# vercel-labs/agent-browser **Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/vercel-labs-agent-browser).** 36,203 stars · 2,289 forks · Rust · Apache-2.0 ## Links - GitHub: https://github.com/vercel-labs/agent-browser - Homepage: https://agent-browser.dev - awesome-repositories: https://awesome-repositories.com/repository/vercel-labs-agent-browser.md ## Description 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 execution and deep observability. It provides a unified abstraction layer for managing browser instances, whether they are running locally, in containerized environments, or via remote cloud infrastructure. To ensure security and consistency, it utilizes microVM-based isolation and policy-driven gating, which allows developers to enforce human-in-the-loop verification for sensitive operations and maintain strict resource constraints during automated sessions. Beyond core navigation, the project offers a comprehensive suite of tools for managing long-running workflows and debugging agent behavior. It supports persistent session management to maintain authentication states across tasks, alongside advanced observability features like real-time viewport streaming, performance profiling, and network traffic inspection. These capabilities allow for the monitoring of agent activity and the diagnosis of complex interactions within dynamic web applications. The framework is designed for programmatic integration, providing a flexible interface to connect with external AI assistants and automated systems. It includes extensive support for configuring browser environments, injecting custom scripts, and handling complex page states, making it suitable for both exploratory testing and production-grade automation tasks. ## Tags ### Artificial Intelligence & ML - [Autonomous Web Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/autonomous-agents/autonomous-web-agents.md) — Translates natural language instructions into autonomous browser actions for complex web navigation and data extraction. - [Browser Automation Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/browser-automation-agents.md) — Enables agents to execute navigation, form interaction, and data extraction workflows through automated browser control. ([source](https://agent-browser.dev/skills)) - [Assistant Skill Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/artificial-intelligence-tooling/agent-and-tool-integrations/assistant-skill-integrations.md) — Integrates with AI assistants to provide web navigation capabilities by automatically updating skill definitions for external automated systems. ([source](https://agent-browser.dev/installation)) - [Context Truncators](https://awesome-repositories.com/f/artificial-intelligence-ml/context-truncators.md) — Limits the size of data returned from browser interactions to prevent context flooding and optimize token usage for connected agents. ([source](https://agent-browser.dev/security)) - [Recurring Agent Scheduling](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/orchestration-engines/ai-agent/runtime-execution-control/recurring-agent-scheduling.md) — Triggers automated web navigation and interaction workflows on a fixed timetable for periodic monitoring. ([source](https://agent-browser.dev/next)) - [AI Chat Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-chat-interfaces.md) — Provides conversational interfaces that allow direct interaction with application components and data. ([source](https://agent-browser.dev/dashboard)) ### DevOps & Infrastructure - [AI-Driven Browser Controls](https://awesome-repositories.com/f/devops-infrastructure/automation-orchestration/task-execution-frameworks/automation-frameworks/ai-agent-control/ai-driven-browser-controls.md) — Translates natural language instructions into executable browser commands through an AI interface. ([source](https://agent-browser.dev/commands)) - [Cloud Execution Environments](https://awesome-repositories.com/f/devops-infrastructure/cloud-execution-environments.md) — Provides platforms that provide remote, containerized runtimes for executing code directly in a web browser. ([source](https://agent-browser.dev/skills)) - [Browser Automation Orchestrators](https://awesome-repositories.com/f/devops-infrastructure/cloud-infrastructure/cloud-computing-serverless/cloud-orchestration-automation/browser-automation-orchestrators.md) — Orchestrates scalable and secure browser automation routines across cloud-based infrastructure and isolated environments. - [Cloud Browser Provisioners](https://awesome-repositories.com/f/devops-infrastructure/cloud-provisioning/cloud-browser-provisioners.md) — Connects to managed remote browser environments to offload navigation tasks from local infrastructure. ([source](https://agent-browser.dev/providers/agentcore)) - [Browser Streaming](https://awesome-repositories.com/f/devops-infrastructure/containerized-application-management/browser-streaming.md) — Transmits the browser interface over a network connection to enable real-time remote monitoring, human-assisted navigation, and visual recording of agent activity. ([source](https://agent-browser.dev/streaming)) ### Web Development - [Browser Automation Engines](https://awesome-repositories.com/f/web-development/browser-automation-engines.md) — Provides