Loading...
Loading...
Browser Harness: Browser Harness | Self-healing harness that enables LLMs to complete any task. It is listed under Development & Code on AI Registry as a free tool.
The tools below are approved listings in the same category, ordered by how closely their tags match Browser Harness. This is an automatic list. We have not written a researched verdict for Browser Harness yet, so treat it as a shortlist and check each vendor's pricing page before switching.
Built from each tool's listing. Vendors can update their own listing after claiming it.
Make Any Website into CLI & Use your logged-in browser by AI agent.
OpenCLI is a general purpose browser automation command line tool built for AI agents. It lets an agent navigate pages, click, fill in forms, and extract content by working through the user's own logged in Chrome browser, so an agent can reach sites where the user is already signed in without handling credentials separ...
Atomic Agent is a local-first AI agent.
Atomic Agent is an open source, local first AI operator that runs on the user's own machine and drives real tools: the browser, the file system, the shell and git. It runs a local model through llama.cpp, so there is no cloud account, no API key and no token bill, and every session is stored on the user's own disk. It ...
Open source and self-hostable browser automation library for AI agents
Browserable is an open source JavaScript library and self hostable platform for building browser agents. An agent built with it navigates websites, fills out forms, clicks buttons and extracts information from pages in response to a plain language task, such as finding a beginner course on a learning site or locating t...
macOS app for 24/7 AI agents in an IDE with memory, scheduled tasks, browser use + access to Whatsapp, Telegram, Slack.
Dorabot is an open source macOS app that runs an always on, self learning AI agent inside its own IDE style workspace. Built on Claude Code, it works with an existing Claude Code or OpenAI Codex subscription, so no separate API key is required. The agent manages its own goals, tracks research, runs scheduled tasks, aut...
Give any AI agent a full desktop — it sees the screen, clicks, types, and runs apps like a human.
GhostDesk is a Model Context Protocol server that gives an AI agent a full desktop to work on. It lets the agent see the screen, click, type and launch applications the way a person would, either inside a disposable containerized sandbox or directly on the machine in front of the user. It is the flagship project of YV1...
let any ai agent use the local browser
Hanzi Browse gives an AI coding agent a real browser to work with. It installs a Chrome extension and an MCP server, then lets agents such as Claude Code, Cursor and Codex delegate browser work like clicking, reading pages and filling forms in the user's own signed in Chrome. A browser sub agent runs the loop of readin...