Narada: a browser built for AI agents, under user control
Narada is a browser designed specifically for AI agents to interact with web content programmatically, while keeping the user in control. It uses LLMs to enable agents to browse, extract, and act on web pages, solving the problem of giving agents a safe, controllable web interface.
Visit project ↗Related
Clark: AI assistant with computer use and browser automation
Clark is an AI assistant that can use a computer and browser to complete tasks autonomously. It leverages LLMs for task planning and execution, aiming to match the capabilities of Manus agent. The tool is designed for users who need an AI agent that can perform complex, multi-step tasks across web and desktop environments.
AI agent that controls PC by watching screen
Rosply is an AI agent that takes over a user's mouse and keyboard by capturing screenshots, sending them to a vision model, and executing actions like clicking, typing, scrolling, and dragging. It works without APIs or browser extensions, enabling tasks such as web browsing, file summarization, and coding in VS Code via voice commands.
AI news aggregator agent that filters and summarizes
An agent that automatically collects AI news from multiple sources, filters out noise, and provides concise summaries. It uses LLMs to understand user interests and generate personalized digests, saving time for professionals who need to stay informed without constant scrolling.
Open-source desktop agent for local computer use, browser control, and file/code tasks
EverFern is an open-source (MIT) desktop agent that performs computer use, browser control, and file/code tasks entirely locally. It uses LangGraph for agent orchestration and supports local models via Ollama/LM Studio or cloud providers. Aimed at users who want to avoid subscription fees and keep data private.
Agent Legibility Analyzer: test if AI shopping agents can parse your store
A tool that lets e-commerce store owners check whether AI shopping agents can read and understand their product listings. It uses LLMs to simulate how agents interpret store content, helping merchants optimize their sites for agent-driven shopping.