software engines that control headless browsers to simulate user interactions and perform web-based tasks. ([source](https://agent-browser.dev/engines/chrome)) - [AI-Driven Navigation](https://awesome-repositories.com/f/web-development/web-automation-scraping/browser-interaction-primitives/browser-navigation/ai-driven-navigation.md) — Executes browser commands through a text-based interface using accessibility trees for deterministic element selection. ([source](https://agent-browser.dev)) - [Remote Browser Infrastructure Management](https://awesome-repositories.com/f/web-development/browser-integration-utilities/browser-infrastructure/remote-browser-infrastructure-management.md) — Provides tools for deploying, scaling, and managing headless browser instances in cloud environments. ([source](https://agent-browser.dev/providers/kernel)) - [Browser Session Management](https://awesome-repositories.com/f/web-development/browser-integration-utilities/browser-session-management.md) — Maintains persistent authentication, cookies, and browser state across automated sessions to support long-running workflows. ([source](https://agent-browser.dev/init-scripts)) - [Browser Session Managers](https://awesome-repositories.com/f/web-development/browser-session-managers.md) — Initiates and manages browser sessions using local or remote infrastructure through a centralized interface. ([source](https://agent-browser.dev/dashboard)) - [Browser Session Persistence](https://awesome-repositories.com/f/web-development/browser-session-persistence.md) — Saves and restores cookies and local storage data to maintain authentication status between agent runs. ([source](https://agent-browser.dev/providers/agentcore)) - [Browser Configuration Profiles](https://awesome-repositories.com/f/web-development/web-automation-scraping/browser-environment-configurations/browser-configuration-profiles.md) — Provides configurations that define and manage distinct browser environments and settings for executing automated test projects. ([source](https://agent-browser.dev/engines/chrome)) - [Browser Navigation](https://awesome-repositories.com/f/web-development/web-automation-scraping/browser-interaction-primitives/browser-navigation.md) — Interacts with websites using a native engine to perform actions and extract information. ([source](https://agent-browser.dev/native-mode)) - [Remote Browser Connections](https://awesome-repositories.com/f/web-development/web-automation-scraping/browser-orchestration-systems/remote-browser-connections.md) — Offloads web navigation and interaction to cloud-based infrastructure for agent operation in environments lacking local browser support. ([source](https://agent-browser.dev/cdp-mode)) - [Browser Dialog Handlers](https://awesome-repositories.com/f/web-development/web-automation-scraping/browser-dialog-event-handlers/browser-dialog-handlers.md) — Handles browser alerts and prompts automatically or allows manual intervention to prevent interruptions during agent navigation. ([source](https://agent-browser.dev/debugging)) - [Browser Environment Configurations](https://awesome-repositories.com/f/web-development/web-automation-scraping/browser-environment-configurations.md) — Provides settings for managing browser instances including proxy routing, stealth headers, and remote debugging capabilities. ([source](https://agent-browser.dev/installation)) - [Browser Isolation Strategies](https://awesome-repositories.com/f/web-development/web-automation-scraping/browser-environment-configurations/browser-isolation-strategies.md) — Creates independent, ephemeral browser environments to prevent data leakage between agent tasks. ([source](https://agent-browser.dev/sessions)) - [Cloud Browser Integrations](https://awesome-repositories.com/f/web-development/web-automation-scraping/browser-orchestration-systems/cloud-browser-integrations.md) — Connects to managed cloud-based browser providers to execute navigation tasks in remote environments. ([source](https://agent-browser.dev/cdp-mode)) - [Browser Session Recorders](https://awesome-repositories.com/f/web-development/web-automation-scraping/web-scraping-automation/browser-automation/browser-session-recorders.md) — Captures automated web interactions as a video file to provide visual evidence for debugging, testing, or documentation purposes. ([source](https://agent-browser.dev/recording)) - [Visual Browser Monitoring](https://awesome-repositories.com/f/web-development/web-automation-scraping/web-scraping-automation/browser-automation/visual-browser-monitoring.md) — Provides a visual dashboard to inspect active sessions, traffic, and browser status through a proxied interface. ([source](https://agent-browser.dev/commands)) ### Development Tools & Productivity - [Headless Browser Automation](https://awesome-repositories.com/f/development-tools-productivity/headless-browser-automation.md) — Executes web navigation and data extraction commands through a lightweight headless engine to minimize resource usage. ([source](https://agent-browser.dev/engines/lightpanda)) - [Communication Automation](https://awesome-repositories.com/f/development-tools-productivity/communication-automation.md) — Automates browser sessions to interact with messaging interfaces for