AI Agents & Automation

Cloudflare AI Cloud offers a comprehensive infrastructure for scaling AI applications, from storing training data to running inference. It allows users to deploy AI agents and applications on Cloudflare's global network, leveraging serverless inference on GPUs for responses under 100 ms worldwide without managing clusters. The platform includes an Agents SDK for building goal-driven agents, Remote MCP servers for secure tool exposure, and AI Gateway for caching, rate-limiting, and observability. It also provides Vectorize for a globally-replicated vector database and R2 object storage for egress-free data storage. Cloudflare AI is designed for developers to build, deploy, and scale AI agents and applications with battle-tested infrastructure.

AutoRCCar is an open-source project designed to create a self-driving RC car. It integrates a Raspberry Pi, Arduino, and various open-source software components to achieve autonomous navigation. The Raspberry Pi collects inputs from a camera module and an ultrasonic sensor, transmitting this data wirelessly to a computer. The computer then processes these inputs for object detection, specifically identifying stop signs and traffic lights, and for collision avoidance. A neural network model, running on the computer, makes predictions for steering based on the input images. These predictions are subsequently sent to the Arduino for controlling the RC car. The project provides detailed instructions for setting up the environment using Anaconda, calibrating the Pi Camera, collecting training data, and training the neural network model.

Hello-Agents is a comprehensive, open-source tutorial designed to guide users through the process of building intelligent AI agent systems from the ground up. This resource, developed by the Datawhale community, focuses on AI-native agents, moving beyond workflow-driven software agents. It covers core principles, architectural understanding, classic paradigms, and hands-on construction of multi-agent applications. The tutorial is structured into five parts, progressing from foundational concepts and historical context of AI agents and large language models to advanced topics like memory systems, context engineering, communication protocols, and agentic RL. It culminates in practical case studies, including building smart travel assistants and simulated cyber towns, and a final graduation project to apply learned skills. The project emphasizes practical application, providing all necessary code and encouraging hands-on experimentation.

2V is a platform designed for creating interactive AI experiences, focusing on personalization. Users can build AI interactions that reflect their own life and personality, leading to unique and engaging AI simulations. The platform aims to provide a distinct approach to AI interaction, moving beyond generic responses to offer a more tailored and immersive experience. While specific features are not detailed, the core offering revolves around enabling users to craft AI agents that embody personal characteristics and respond in a customized manner, fostering a deeper connection with the AI.

Awesome-Embodied-Robotics-and-Agent is a curated list of research focusing on "Embodied AI or robot with Large Language Models" and Vision-Language Models (VLMs). Maintained by haonan, this repository serves as a dynamic resource for academics and researchers to stay updated on the latest advancements. It includes a systematic categorization of efficient VLAs, covering model design, training strategies, and data collection methods. The list features surveys, vision-language-action models, self-evolving agents, advanced agent applications, LLMs with RL or world models, and more, making it an invaluable resource for anyone exploring the intersection of AI, robotics, and large language models.

Awesome-AI-Agents-for-Healthcare is a comprehensive, open-source repository that curates the latest advancements in Agentic AI and AI agents specifically tailored for the healthcare domain. This resource provides a meticulously organized collection of research papers, innovative projects, and valuable tools. It covers a wide array of applications, including medical image analysis, electronic health record (EHR) manipulation, counseling, drug discovery, patient dialogue systems, and healthcare administration. The repository also features a conceptual framework illustrating the pipeline from data perception to a hierarchical application ecosystem, alongside a quantitative analysis of academic literature highlighting key trends in data modalities, technologies, and application domains. It's an invaluable resource for researchers, developers, and practitioners looking to explore and implement AI solutions in healthcare.

Awesome-GPT-Agents is a community-driven, open-source repository that compiles a comprehensive list of GPT agents specifically designed for cybersecurity. This curated collection includes tools for both offensive and defensive security operations, making it a valuable resource for cybersecurity professionals, researchers, and AI enthusiasts. The repository emphasizes community contributions, encouraging users to add their own creations. It also provides basic guidelines for maximizing the use of these GPTs, including specific keywords that trigger actions like information retrieval or code interpretation. Users are advised to exercise caution and evaluate agents before use, as some are still in experimental phases.

uAgents is a fast and lightweight framework developed by Fetch.ai for creating decentralized AI agents using Python. It provides an intuitive way for developers to build autonomous agents that can perform various tasks, either on a predefined schedule or in response to specific events. A key feature is its automatic registration on the Fetch.ai blockchain's Almanac upon startup, connecting agents to a growing decentralized network. The framework ensures secure communication and wallet management through cryptographic methods, protecting agent identities and assets. It offers simple, expressive decorators for defining agent behaviors and supports fixed agent addresses via seed parameters. uAgents is designed for ease of use, allowing for rapid development and deployment of AI agents within the Fetch.ai ecosystem.

