awesome-web-agents

Agent & framework with HTML DOM distillation.

Deploy autonomous AI agents in your browser.

Computer use agent that can control your browser.

AI browser automation tool with natural language control.

An open-source & self-hostable browser automation library for AI agents.

SOTA agent and framework that makes the web LLM-friendly.

Self-improving QA harness for natural-language web test runs with execution memory and self-healing actions.

Hosted browser agents for SMEs to automate complex workflows.

A free, experimental Chrome extension that leverages Claude Computer Use to automate tasks in your browser.

Experimental agent for task completion and web browsing.

HTTP API and MCP server that lets AI agents interact with websites through natural language instead of CSS selectors.

A Chrome extension that enables AI-powered browser automations, allowing users to automate tasks and workflows directly within the browser.

A query language and toolkit that makes the web AI-ready.

The fastest and most accurate web search API for AI agents.

Neural search platform for web data.

Search engine that indexes 1,750+ agent-first tools ranked by agentic readiness. Available as an MCP server with tools for searching, scoring, and monitoring agent infrastructure.

Search API that provides Google Search results for your agents.

Performant and cost effective search API that provides Google Search results for your agents.

An open-source evaluation framework for web-based AI agents.

A gym environment for web task automation.

283 everyday tasks (V1 153 + V2 130) on 163 live production websites across 15 categories. Two-stage scoring (final HTTP-request interception + LLM judge) blocks only the write request so real sites stay clean. Public leaderboard with 5-layer execution traces (recording, action log, request log, agent messages, interception).

A large-scale dataset for generalist web agents.

A classic suite of 104 mini web browser tasks in a synthetic environment. It is an extension of the OpenAI MiniWoB benchmark.

A benchmark on historical versions of web UI.

Walks through deploying a Browser-Use web UI agent powered by the DeepSeek model on a cloud VM.

Step-by-step guide to create an AI that browses the web using Playwright and the Browser-Use library.

Instructions on installing the open-source Browser-Use agent with a local LLM.

Tutorial demonstrating how to build a web navigation agent using LangGraph Agents, Vision Models, and Web Voyager.

Open-source LLM Friendly Web Crawler & Scraper.

AI web data agent that plans browser scraping tasks, extracts structured web data, and exposes MCP tools for dataset workflows.

Turns any website into a type-safe API you can rely on.

APIs for turning websites into LLM-friendly markdown.

Uses LLMs for intelligent scraping and content understanding.

Open-source headless browser engine for AI agents. Compiles HTML to Semantic Object Model (SOM) with 17.5x token compression. 13 MCP tools. First browser tool on the MCP Registry. Rust, Apache-2.0.