AI Agents & Automation

gym-pybullet-drones offers PyBullet Gymnasium environments specifically designed for single and multi-agent reinforcement learning in quadcopter control. This tool is a minimalist refactoring of its original repository, ensuring compatibility with Gymnasium, Stable-Baselines3 2.0, and Betaflight/Crazyflie-firmware SITL. It provides examples for PID control, downwash effect simulation, and reinforcement learning using SB3's PPO algorithm. Researchers and developers can use this environment to train and test control policies for drones, facilitating advancements in robotics and autonomous systems. The project also includes examples for integrating with Betaflight SITL and pycffirmware Python bindings.

infiAgent, also known as MLA (Multi-Level Agent), is an open-source agent framework designed for handling long-running, complex tasks without issues like tool calling chaos or system crashes due to cumulative task resources and conversation history. It enables users to build powerful general-purpose and semi-specialized agents by simply editing configuration files. Key features include support for days-long complex tasks with full recovery from interruptions, compatibility with the Agent Skills open standard for dynamic skill loading, and a flexible architecture supporting both multi-level hierarchy and flat designs. The framework utilizes a file-directory-based memory system for persistent memory across sessions, eliminating the need for external databases. It also offers a Docker-based Web UI for multi-user registration and account management, and supports multi-provider model configurations for fine-grained cost control.

Godela is an AI Physics Engine designed to revolutionize engineering and research by applying AI to understand the physical world. It learns the governing behavior of systems from existing simulation data, allowing users to train physics-constrained models. With Godela, users can explore 'what-if' scenarios by changing parameters like airflow, geometry, or materials, and receive physics-accurate answers in seconds, significantly faster than traditional simulations. The tool then helps converge on optimal configurations, turning months of R&D into minutes. Godela's applications span various physical domains, including data center thermal optimization, electronics cooling, aerodynamics, electromagnetics, and structural analysis, enabling faster problem-solving and design iteration.

Pastey Extension is a browser extension designed to bring AI capabilities to your workflow precisely when needed. It operates without explicit prompts, leveraging context-awareness to deliver relevant AI assistance directly within your current tab. The extension is built around your clipboard, allowing you to hold Ctrl+V to activate Pastey and paste content with AI enhancements. It prioritizes user privacy by storing clipboard data on-device. This tool aims to make AI accessible and efficient for everyday tasks, adapting copied text, rewriting tone, and offering a searchable clipboard history, making it a powerful addition for anyone looking to augment their copy-paste functionality with intelligent features.

LayoutParser is a comprehensive toolkit designed to streamline Deep Learning Based Document Image Analysis (DIA) tasks. It offers a rich repository of deep learning models for layout detection, along with unified APIs for easy integration and use. The toolkit includes carefully designed layout data structures optimized for DIA, enabling tasks like selecting specific layout elements or performing OCR on detected regions. LayoutParser also provides flexible APIs for visualizing detected layouts and supports loading layout data from various formats including JSON, CSV, and PDFs. It functions as an open platform, encouraging the sharing of layout detection models and DIA pipelines within the community, making it a versatile resource for researchers and developers in the field.

Isaac Lab is a GPU-accelerated, open-source framework designed to unify and simplify robotics research workflows, including reinforcement learning, imitation learning, and motion planning. Built on NVIDIA Isaac Sim, it combines fast and accurate physics and sensor simulation, making it an ideal choice for sim-to-real transfer in robotics. The framework provides developers with essential features for accurate sensor simulation, such as RTX-based cameras, LIDAR, and contact sensors. Its GPU acceleration enables faster complex simulations and computations, crucial for iterative processes like reinforcement learning. Isaac Lab supports over 16 robot models and more than 30 ready-to-train environments, compatible with popular reinforcement learning frameworks like RSL RL, SKRL, RL Games, and Stable Baselines. It can run locally or be distributed across the cloud, offering flexibility for large-scale deployments.

