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
feder-cr/AIHawk
AIHawk is an open-source browser automation agent that operates a real browser the way a person would, moving the pointer and pressing keys, in response to a plain-language instruction rather than a fixed script. It can be used two ways: as an MCP server (aihawk) that any MCP-capable assistant such as Claude Code, Codex, or Gemini CLI can call to drive a real browsing session, or as a standalone local web UI (aihawk ui) served at 127.0.0.1:8765, pairing a chat panel with a live view of the browser it controls, using a user-supplied OpenRouter API key. Under the hood it is built on invisible_playwright, a Playwright-compatible engine exposed as a Python library for developers who want to script the same browsing behavior in code, and invisible_core, which manages the browser's fingerprint, seed, locale, timezone and proxy so a session's identity stays consistent across runs. Configuration options cover proxy support over HTTP or SOCKS5, a persistent profile directory so logins and cookies survive restarts, a fixed random seed for reproducible browser identities, and a .env file for credentials that keeps API keys out of shell history and process listings. The project's wiki documents the wider landscape of browser and computer-use agents and troubleshooting guidance for agents that get blocked by anti-bot defenses. AIHawk was previously used and covered in the press for automating large volumes of job applications, though the current README frames it as a general-purpose web browsing agent for any task requiring real browser interaction and human-like judgment about page content. It is MIT-licensed since September 2026, with earlier releases under AGPL-3.0.
https://github.com/feder-cr/AIHawk
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.
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.
ev-flow/quark-engine
Quark Agent is an AI-powered tool that enables natural language-based Android APK vulnerability and malware analysis through automated script generation and intuitive workflow design.