awesome-repositories.com
博客
MCP
awesome-repositories.com

通过 AI 驱动的搜索,发现最优秀的开源仓库。

探索精选搜索开源替代品自托管软件博客网站地图
项目MCP 服务器关于排名机制媒体报道
法律隐私政策服务条款
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
Skyvern-AI avatar

Skyvern-AI/skyvern

0
View on GitHub↗
21,918 星标·2,040 分支·Python·AGPL-3.0·14 次浏览www.skyvern.com↗

Skyvern

Skyvern is an autonomous web navigation agent and browser-based workflow orchestrator that uses large language models to execute multi-step tasks on websites. By translating natural language instructions into actionable browser commands, the framework enables the automation of complex user workflows, including data extraction and interface interaction, without manual intervention.

The platform distinguishes itself through a focus on secure, self-hosted infrastructure and stealth-oriented execution. It utilizes containerized browser isolation to maintain consistent environments and employs proxy routing and fingerprinting configurations to mimic human traffic patterns. To ensure efficiency and continuity, the system supports stateful session persistence and deterministic action caching, which reduces redundant model inference and minimizes operational costs.

The project provides a comprehensive suite of tools for managing the full lifecycle of web automation. This includes secure credential management for handling authentication, structured data parsing for web content, and robust monitoring capabilities that archive logs, recordings, and screenshots for auditing. The system is designed for integration into broader business process pipelines, allowing for programmable task execution via external platforms.

Features

  • LLM-Powered - Uses large language models to interpret natural language instructions and orchestrate multi-step browser automation workflows.
  • Autonomous Web Agents - Performs multi-step web tasks and data gathering by interpreting natural language goals autonomously.
  • Browser-Based Workflow Automations - Automates complex multi-step tasks on websites using natural language instructions to navigate interfaces and complete workflows.
  • Self-Hosted Infrastructure - Provides a containerized, self-hosted infrastructure for deploying browser-based automation agents within private environments.
  • Browser Automation Orchestrators - Coordinates headless browser engines to automate web interaction and content extraction using language models.
  • Private Infrastructure Management - Deploys and administers secure, scalable production environments within private infrastructure to maintain full operational control.
  • Anti-Bot Evasion - Implements stealth browser configurations and proxy routing to bypass bot detection and security challenges.
  • Workflow Orchestrators - Defines and manages multi-step processes that track state and support resumption after failure.
  • Execution Logging and Diagnostics - Tracks execution status, logs, and visual recordings to facilitate auditing and debugging of automated browser workflows.
  • Browser Automation Interfaces - Enables programmatic control and interaction with browser environments for complex, multi-step automation tasks.
  • AI Agents and Automation - AI browser automation using LLMs & computer vision. Playwright-compatible SDK no-code workflows.
  • Search and Web - Browser automation for LLM-driven workflows.
  • Structured Data Extraction - Extracts specific data points into structured formats from complex web documents.
  • Session and Credential Management - Manages sensitive credentials and securely injects them into browser sessions for automated access to protected services.
  • Stateful Session Persistence - Maintains browser context and authentication state across multi-step interactions to ensure continuity in long-running tasks.
  • Stealth Navigation - Employs techniques for mimicking human behavior and proxy routing to prevent detection by anti-scraping systems.
  • Browser Isolation Strategies - Generates independent, ephemeral browser sessions that ensure isolated storage, cookies, and data states.
  • Browser Session Managers - Persists cookies and local storage data to maintain authentication states across recurring browser-based tasks.
  • Language Model Integrations - Provides connectors and configuration utilities for integrating external language models into browser automation workflows.
  • Cost-Optimization Strategies - Minimizes operational costs by caching deterministic action sequences and limiting task steps to reduce model inference.
  • Automation Task Runners - Executes and manages the lifecycle of automated browser tasks, including credential and session handling.
  • Traffic Routing Proxies - Routes traffic through specific proxies to bypass regional restrictions and ensure consistent access to target websites.
  • Workflow Automation Integrations - Synchronizes data and triggers actions across disparate software platforms to automate cross-functional business processes.
  • Element Locators - Identifies and selects specific elements within a document structure for automated interaction.
  • Browser Environment Configurations - Configures browser execution modes and settings to simulate human behavior and bypass security mechanisms.
  • Artifact Logging - Associates local files like logs, recordings, and screenshots with specific execution runs as tracked artifacts.
  • Authentication Flows - Handles complex login flows and multi-factor authentication requirements during automated web interactions.
  • Navigation Sequence Caching - Stores successful navigation sequences to reduce redundant model inference calls and minimize operational costs.

