NousResearch/hermes-agent
Hermes Agent is a self-improving AI agent by Nous Research designed to learn from experience, create and refine skills, and maintain knowledge across sessions.
Awesome AI Agents › AI-Powered Agents
normal-computing/fuji-web
Fuji-Web is an AI-powered browser extension designed to automate tasks within the web browser by understanding user intent and autonomously navigating websites to execute commands. It operates from a sidepanel in the browser, allowing users to input tasks that the AI agent then performs while providing explanations for each action taken. The project aims to simplify online task completion by enabling users to accomplish complex workflows with a single command. Users install the extension by downloading it from the releases page, loading it into their Chrome browser, and providing an OpenAI or Anthropic API key to enable AI functionalities. The extension processes all prompts directly through the selected API, ensuring user data privacy as no information is collected by Fuji-Web itself. The project includes detailed instructions for installation, usage, and building the extension from source, supporting developers who want to contribute or customize the tool. Fuji-Web's roadmap outlines plans to enhance its capabilities by adding an API for integration with popular browser automation frameworks like Puppeteer, Playwright, and Selenium, supporting more complex and cross-tab workflows, enabling content extraction and interaction with page elements, and facilitating workflow saving and sharing. Additionally, the project envisions a collaborative knowledge base to improve AI performance through community contributions. Fuji-Web is inspired by academic research and existing browser automation tools, incorporating innovative image annotation methods and UI elements from other projects. It is actively maintained with a contribution guide and a dedicated Discord channel for feedback. The project is well-documented, including troubleshooting resources and a clear vision for future development, making it a promising tool for users seeking to automate web browsing tasks efficiently and intuitively.
https://github.com/normal-computing/fuji-web
Also in AI-Powered Agents
google-gemini/gemini-cli
Gemini CLI is an open-source AI agent that integrates Google's powerful Gemini model directly into the terminal, enabling developers to perform advanced code understanding, automation, and integration tasks efficiently from the command line.
feder-cr/AIHawk
Open-source AI browser agent that follows natural-language instructions to click, type and read a real browser, usable via MCP or a standalone web UI.
earthtojake/text-to-cad
A library providing agent skills for CAD, robotics, and hardware design, enabling AI agents to generate, inspect, and manage various design artifacts.
lsdefine/GenericAgent
GenericAgent is a minimal, self-evolving autonomous agent framework that allows LLMs system-level control over a local computer, growing skills through task execution.
browseros-ai/BrowserOS
BrowserOS is an open-source, privacy-first Chromium-based browser that runs AI agents locally to automate browsing tasks and protect user data.
ChatLab/ChatLab
ChatLab is a local-first desktop application that analyzes chat histories from various platforms using AI agents and a SQL engine for insights and visualizations, prioritizing user data privacy.
Integuru-AI/Integuru
Integuru is an AI agent that generates integration code by reverse-engineering platforms' internal APIs using browser network requests and OpenAI models to automate platform interactions without requiring permission.