Discovery Machine, Inc. specializes in advanced AI solutions that transform the nuanced decision-making of subject matter experts into scalable, self-directed agentic AI. Since 1999, the company has combined proven methodologies with cutting-edge AI to offer expert training, decision support, and automation services. Their platform creates AI Role Players for increased training realism, AI Instructors for 24/7 custom coaching, and AI Advisors to streamline enterprise ecosystems. These solutions are designed to deliver efficiency gains, reduce operating costs, and enhance team experiences, with comprehensive services from initial scoping to delivery and ongoing support. Discovery Machine serves mission-critical enterprises, particularly in defense, by addressing the challenge of perishable institutional knowledge.

EasyApplyJobsBot is a Python bot designed to automate the job application process across various platforms including LinkedIn, Glassdoor, Indeed, and Monster. It streamlines job searching by automatically logging in, filling out additional questions, and submitting applications based on user-defined preferences. The bot supports filtering jobs by location, keywords, experience, and salary. Users can choose between a free version with basic functionalities or a 'Pro' version that offers advanced features like AI-powered resume enhancement, real-time analytics, automated follow-ups, and cross-platform compatibility. The tool can be installed via Docker for ease of use or manually, and it includes a dry-run mode for safe simulation before actual applications.

NukkAI specializes in agentic AI solutions, bridging human and machine intelligence to solve complex problems, particularly in crew scheduling and critical systems. Their flagship product is an agentic crew scheduling software that is designed to be the fastest on the market, incorporating business rules, regulations, and handling potential disruptions. A key differentiator is its explainable AI, ensuring transparency and human-in-the-loop control, avoiding black box operations. Beyond aviation, NukkAI co-designs decision systems for organizations facing critical challenges, leveraging neuro-symbolic research for real-time adaptation and explainable AI in high-stakes environments like transport and healthcare.

HOAi is the leading AI solution for the community association management industry, offering an AI workforce that handles operations end-to-end. It deploys AI agents that act like experienced managers, executing complex tasks autonomously 24/7, without breaks or burnout. These agents can process thousands of business emails, handle resident and board requests, prepare reports, manage budgets, and more, all in minutes. HOAi enables organizations to scale without new hires, delivering faster, higher-quality service with clear ROI by automating repetitive work and allowing human teams to focus on strategic tasks. Users teach the AI processes once, then it handles customer inquiries and completes tasks, with the ability for users to review and approve results.

ELNA.ai is positioned as an AI companion operating on the blockchain, focusing on the development, creation, and monetization of AI agents. While specific features are not detailed on the homepage, the platform's core identity revolves around leveraging blockchain technology for AI agent infrastructure. It aims to provide a decentralized environment for users to interact with and potentially build AI agents, suggesting a focus on the underlying framework and infrastructure for AI within a decentralized ecosystem. The platform's emphasis on blockchain implies aspects like transparency, security, and potentially tokenization or decentralized governance for AI agents.

factorie.io, led by Urvesh Goel, is a business consulting service focused on democratizing manufacturing and fostering growth. The platform offers business consulting services and features articles written by Urvesh Goel on a range of topics including execution, understanding emotions, and digital trends like Artificial Intelligence. These articles delve into subjects such as the impact of AI on jobs, decoding intelligence, and intelligent customer engagement. The site also showcases Urvesh Goel's professional experience and education, highlighting his background in digital entrepreneurship and his academic pursuits at the Indian Institute of Technology, Roorkee. The content suggests a focus on strategic insights and practical applications for business leaders.

Marlin is an extremely optimized FP16xINT4 matrix multiplication kernel specifically designed for Large Language Model (LLM) inference. It aims to deliver close to ideal (4x) speedups for batch sizes up to 16-32 tokens, significantly outperforming prior work that typically achieves comparable speedups only at 1-2 tokens. This makes Marlin particularly well-suited for larger-scale serving, speculative decoding, and advanced multi-inference schemes like CoT-Majority. The kernel employs numerous techniques and optimizations, including organizing computation for efficient L2 cache usage, asynchronous global weight loads, double buffering for shared memory loads, and careful ordering of dequantization and tensor core instructions. It also reshuffles quantized weights and group scales offline for ideal access patterns and uses a "striped" partitioning scheme for good SM utilization across various matrix shapes. Marlin requires CUDA >= 11.8, an NVIDIA GPU with compute capability >= 8.0 (Ampere or Ada), and torch>=2.0.0.

awesome-llm-agents is a comprehensive, curated list of open-source LLM agent frameworks and development tools designed to assist developers in building sophisticated AI agents. The repository features a wide array of frameworks, each detailed with its key characteristics, such as multi-agent collaboration, modular architecture, data analysis capabilities, and integration with various LLM providers. It includes popular tools like CrewAI, Langchain, Microsoft AutoGen, and Llama Index, alongside specialized frameworks for areas like software development (MetaGPT), scientific discovery (GenoMAS), and robotics (RAI). The list is regularly updated and serves as a valuable resource for anyone looking to explore or implement LLM agent technologies, offering insights into different approaches to agent design, workflow orchestration, and tool integration.