Sparkle is an AI-powered Mac cleaner and file organizer designed to declutter your computer with minimal effort. It automatically identifies and deletes junk files, duplicates, and wasted storage space, helping users reclaim gigabytes of storage. Beyond just cleaning, Sparkle uses AI to organize files into personalized folders based on your work patterns, eliminating the need for manual sorting or complex rules. Users can set a schedule for continuous cleanup, ensuring their Mac remains organized without ongoing intervention. The tool prioritizes privacy, only reading file names for organization and never storing, selling, or using your content for other purposes. Sparkle offers a 15-day free trial to experience its features.

ix is an autonomous GPT-4 agent platform designed for building and deploying AI-powered agents and workflows. It offers a flexible and scalable solution for delegating tasks to AI agents, enabling them to automate a wide variety of tasks, run in parallel, and communicate with each other. Key features include a no-code agent editor for creating and testing agents with a visual graph interface, a multi-agent chat interface for interacting with teams of agents, and smart input with auto-completion. The platform supports various models like OpenAI, Google PaLM, Anthropic, and Llama. Its backend is dockerized and uses a Celery message queue for horizontal scaling of agent workers, making it suitable for complex and demanding AI applications.

Allofus is an AI platform designed to deliver personalized interactions through sophisticated AI-generated conversations. It empowers users to inform, educate, and entertain themselves by providing tailored information in real-time. The platform is built to mimic real conversations, offering an intuitive design that makes it accessible for users of all technical levels. Allofus prioritizes user privacy and data security, ensuring a safe and reliable environment for engaging with AI. Its core functionality revolves around creating dynamic and responsive conversational experiences that adapt to individual user needs and preferences.

Altered State Machine (ASM) is a protocol designed for Non-Fungible Intelligence, enabling the ownership of AI within NFTs. It provides an open protocol for AI agents that users can own, evolve, and personalize. The platform, branded as THINK, emphasizes 'Compiled Intelligence' where AI becomes code, reducing its reliance on models over time. This approach aims for on-device intelligence by default. Users can explore ThinkOS, a system for building and interacting with these AI agents, and engage with the community. The project also features a dashboard, AppCoin, and points system, suggesting a broader ecosystem for AI agent development and interaction.

gpt-pro-mode offers a collection of notebooks designed to give users access to advanced 'Pro Mode' functionalities for different GPT models, including gpt-oss-pro-mode, gpt-5-pro-mode, and nemotron-pro-mode. Users can run these notebooks to explore and experiment with enhanced AI capabilities. The tool also provides an integrated Pro Mode API endpoint, allowing for programmatic access and integration into other applications. It supports a 'tournament mode' for generation and synthesis, which processes requests with a higher number of generations in groups for more comprehensive results. This open-source project encourages community contributions and feedback for feature additions.

LlamaGym is an open-source framework designed to simplify the fine-tuning of Large Language Model (LLM) agents using online reinforcement learning. Unlike many current LLM-based agents that do not learn continuously in real-time, LlamaGym enables agents to interact with an environment and receive immediate reward signals for ongoing learning. It addresses common challenges such as managing LLM conversation context, handling episode batches, assigning rewards, and setting up Proximal Policy Optimization (PPO). By providing a single abstract Agent class, LlamaGym allows developers to quickly iterate and experiment with agent prompting and hyperparameters across various Gym environments, making the process of integrating LLMs with RL more accessible. While currently a work in progress, it aims to streamline the development of adaptive LLM agents.

explai.com is an innovative platform leveraging agentic AI to transform data analytics. It creates data agents that act as a personal 24/7 data analytics team, enabling business users to gain value from their data quickly. The platform focuses on guided analytics, proactively suggesting personalized next steps and discovering relevant data on demand. It also features safeguarded automation, where AI agents co-operate and use tools with best practices for handovers and quality checks. explai.com emphasizes privacy, with all data staying in the user's private space, deployed according to company guidelines. It aims to empower every knowledge worker to competently work with data, supporting decisions with strong rationales and impactful communication.

chatgpt-web is an open-source, third-party web user interface for ChatGPT, developed using Express and Vue3, and powered by the official OpenAI completion API. This project enhances the standard ChatGPT experience with several key features, including user registration, login, password reset, and two-factor authentication. It supports synchronized historical sessions, allowing users to maintain context across interactions, and enables the use of unique prompts for each conversation. The tool also provides user management capabilities, custom sensitive word filtering, and multi-key random selection for API calls. Additionally, it includes conversation quantity limits, adjustable per-user limits, and a web search function based on the Tavily API for real-time information retrieval. It also supports VLLM API models and offers an optional deep thinking mode.

HalloSophia is a leading platform designed to empower digital services with scalable eService and eConsulting, significantly enhanced by AI-driven support automation. It enables businesses, particularly tech companies and consulting agencies, to offer world-class, productized expert video consultations to their clients. The platform focuses on elevating service offerings through innovative technology, providing a robust solution for managing and automating customer interactions and expert advice. HalloSophia helps streamline operations, improve customer satisfaction, and drive efficiency in service delivery by leveraging artificial intelligence to support and automate various aspects of customer engagement and consultation.

