Tag
BrowserBC is an open-source system that converts recorded human browser interactions into reusable agent skills, enabling skills to be used in Claude Desktop and Claude Code with just one recording.
browser-search is an open-source, self-hosted suite of three tools (SearXNG, Camofox, CloakBrowser) that enables AI agents to search and browse the web without API keys or subscriptions, with automatic navigation escalation and deep research capabilities.
The author open-sources their Rust-based browser automation tool with infrastructure and deployment features, originally a business, now free for AI agent development.
agent-browser is a CLI tool for browser automation designed for AI agents, using compact text output and ref-based element selection to minimize token usage. The post also highlights three other tools—portless, emulate, and ai-cli—for improving agent loop efficiency.
Puppeteer is a popular browser automation JavaScript library that supports controlling Chrome and Firefox. It can be used for web scraping, automated testing, and other scenarios. Recently it has integrated the MCP protocol to support AI agents directly controlling the browser.
This article recommends several plugins for Codex, including computer use and browser, for building personal websites and deploying to GitHub and Vercel, emphasizing their convenience.
browser_use announces it has reached the top position on the Browser Arena leaderboard.
This article introduces claude-browser-stack and agent-pods, a tool that automates browser development loops by enabling AI agents to debug APIs, scan for vulnerabilities, record user flows, and provide visual context to Claude, closing the loop between coding and verification.
Lightpanda Agent and PandaScript enable browser automation by using LLMs at build time to generate executable scripts from plain English, eliminating runtime LLM calls and dependency on Playwright or Puppeteer.
A developer open-sourced patchright-cli, a lightweight CLI that uses Patchright to allow AI agents to drive a real Google Chrome browser, designed to avoid detection on websites.
Shared a case library containing 16 Codex hands-on examples, covering PPT generation, MCP, browser automation, knowledge base, and other functions, with screenshots and step-by-step guides.
OpenAI added Chrome DevTools Protocol support to Codex, allowing its AI coding agent to inspect and modify live websites. The feature is opt-in, early-stage, and currently available only outside the EEA, UK, and Switzerland.
browser_use demonstrates their v4 AI agent autonomously playing the online game powerline.io by analyzing the game state and creating a real-time subagent to compete for first place.
BrowserAct is a web browser automation tool designed for AI agents, enabling automated web interactions.
Maka is a local-first desktop AI workbench that achieves long-running execution via DAG workflows, with built-in browser automation and plugin capabilities. It is now open-sourced on GitHub.
The author shares extensive experience using Xiaomi's MiMo v2.5 Pro LLM for agentic browser automation and full-stack development, highlighting its cost efficiency (80%+ cache hit ratio) and ability to handle long-context tasks, while noting it requires structured prompting.
Claude Fable 5 demonstrates relentless proactivity by autonomously debugging a UI bug, using browser automation and Python scripting to create test pages and take screenshots.
Browser Use launched Fetch Use, a Python SDK for scraping websites with a stealth browser that handles proxies, cookies, and sessions automatically.
AI agents often fail due to messy environments rather than bad models; improving environment stability makes simple agents perform well.
This article introduces 5 open-source tools (Agent-reach, Scrapling, Browser-use, Claude in Chrome, Web-access) that enable AI agents like Claude Code to perform web scraping, browser operations, etc., covering scenarios from lightweight to heavy-duty, along with configuration tips.