An agent-first browser automation CLI from Vercel Labs that enables efficient, low-token web interactions using a Ref-based system.

AI AgentsPlaywrightTypeScript

VIEW DETAILS →

High-performance browser automation bridge for AI agents. 12MB Go binary. Zero config. Accessibility-first approach for low-token page understanding and interaction.

AI AgentsGoCLI

VIEW DETAILS →

A cloud sandbox environment specifically built for AI agents, providing automation capabilities across browsers, desktops, mobile devices, and code spaces with multi-language SDK support.

Agent & ToolingPythonJava

VIEW DETAILS →

A tool that gracefully solves hCaptcha challenges using multimodal large language models, without relying on browser extensions or third-party captcha services.

Agent & ToolingPythonMultimodal

VIEW DETAILS →

AI-powered web content extraction tool that precisely scrapes webpage data using natural language queries, eliminating the need for complex selectors.

Agent & ToolingJavaScriptTypeScript

VIEW DETAILS →

An all-in-one agent sandbox environment that combines Browser, Shell, File, MCP operations, and VSCode Server in a single Docker container, providing a unified, secure execution environment for AI agents and developers.

Agent & ToolingDockerModel Context Protocol

VIEW DETAILS →

DeepResearch is an open-source deep research agent developed by Alibaba, designed for long-horizon, deep information-seeking tasks. With 30.5 billion total parameters but only 3.3 billion activated per token, it demonstrates state-of-the-art performance across various agentic search benchmarks like Humanity's Last Exam, BrowseComp, and WebWalkerQA.

Model & Inference FrameworkPythonPyTorch

VIEW DETAILS →

An open-source multimodal AI Agent stack developed by ByteDance, comprising the general Agent TARS framework and the UI-TARS Desktop client. It enables natural language control of computers, browsers, and terminals via Vision-Language Models.

Agent & ToolingTypeScriptNode.js

VIEW DETAILS →