browse CLI

browse.sh is a browser-automation platform for AI agents that combines an open catalog of reusable SKILL.md recipes with a command-line interface. The catalog contains website-specific skills for tasks such as searching listings, tracking flights, finding events, and querying public APIs; skills can be installed with the browse CLI, and the videos describe generating new skills on demand by email. The CLI also provides low-level browser actions such as clicking, typing, selecting, scrolling, hovering, pressing keys, and taking screenshots, along with network and console tracing for debugging. It can run commands against local Chromium or remote Browserbase sessions, including cloud search and fetch operations.

BrowserSkill is an open-source browser-automation bridge for AI agents, consisting of the `bsk` CLI and daemon plus a Chrome or Microsoft Edge extension. An agent sends browser tasks through the CLI; the local daemon routes them over WebSocket to the extension, which performs actions in a separate visible Agent Window. Agents can use existing browser login state, borrow an already open tab only with explicit approval, and request human intervention for captchas, confirmations, or other user-only steps. It supports shell-capable agent harnesses, macOS, Linux, and Windows, and is distributed under the MIT license.

AutoBrowse is an open-source browser-skill training demo from the AI Engineers workshop. It pairs a frozen doer agent, which operates a browser through the browse CLI and records a trace, with a teacher agent that studies the trace, forms a hypothesis, edits strategy.md, and judges the next attempt. Repeated iterations hill-climb the strategy for a specified website and task; a final graduation run converts the strategy into a reusable SKILL.md that can be installed for Claude Code or Codex. The repository includes a local live UI, headless forge and demo commands, streamed run events, and per-run artifacts under ./workspace. It uses Browserbase for browser sessions and Anthropic models by default, and the README identifies the vendored evaluate.mjs doer as MIT-licensed.

skills.sh is an agent skills directory and open ecosystem for reusable capabilities for AI agents. It lets users browse and search skills, then install a skill from an owner and repository with the `npx skills add <owner/repo>` command. The site publishes a leaderboard and catalog of skills, including the AutoBrowse skill described in the video as a reusable artifact for browser-agent tasks.

Browser Use is an AI browser-automation framework and hosted service for assigning web tasks to agents. Its agents operate websites through a browser by opening pages, clicking controls, entering text, filling forms, and extracting structured data. The project provides a Python library for embedding browser agents in applications, a CLI for agent-driven one-off tasks, and a Browser Use Cloud API with hosted agents and managed browser infrastructure. The library supports different LLM providers, custom tools, structured output, reusable browser profiles, and parallel or scheduled automation. The open-source library is free to use and licensed under the MIT License; the hosted service adds scalable browser infrastructure, proxy rotation, stealth browser fingerprinting, CAPTCHA handling, persistent storage, and integrations.