9 रिपॉजिटरी
Commanding an AI to operate a web browser and execute tasks while showing the browser view in real time.
Distinct from Headless Browser Controllers: Distinct from Headless Browser Controllers: focuses on AI-driven browser control with a live view, not just headless automation.
Explore 9 awesome GitHub repositories matching web development · AI-Driven Browser Controllers. Refine with filters or upvote what's useful.
This project is a graphical user interface for controlling, configuring, and monitoring AI agents that automate web browser interactions. It provides a visual dashboard to execute autonomous web tasks and manage the behavior of browser-based agents without requiring raw code for every operation. The system includes a browser profile manager to link agents to local executables and user data directories, which allows for persistent authenticated sessions. To support remote observation, it features a VNC streamer that provides a real-time visual feed of headless browser agents operating within a
Provides a graphical dashboard to execute and configure AI-driven browser automation with a real-time view.
Page Assist is a browser-based AI integration tool that provides a sidebar interface for interacting with AI models while browsing the web. It focuses on privacy-focused chatting and web content analysis, allowing users to extract and query information from active webpages to receive context-aware responses. The project distinguishes itself through local AI integration, enabling connections to locally hosted models or private API endpoints to process data without relying on cloud services. It also supports collaborative AI conversations via public sharing links or self-hosted sharing infrastr
Exposes browser tab and element manipulation as tools for an AI model to execute tasks.
jcode is a framework for developing autonomous AI coding agents that automate software development tasks. It functions as an agent orchestrator, tool runtime, and semantic memory engine, enabling the creation of agents that can modify code, run tests, and iterate on their own functionality. The project is distinguished by its use of recursive agent swarming, where a hierarchy of collaborating agents can spawn child agents to decompose complex tasks. It implements a semantic memory system that combines vector-based retrieval with graph-based relationship mapping to maintain context across sess
Implements an AI-driven browser controller to interact with page elements and extract DOM snapshots.
Commands an AI to operate a web browser and execute tasks while showing a live view of the browser.
BrowserMCP is a browser automation bridge that connects AI tools to a live browser session through a local proxy server. It implements a standardized protocol for sending commands like click, type, and navigate to a real browser instance running on the user's machine, while keeping all browsing data on the device. The project distinguishes itself by preserving user sessions and fingerprints across automation tasks. It attaches to the user's existing browser profile to maintain cookies, logins, and authentication state, and uses the real browser's user agent, viewport, and extension context to
Enables AI applications to programmatically navigate pages, fill forms, and extract data through a live browser session.
यह प्रोजेक्ट एक LLM ब्राउज़र ऑटोमेशन फ्रेमवर्क और AI एजेंट ब्राउज़र इंटरफ़ेस है। यह एक नियंत्रण परत के रूप में कार्य करता है जो प्राकृतिक भाषा के निर्देशों को बड़े भाषा मॉडल का उपयोग करके ब्राउज़र इंटरैक्शन में अनुवादित करता है, जिससे AI एजेंटों को मानकीकृत ब्राउज़र-नियंत्रण फ़ंक्शंस के माध्यम से वेब पेजों को नेविगेट करने और उनके साथ इंटरैक्ट करने में सक्षम बनाता है। यह सिस्टम एक RPA वर्कफ़्लो ऑर्केस्ट्रेटर और हेडलेस ब्राउज़र प्रबंधन उपकरण के रूप में कार्य करता है, जो दोहराव वाले कार्यों को स्वचालित करने के लिए नियतात्मक ब्राउज़र अनुक्रमों को रिकॉर्ड और रीप्ले करने में सक्षम है। यह बॉट डिटेक्शन को बायपास करने और CAPTCHAs को हल करने के लिए रेजिडेंशियल प्रॉक्सी और संशोधित ब्राउज़र इंजन सहित स्टील्थ कॉन्फ़िगरेशन के माध्यम से खुद को अलग करता है। यह प्लेटफ़ॉर्म क्षमताओं की एक विस्तृत श्रृंखला को कवर करता है, जिसमें संरचित वेब डेटा निष्कर्षण, प्रमाणीकरण बनाए रखने के लिए पर्सिस्टेंट सेशन प्रबंधन, और मल्टी-फैक्टर ऑथेंटिकेशन जैसे जटिल चरणों के लिए ह्यूमन-इन-द-लूप हस्तक्षेप शामिल है। यह स्थानीय कनेक्टिविटी और प्रबंधित क्लाउड सैंडबॉक्स परिनियोजन दोनों का समर्थन करता है, जो इंटरैक्टिव ग्राफ़ के माध्यम से विज़ुअल वर्कफ़्लो प्रबंधन और रीयल-टाइम गतिविधि निगरानी प्रदान करता है। एकीकरण बाहरी LLM प्रदाताओं और तृतीय-पक्ष ऑर्केस्ट्रेशन प्लेटफ़ॉर्म के लिए कमांड-लाइन इंटरफ़ेस और API कनेक्टिविटी के माध्यम से प्रदान किया जाता है।
Commands an AI agent to operate a web browser and execute natural language tasks with real-time visual feedback.
This project is a multi-agent development framework and orchestrator designed to coordinate autonomous AI agents for software engineering tasks. It functions as an engine that plans, implements, and reviews complex code changes across multiple files and isolated worktrees from a command line interface. The system distinguishes itself through a multi-agent coordination layer that decomposes tasks into sequential phases and applies changes across isolated worktrees to validate solutions. It maintains project-specific knowledge and constraints across sessions via context persistence using dedica
Employs agents to control web browsers for navigating websites and extracting information for development tasks.
Open-claude-cowork is an LLM agent workflow orchestrator and multi-agent collaborative workspace. It serves as a SaaS tool integration framework and a real-time AI chat interface designed to connect large language models with external software applications and browser tools to automate complex business processes. The platform functions as a headless browser automation tool, enabling AI agents to navigate websites and interact with web-based interfaces automatically. It allows for the creation of shared environments where multiple agents coordinate using external tools and shared memory to com
Enables AI agents to operate a web browser and execute tasks via a headless automation engine.
Controls a headless browser to execute multi-step tasks from natural language instructions.