reading channels and sending messages. ([source](https://agent-browser.dev/skills)) - [Browser Console Debugging](https://awesome-repositories.com/f/development-tools-productivity/debugging-profiling-testing/debugging-diagnostics/debugging-inspection-tools/debugging-and-inspection-tools/browser-console-debugging.md) — Retrieves console messages and uncaught JavaScript exceptions from the active page to diagnose issues during automated browsing sessions. ([source](https://agent-browser.dev/debugging)) - [Input Automation](https://awesome-repositories.com/f/development-tools-productivity/input-pointer-automation/input-automation.md) — Sends synthetic mouse, keyboard, and touch events to the browser to simulate user interaction. ([source](https://agent-browser.dev/streaming)) ### Testing & Quality Assurance - [Browser Automation Frameworks](https://awesome-repositories.com/f/testing-quality-assurance/software-testing/testing-frameworks/test-frameworks/browser-and-ui-testing/browser-automation-frameworks.md) — Provides a framework for executing complex browser-based navigation and interaction workflows. - [Accessibility Tree Generators](https://awesome-repositories.com/f/testing-quality-assurance/accessibility-visual-testing/accessibility-testing/accessibility-tree-generators.md) — Extracts compact accessibility trees with unique references to enable efficient agent navigation. ([source](https://agent-browser.dev/snapshots)) - [Element Interaction](https://awesome-repositories.com/f/testing-quality-assurance/automation-interaction-tools/element-interaction.md) — Locates and manipulates page elements using semantic selectors to perform actions like clicking or typing. ([source](https://agent-browser.dev/commands)) - [Headless Browser Controllers](https://awesome-repositories.com/f/testing-quality-assurance/software-testing/testing-frameworks/test-frameworks/browser-and-ui-testing/browser-automation-frameworks/headless-browser-controllers.md) — Manages local and remote headless browser instances to execute complex navigation workflows programmatically. - [Autonomous Exploratory Agents](https://awesome-repositories.com/f/testing-quality-assurance/software-testing/e2e-integration-testing/end-to-end-testing/agent-testing-suites/autonomous-exploratory-agents.md) — Navigates applications to identify bugs and usability issues, generating structured reports that include visual evidence and reproduction steps. ([source](https://agent-browser.dev/skills)) - [Browser Automation Interfaces](https://awesome-repositories.com/f/testing-quality-assurance/software-testing/testing-frameworks/test-frameworks/browser-and-ui-testing/browser-automation-frameworks/browser-automation-interfaces.md) — Exposes a programmatic interface to manage browser sessions and streaming data for custom automation. ([source](https://agent-browser.dev/streaming)) - [Screenshot Capture](https://awesome-repositories.com/f/testing-quality-assurance/automation-interaction-tools/screenshot-capture.md) — Generates screenshots or PDF documents of the current browser state with configurable formats, quality settings, and output locations. ([source](https://agent-browser.dev/files)) - [Initialization Script Injections](https://awesome-repositories.com/f/testing-quality-assurance/general-testing-utilities/test-configuration/initialization-script-injections.md) — Provides the capability to inject custom scripts into the browser context before page load for environment setup. ([source](https://agent-browser.dev/init-scripts)) ### Security & Cryptography - [Automated Login Frameworks](https://awesome-repositories.com/f/security-cryptography/authentication-services/automated-login-frameworks.md) — Executes login sequences by targeting specific input fields to reliably authenticate on complex applications. ([source](https://agent-browser.dev/commands)) - [Stateful Session Persistence](https://awesome-repositories.com/f/security-cryptography/identity-access-management/session-management/stateful-session-persistence.md) — Maintains authentication, cookies, and storage state across multiple commands to support long-running automated workflows. ([source](https://agent-browser.dev)) - [Execution Confirmation Requirements](https://awesome-repositories.com/f/security-cryptography/governance-policy-frameworks/security-frameworks/policy-management-systems/execution-confirmation-requirements.md) — Mandates human confirmation for sensitive automated actions to ensure security. ([source](https://agent-browser.dev/security)) - [Action Resolution Policies](https://awesome-repositories.com/f/security-cryptography/identity-access-management/access-control/policy-enforcement-engines/action-resolution-policies.md) — Enforces security policies and human-in-the-loop verification for automated actions. ([source](https://agent-browser.dev/security)) - [Credential Security Managers](https://awesome-repositories.com/f/security-cryptography/credential-security-managers.md) — Securely manages and injects authentication credentials into login forms. ([source](https://agent-browser.dev/security)) ### System Administration & Monitoring - [Execution Observability](https://awesome-repositories.com/f/system-administration-monitoring/execution-observability.md) — Captures video, performance