von lavague-ai

    lavague-ai/LaVague

    6,374Auf GitHub ansehen↗

    LaVague is an LLM web agent framework and large action model designed to translate natural language instructions into executable browser automation scripts. It functions as a multi-modal orchestrator that reasons over web page states and HTML content to automate multi-step tasks via a Selenium-based automation engine. The framework features a modular model provider layer, allowing users to swap between different language and vision models from providers such as Anthropic, Gemini, and Azure OpenAI. It employs a multi-modal world model to process screenshots and HTML structures, utilizing retri

    Pythonaibrowserlarge-action-model
    Auf GitHub ansehen↗6,374
  • browser-use/workflow-useAvatar von browser-use

    browser-use/workflow-use

    4,054Auf GitHub ansehen↗

    This project is an LLM browser automation framework and AI agent browser interface. It serves as a control layer that translates natural language instructions into browser interactions using large language models, enabling AI agents to navigate and interact with web pages through standardized browser-control functions. The system functions as an RPA workflow orchestrator and headless browser management tool, capable of recording and replaying deterministic browser sequences to automate repetitive tasks. It distinguishes itself through stealth configurations, including residential proxies and

    Pythonbrowser-automationbrowser-use-boxrpa
    Auf GitHub ansehen↗4,054
  • chromedp/chromedpAvatar von chromedp

    chromedp/chromedp

    13,137Auf GitHub ansehen↗

    chromedp is a browser automation framework and driver that controls web browsers via the Chrome DevTools Protocol. It functions as a headless browser automation tool and web browser controller, enabling the programmatic management of browser sessions, targets, and network responses through a remote debugging interface. The project provides specialized capabilities for Chrome DevTools Protocol automation, including headless browser testing, web scraping and data extraction, and mobile device emulation. It also supports browser-based visual regression by capturing precise screenshots of web pag

    Go
    Auf GitHub ansehen↗13,137
  • Alle 30 Alternativen zu Browser Harness anzeigen→