Star 历史

skyvern-ai/skyvern 的 Star 历史图表skyvern-ai/skyvern 的 Star 历史图表

AI 搜索

探索更多 awesome 仓库

用简单的语言描述您的需求 —— AI 将根据相关性为您从数千个精选开源项目中进行排序。

Start searching with AI

常见问题解答

skyvern-ai/skyvern 是做什么的?

Skyvern is an autonomous web navigation agent and browser-based workflow orchestrator that uses large language models to execute multi-step tasks on websites. By translating natural language instructions into actionable browser commands, the framework enables the automation of complex user workflows, including data extraction and interface interaction, without manual intervention.

skyvern-ai/skyvern 的主要功能有哪些?

skyvern-ai/skyvern 的主要功能包括:LLM-Powered, Autonomous Web Agents, Browser-Based Workflow Automations, Self-Hosted Infrastructure, Browser Automation Orchestrators, Private Infrastructure Management, Anti-Bot Evasion, Workflow Orchestrators。

skyvern-ai/skyvern 有哪些开源替代品?

skyvern-ai/skyvern 的开源替代品包括: apify/crawlee — Crawlee is a web scraping framework designed for building scalable, reliable, and distributed data extraction… vercel-labs/agent-browser — This project is an agentic framework designed to enable autonomous web navigation and browser automation. It functions… browserbase/mcp-server-browserbase — This project is an MCP browser automation server that connects large language models to headless cloud browsers. It… browser-use/browser-use — Browser-use is a framework for building autonomous agents that navigate, interact with, and extract data from web… steel-dev/steel-browser — Steel is a cloud browser automation platform that provides a REST API for launching and controlling remote Chrome… getmaxun/maxun — Maxun is an open-source web scraping and automation platform designed to transform dynamic website content into…

Skyvern 的开源替代方案

相似的开源项目,按与 Skyvern 的功能重合度排序。
  • apify/crawleeapify 的头像

    apify/crawlee

    24,002在 GitHub 上查看↗

    Crawlee is a web scraping framework designed for building scalable, reliable, and distributed data extraction pipelines. It provides a unified interface for managing headless browser automation and lightweight HTTP requests, allowing developers to handle complex web navigation, dynamic content rendering, and large-scale data collection within a single, modular architecture. The project distinguishes itself through its resource-aware concurrency controller, which dynamically scales task execution based on real-time CPU and memory usage to prevent host machine exhaustion. It also features a rob

    TypeScriptapifyautomationcrawler
    在 GitHub 上查看↗24,002
  • vercel-labs/agent-browservercel-labs 的头像

    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
  • browserbase/mcp-server-browserbasebrowserbase 的头像

    browserbase/mcp-server-browserbase

    3,139在 GitHub 上查看↗

    This project is an MCP browser automation server that connects large language models to headless cloud browsers. It functions as an autonomous web workflow engine and an LLM web agent interface, enabling the translation of natural language instructions into browser actions and structured data retrieval. The system distinguishes itself through a managed headless browser cloud API that supports concurrent Chromium sessions with integrated stealth modes, CAPTCHA solving, and proxy traffic routing. It utilizes self-healing element selection to maintain automation resilience when page structures c

    TypeScriptaibrowserchrome
    在 GitHub 上查看↗3,139
  • browser-use/browser-usebrowser-use 的头像

    browser-use/browser-use

    100,229在 GitHub 上查看↗

    Browser-use is a framework for building autonomous agents that navigate, interact with, and extract data from web interfaces using natural language instructions. By acting as an orchestration layer between large language models and browser automation protocols, it enables the execution of complex, multi-step workflows without relying on brittle selectors. The system functions as a headless browser controller, providing a programmatic interface to manage browser instances and execute granular interactions. The project distinguishes itself through its ability to translate high-level intent into

    Pythonai-agentsai-toolsbrowser-automation
    在 GitHub 上查看↗100,229
查看 Skyvern 的所有 30 个替代方案→