awesome-online-machine-learning is a comprehensive, open-source curated list of resources dedicated to online machine learning. This field focuses on machine learning where data arrives sequentially, allowing models to update incrementally with one data point at a time, contrasting with traditional batch learning. The repository provides valuable links to courses, books, blog posts, and software related to online ML. It also features an extensive collection of research papers covering various online learning topics such as linear models, support vector machines, neural networks, decision trees, unsupervised learning, time series analysis, drift detection, and anomaly detection. This resource is ideal for anyone looking to deepen their understanding or find tools for online machine learning.

Xpress AI offers an enterprise operating system for AI agents, transforming AI potential into measurable results by deploying managed digital workforces. It addresses common pain points of AI agent deployment, such as complex setup, reliability issues, and lack of trust. The platform enables users to name agents, assign roles, and have them perform tasks like SDRs, content managers, or DevOps engineers, without requiring extensive technical knowledge or dedicated hardware. Xpress AI features isolated container environments for safety, persistent memory systems for agents, and platform-level integrations for seamless workflow. It also provides XpressCLAW, a free, open-source agent runtime for local deployment.

HelixScale offers a signal-first outbound pilot designed for early-stage B2B founders selling technical products who lack a predictable pipeline. The tool identifies companies most likely to buy, builds a verified contact list, and activates them with outbound timed to their buying signals. It operates in three tiers: Pulse for identifying buyers and intent, Engage for converting signals into qualified conversations, and Accelerate for shortening sales cycles and improving close rates. HelixScale promises 5 qualified decision-maker conversations per month, with an extension if fewer than 3 are achieved. It focuses on precise, signal-driven outreach rather than generic, high-volume campaigns, ensuring every contact has a documented reason to act now.

Barie AI is an advanced AI agent designed to streamline complex workflows, from deep research and market analysis to strategy execution. It boasts the world's largest context window, enabling it to handle research tasks that other AI tools cannot, surfacing every source live. Barie AI integrates with numerous applications, allowing for multi-app workflows and automating tasks with contextual awareness. It also features a complete creation suite for generating videos, designing images, and building slides from a single prompt. Proven by GAIA Benchmark Testing, Barie AI adapts to various professions, offering capabilities like coding assistance, web search, and connectors to automate tasks, making work smarter and faster.

This open-source project, named Snake, provides an AI-driven approach to playing the classic game of snake. It implements two distinct artificial intelligence algorithms: graph search and reinforcement learning. The graph search algorithm uses a rule-based strategy, modeling the grid as a graph to find paths for the snake, including Hamiltonian paths for optimal play. The reinforcement learning algorithm, based on deep reinforcement learning with a neural network and Double DQN technique, allows the snake to learn through trial and error, maximizing cumulative rewards. The project includes a pre-trained reinforcement learning model and offers options to play with either algorithm or train your own RL model, making it a valuable resource for AI enthusiasts and developers.

Baby AGI offers an experimental framework for developing self-building autonomous agents, evolving from its original task planning approach. It introduces a new `functionz` framework for storing, managing, and executing functions from a database, complete with a graph-based structure for tracking imports, dependencies, and authentication secrets. The tool provides automatic loading, comprehensive logging, and a dashboard for managing functions, running updates, and viewing logs. It also includes experimental self-building agents that can generate and combine functions based on user input, showcasing its potential for automated code creation. While not intended for production use, it serves as a platform for experienced developers to explore and discuss ideas in autonomous agent development.

Awesome-LLM4AD is a comprehensive, open-source collection of research papers focused on Large Language Models for Autonomous Driving (LLM4AD). This resource tracks the latest advancements in the field, encompassing Vision-Language Models for AD (VLM4AD) and Vision-Language-Action models for AD (VLA4AD). Maintained by SJTU-ReThinklab, the repository categorizes existing works based on LLM applications in planning, perception, question answering, and generation for autonomous driving. It also highlights the motivation behind LLM4AD, addressing challenges like the sim2real gap and the long-tailed nature of autonomous driving tasks. Researchers and developers can find detailed information on papers, datasets, and project pages, making it an invaluable resource for staying current with the frontier of LLM4AD research.

The wuying-agentbay-sdk provides a cloud sandbox environment specifically designed for AI agents, enabling them to operate in isolated, on-demand settings. This SDK supports multiple programming languages including Python, TypeScript, Golang, and Java, offering a comprehensive API for agents to interact with a full cloud environment. Key functionalities include automating web operations, controlling cloud desktop applications, managing mobile UI automation, and providing a professional cloud development environment for code generation, compilation, and debugging. It eliminates the need for users to manage infrastructure, allowing agents to perform tasks and then be torn down, making it ideal for testing, development, and automated workflows.