Hugging Face's Open Computer Agent is an open-source AI tool designed to perform web-based tasks by emulating human interactions within a virtual Linux desktop environment. Powered by vision-language models like Qwen2-VL-72B and frameworks such as smolagents and E2B Desktop, it can navigate websites, fill out forms, and retrieve information based on natural language prompts. Operating through a browser interface, the agent simulates mouse and keyboard actions to execute tasks. While still in its experimental phase, it showcases the potential of AI agents in automating routine digital activities.

Hugging Face Open Computer Agent

hugging-face-open-computer-agent

An open-source AI agent that automates web tasks by simulating user interactions in a virtual Linux environment.

Google's Agent Development Kit (ADK) is an open-source framework designed to simplify the creation, deployment, and management of AI agents. Optimized for Google's Gemini models yet model-agnostic, ADK supports various agent types, including LLM-powered agents, workflow controllers, and custom agents. It offers features like multi-agent orchestration, tool integration, session management, and built-in evaluation tools. ADK facilitates flexible deployment options, including local environments, Google Cloud's Vertex AI Agent Engine, and Cloud Run, making it suitable for a wide range of AI applications.

Google Agent Development Kit

google-agent-development-kit

A modular framework for building, deploying, and managing AI agents across diverse workflows.

Google's Agent2Agent (A2A) protocol is an open standard designed to facilitate seamless communication and collaboration between AI agents developed by different organizations using various frameworks. A2A provides a standardized method for agents to discover each other's capabilities, negotiate interaction modalities, and securely collaborate on tasks without exposing internal states or proprietary tools. Built on existing technologies like HTTP, JSON-RPC 2.0, and Server-Sent Events (SSE), A2A supports both synchronous and asynchronous interactions, enabling agents to handle complex, long-running tasks efficiently. The protocol emphasizes security, interoperability, and scalability, making it suitable for enterprise-grade applications.

Google A2A

google-a2a

An open protocol enabling AI agents to communicate and collaborate across diverse systems securely.

Crawl4AI is an open-source, LLM-friendly web crawler and scraper designed to streamline web data extraction for AI agents and data pipelines. It offers features such as asynchronous crawling, structured data output in formats like JSON and Markdown, and integration capabilities with large language models. Crawl4AI supports advanced extraction strategies, including LLM-based methods, and provides tools for handling dynamic content, making it a versatile solution for developers seeking efficient and customizable web scraping solutions.

Crawl4AI

crawl4ai

An open-source, LLM-friendly web crawler and scraper optimized for AI agents and data pipelines.

Dcup is an open-source, self-hostable Retrieval-Augmented Generation (RAG) platform designed to help developers and teams build scalable, AI-powered retrieval pipelines. It enables seamless integration with data sources like Google Drive, Dropbox, and AWS, and supports advanced search capabilities including LLM re-ranking, summary indexing, and hybrid search using OpenAI embeddings and Qdrant vector storage. With its intuitive Retrieval API and modular architecture, Dcup simplifies the process of ingesting, indexing, and retrieving data, making it ideal for AI applications requiring efficient and accurate information retrieval.

Dcup

dcup

An open-source RAG-as-a-Service platform for building scalable, AI-powered retrieval pipelines.

HeyGem.ai is an open-source video synthesis tool developed by GuijiAI, designed for Windows systems. It enables users to create realistic digital avatars by precisely cloning their appearance and voice. The platform supports text and voice-driven virtual avatars, high-definition video synthesis, and multilingual support. Operating fully offline, HeyGem.ai ensures user privacy and offers a customizable solution for various applications, including content creation, education, and virtual assistance.

HeyGem.ai

heygem-ai

An open-source tool for creating realistic digital avatars with precise appearance and voice cloning, operating fully offline.

JobHuntr.fyi is a native macOS desktop application that leverages Ollama-powered AI to automate job applications on LinkedIn. Operating entirely on-device, it ensures user privacy while providing features like semantic filtering, tailored cover letter generation, and direct messaging to hiring teams. The app supports functionalities such as auto-apply, application queuing, and progress tracking, aiming to streamline the job search process with high personalization and efficiency.

JobHuntr.fyi

jobhuntr-fyi

A macOS app that automates personalized job applications using on-device AI, enhancing job search efficiency.

Codex CLI is an open-source, terminal-native AI coding assistant developed by OpenAI. Designed for developers who prefer working directly in the terminal, it integrates OpenAI's latest models (like o4-mini) to perform tasks such as reading, modifying, and executing code within a local environment. Codex CLI supports multimodal inputs, allowing users to pass text, screenshots, or diagrams to generate or edit code accordingly. It offers three distinct approval modes—Suggest, Auto Edit, and Full Auto—providing flexibility in how autonomous the agent operates. The tool emphasizes security by running in a sandboxed, network-disabled environment and ensures that your source code remains on your machine unless explicitly shared. With zero-setup installation and compatibility with macOS, Linux, and experimental support for Windows via WSL, Codex CLI aims to streamline the development workflow by bringing powerful AI capabilities directly to the command line.

Codex CLI

codex-cli

Open-source terminal-based AI coding assistant that reads, writes, and executes code locally with multimodal input support.

Cerebrum is the Software Development Kit (SDK) for AIOS, the AI Agent Operating System. It provides developers with tools to build, deploy, and manage large language model (LLM)-based AI agents. Cerebrum addresses challenges such as scheduling, context switching, memory management, and tool integration, facilitating the creation of efficient and scalable AI agents. The SDK features a modular architecture encompassing LLM, memory, storage, and tool management layers, and includes an Agent Hub for sharing and discovering agents with version control and dependency management.

Cerebrum: AIOS SDK

cerebrum-aios-sdk

An SDK for developing and deploying LLM-based AI agents within the AIOS framework.

Apple's Ferret-UI is a multimodal large language model (MLLM) designed to comprehend and interact with mobile user interfaces (UIs). It possesses referring, grounding, and reasoning capabilities, enabling it to identify UI elements such as icons and text, understand their spatial relationships, and execute tasks based on this understanding. Ferret-UI aims to improve user interactions by facilitating advanced control over devices through natural language commands, potentially enhancing accessibility and automation in mobile applications.

Apple Ferret-UI

apple-ferret-ui

A multimodal AI model for enhanced understanding and interaction with mobile user interfaces.

The Capability Collaboration based AI Agent (CACA Agent) is an AI system designed to enhance the extensibility and functionality of AI agents by integrating a set of collaborative capabilities. Inspired by service computing, it reduces reliance on a single large language model (LLM) and promotes an open architecture. CACA Agent introduces components such as Planning Capability, Methodology Capability, Tools Capability, Tool Broker, and Tool Service, which work together to provide AI agent functionalities. This design facilitates quick deployment of AI agents and convenient expansion of their application scenarios, allowing for dynamic tool integration and improved planning abilities. A demonstration of the system illustrates its operation and the extension of application scenarios.

CACA Agent

caca-agent

An AI system enhancing agent extensibility through collaborative capabilities.

PC Agent is an AI system developed by GAIR-NLP that facilitates the creation of autonomous digital agents by transferring human cognitive processes. It comprises three key components: PC Tracker, a lightweight infrastructure for collecting large-scale human-computer interaction data; a Cognition Completion post-processing pipeline that converts raw interaction data into cognitive trajectories; and a multi-agent system combining a planning agent for decision-making with a grounding agent for robust visual grounding. PC Agent aims to enable AI to perform complex digital tasks autonomously by learning from human interactions.

PC Agent

pc-agent

An AI system enabling autonomous digital agents through human cognition transfer.

Explore AI Agents with free pricing