metrics, and network activity to provide observability into agent actions and debug interactions with modern web applications. ([source](https://agent-browser.dev)) - [Session Activity Monitors](https://awesome-repositories.com/f/system-administration-monitoring/system-activity-monitoring/session-activity-monitors.md) — Displays a live browser viewport and a chronological feed of commands, results, and console logs to track agent behavior in real time. ([source](https://agent-browser.dev/dashboard)) - [AI Session Monitoring](https://awesome-repositories.com/f/system-administration-monitoring/ai-session-monitoring.md) — Streams a live visual feed of the browser session to a web interface for real-time observation of agent activity. ([source](https://agent-browser.dev/providers/agentcore)) - [Application Performance Profiling](https://awesome-repositories.com/f/system-administration-monitoring/performance-monitoring-tools/application-performance-profiling.md) — Provides capabilities for identifying performance bottlenecks and measuring execution time within an application environment. ([source](https://agent-browser.dev/profiler)) ### User Interface & Experience - [Semantic Navigation Hooks](https://awesome-repositories.com/f/user-interface-experience/component-utilities/navigation-semantic-hooks/semantic-navigation-hooks.md) — Resolves interactive elements using semantic roles and labels for reliable navigation. - [Element Locators](https://awesome-repositories.com/f/user-interface-experience/element-locators.md) — Identifies interactive elements using CSS selectors or semantic descriptions for targeted agent interaction. ([source](https://agent-browser.dev/quick-start)) - [Synthetic Event Bridges](https://awesome-repositories.com/f/user-interface-experience/interaction-event-handlers/synthetic-event-bridges.md) — Synthesizes low-level mouse, keyboard, and touch events to simulate authentic user interactions. ### Operating Systems & Systems Programming - [MicroVM Runtimes](https://awesome-repositories.com/f/operating-systems-systems-programming/virtualization-emulation/microvm-runtimes.md) — Provides execution environments for lightweight, hardware-isolated virtual machines. ([source](https://agent-browser.dev/next)) - [Desktop Application Automation](https://awesome-repositories.com/f/operating-systems-systems-programming/desktop-environment-frameworks/desktop-environment-components/desktop-applications/desktop-application-automation.md) — Connects to desktop applications via debugging ports to automate interactions within software like code editors. ([source](https://agent-browser.dev/skills)) ### Software Engineering & Architecture - [Sandboxed Execution Environments](https://awesome-repositories.com/f/software-engineering-architecture/sandboxed-execution-environments.md) — Provides isolated runtime environments for executing untrusted or custom code securely. ([source](https://agent-browser.dev/engines/chrome)) - [Change Detection](https://awesome-repositories.com/f/software-engineering-architecture/architectural-design-patterns/state-management/change-detection.md) — Compares accessibility trees or visual screenshots between two points in time to identify structural updates or unintended regressions in a web interface. ([source](https://agent-browser.dev/diffing)) ### Data & Databases - [Virtual Machine Snapshots](https://awesome-repositories.com/f/data-databases/data-engineering-infrastructure/data-persistence-storage/data-persistence-management/snapshot-management-strategies/virtual-machine-snapshots.md) — Provides capabilities to capture and restore the state of virtual machine instances to facilitate recovery and environment persistence. ([source](https://agent-browser.dev/next)) - [JSON Message Serializers](https://awesome-repositories.com/f/data-databases/data-serialization-formats/json-serialization/json-message-serializers.md) — Serializes browser interaction results into structured JSON to facilitate integration with external scripts. ([source](https://agent-browser.dev/quick-start)) - [Structured Data Exporters](https://awesome-repositories.com/f/data-databases/data-serialization-formats/structured-data-exporters.md) — Formats accessibility snapshots into structured JSON data for programmatic parsing and analysis. ([source](https://agent-browser.dev/snapshots)) ### Mobile Development - [Mobile Browser Automation](https://awesome-repositories.com/f/mobile-development/mobile-infrastructure-security/mobile-synchronization/automation-frameworks/mobile-browser-automation.md) — Controls mobile web browsers on simulators or physical devices to perform agent-driven navigation and testing. ([source](https://agent-browser.dev/ios)) ### Networking & Communication - [Network Traffic Analyzers](https://awesome-repositories.com/f/networking-communication/network-traffic-analyzers.md) — Logs and filters browser traffic by URL, resource type, or status to analyze request and response details during navigation. ([source](https://agent-browser.dev/network)) - [Traffic Interception Tools](https://awesome-repositories.com/f/networking-communication/traffic-interception-tools.md) — Intercepts and mocks network traffic to control browser behavior during automation. ([source](https://agent-browser.dev/network))