The SOTA Open-Source Browser Agent for autonomously performing complex tasks on the web
-
Updated
Jun 9, 2025 - Python
#
browser-agent
Here are 37 public repositories matching this topic...
Browser4: a lightning-fast, coroutine-safe browser for your AI.
-
Updated
Dec 8, 2025 - Kotlin
AI Browser Agent is an advanced Browser AI tool developed by Oxylabs AI Studio that automates real user browsing tasks using natural language instructions.
browser-automation ai-agents ai-agent browser-agent browser-automation-studio ai-studio browser-ai ai-browser
-
Updated
Oct 22, 2025
This is the repo for the paper "OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use" (ACL 2025 Oral).
agent gui survey operator web-agent browser-agent llms phone-use mllms computer-use gui-agent os-agent os-agent-survey computing-devices computer-using-agent computer-using
-
Updated
Aug 16, 2025
Open‑source alternative to Perplexity Comet and director.ai and firecrawl combined
scraper google browser ai comet gemini browser-automation ai-agents gemini-api perplexity ai-agent browser-agent scraper-tools llm firecrawl browser-use deep-research deep-research-agent firecrawl-alternative firecrawl-dev
-
Updated
Sep 28, 2025 - Python
Autonomous web browser agent that audits performance, functionality & UX for engineers and vibe-coding creators. 网页自主评估测试 Agent，一键完成性能、功能与交互体验的测试评估
-
Updated
Dec 8, 2025 - Python
✉️ Use the power of browser-use to contact any person or organization... by any means necessary
sales ai scraping operator sales-automation scraping-bot browser-agent contact-info-scraper computer-use browser-use
-
Updated
Jul 30, 2025 - HTML
A smart AI agent that controls your browser with natural language, using Playwright and advanced LLMs to navigate, analyze, and perform tasks.
-
Updated
Nov 22, 2025 - Python
Auto-Browse: AI Enabled Browser Automation
testing automation ai mcp test-automation openai browser-automation playwright browser-agent auto-browser llm langchain ai-testing-tool computer-use browser-use ai-test-generator
-
Updated
Jul 7, 2025 - TypeScript
High-performance web crawler API optimized for LLMs. Turn any search or website into clean Markdown using remote browsers.
markdown ai html-to-markdown web-scraper web-scraping data-extraction browser-automation ai-agents web-search google-serp ai-search serpapi browser-agent llm ai-crawler antibot-bypass ai-scraping
-
Updated
Dec 3, 2025 - TypeScript
The Anal-Queen of AI Browser Automation 🏴☠️ A beautifully fucked-up Skynet-powered browser automation script that harnesses neural brainfuck and machine learning chaos to give zero shits about anything while somehow still working perfectly.
python automation vision anal browser-automation ai-agents multimodal browser-agent auto-browser smart-browser llm ai-browser-control ai-browser app-for-lazy-fucks robot-browser smart-af
-
Updated
Aug 11, 2025 - Python
Build your own AI operators like OpenAI
nodejs javascript typescript browser ai nextjs openai playwright browser-agent anthropic computer-use open-operator
-
Updated
Jan 27, 2025 - TypeScript
User-Agent information harvester
-
Updated
Sep 6, 2021 - Python
Screen recording and computer interaction capture tool that records keyboard/mouse input, screen video, DOM snapshots, and accessibility trees. Perfect for creating datasets to train and evaluate computer-use AI models.
python macos computer-vision accessibility dataset human-computer-interaction screen-recording web-agent browser-agent computer-use computer-use-agent dom-capture
-
Updated
Oct 17, 2025 - Python
Real-time Google Search API for AI Agents & RAG pipelines. Get structured SERP data instantly using remote browsers.
web-scraping data-extraction google-search browser-automation ai-agents rag serp-api playwright serpapi browser-agent llm
-
Updated
Dec 3, 2025 - TypeScript
Trajectory Recording and Capture Environments
-
Updated
Nov 26, 2025 - Python
An AI-powered browser automation tool built with Next.js and Gemini 2.0 Vision AI. Transform natural language into browser automation with visual understanding.
-
Updated
May 23, 2025 - TypeScript
Screen recording and computer interaction capture tool that records keyboard/mouse input, screen video, DOM snapshots, and accessibility trees. Perfect for creating datasets to train and evaluate computer-use AI models.
python windows computer-vision accessibility dataset screen-capture human-computer-interaction screen-recording web-agent browser-agent computer-use computer-use-agent dom-capture
-
Updated
Oct 17, 2025 - Python
Agent-CE is a containerized continuous evaluation (CE) platform for web browsing agents. It provides production-ready Docker images and CI/CD pipelines for running and evaluating multiple agent frameworks including Browser Use, Notte, Anthropic Computer Use, and OpenAI Computer Use.
computer-vision evaluation ci-cd evaluation-metrics cua evaluation-framework continuous-evaluation web-agent browser-agent computer-use browser-use
-
Updated
Oct 29, 2025 - Python
Heybro transforms Chrome into an intelligent AI agent that executes browser tasks through natural language commands. Powered by Google Gemini, this open-source side-panel extension interprets your requests, analyzes page DOM structures, and autonomously performs clicks, form fills, and multi-page navigation— eliminating manual browser interactions
chrome-extension web-scraping workflow-automation chromium-extension web-automation browser-agent gemini-ai agentic-ai ai-browser-automation natural-language-control llm-powered-automation intelligent-browsing
-
Updated
Nov 28, 2025 - JavaScript
Improve this page
Add a description, image, and links to the browser-agent topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the browser-agent topic, visit your repo's landing page and select "manage topics."