Dragonfruit AI is an all-in-one enterprise AI platform specifically designed for retail, leveraging existing camera infrastructure to provide actionable intelligence. It employs computer vision and specialized AI agents to address critical retail functions such as shoplifting detection, queue management, checkout loss prevention, and customer journey insights. The platform offers a unified dashboard for centralized control across various applications and agents, making it easy for LP, Operations, and CX teams to manage. Dragonfruit AI is built for scalability and cost-effectiveness, integrating with existing VMS and camera systems even in low-bandwidth environments. Its patented split AI architecture focuses on edge-first processing to reduce bandwidth and cloud compute costs, making it an efficient solution for multi-location enterprises.

RF-DETR is a real-time transformer architecture for object detection and instance segmentation, developed by Roboflow. Built on a DINOv2 vision transformer backbone, it achieves state-of-the-art accuracy and latency trade-offs on Microsoft COCO and RF100-VL datasets. The tool supports both detection and instance segmentation through a consistent API and is designed for fine-tuning. It offers various model sizes, from Nano to 2XLarge, with some larger models requiring the `rfdetr_plus` extension. RF-DETR can be installed via pip or from source, and models can be run using the `rfdetr` package or the Inference library. Training capabilities are available in Google Colab or directly on the Roboflow platform.

Vibe Voice Custom Voices is an innovative audio & music tool hosted on Hugging Face Spaces, designed for generating audio from text input. It offers robust support for both single and multi-speaker voices, making it versatile for various audio production needs. A key feature is its voice cloning capability, allowing users to upload audio clips for each speaker to replicate their voices accurately. The application provides a generated audio output, enabling creators to produce custom voice content efficiently. This tool is ideal for those looking to experiment with voice synthesis and cloning without complex setups, offering an accessible platform for audio creation.

GradioChat is a versatile AI chat application hosted on Hugging Face Spaces, enabling users to interact with a multitude of AI chat channels simultaneously. The platform supports up to 10 distinct AI channels, providing a dynamic environment for conversational AI exploration. Users can input their messages and select a specific AI channel to receive responses, facilitating comparative analysis or diverse conversational experiences. The tool offers predefined examples for quick interaction, alongside the flexibility for users to type their own questions, making it accessible for both casual exploration and more specific inquiries into conversational AI capabilities. It's built with Gradio, emphasizing ease of use for creating interactive chat applications.

Olimi AI specializes in providing voice AI agents for businesses, particularly focusing on the MENA region with native accuracy in Arabic. The platform supports over 20 languages and dialects, including English, French, Spanish, and Italian, allowing for broad international deployment. These voice agents are designed to handle various tasks, such as qualifying leads, following up on payments, and managing routine conversations, making them suitable for businesses with high call volumes. Olimi AI aims to deliver natural, human-sounding interactions in real-time, enhancing customer experience and operational efficiency across multiple industries.

PepHop AI provides an AI-powered platform for creating and interacting with customizable AI characters. Users can choose from a variety of existing AI personalities or design their own, tailoring their appearance, backstory, and conversational style. The platform supports both SFW (Safe for Work) and NSFW (Not Safe for Work) content, offering flexibility for different user preferences. It leverages advanced language processing to facilitate natural and engaging conversations, and importantly, it remembers past dialogues to maintain context and continuity across interactions. This allows for more personalized and evolving relationships with the AI characters.

Ithaca is a pioneering deep neural network developed by Google DeepMind for the restoration, geographical, and chronological attribution of ancient Greek inscriptions. This open-source tool significantly enhances the historian's workflow by providing a collaborative, decision-support, and interpretable architecture. It achieves 62% accuracy in restoring damaged texts, and when used by historians, their performance leaps from 25% to 72%. Ithaca can also attribute inscriptions to their original location with 71% accuracy and date them with a distance of less than 30 years from ground-truth ranges, contributing to critical debates in Ancient History. The project includes an interactive online notebook and an offline library for advanced users.

Ditto offers a unique platform where users can create an AI avatar of themselves, which then inhabits a shared digital city alongside other AI avatars. These AI entities are designed to live a 'second life,' engaging in social interactions, forming relationships, and embarking on various adventures. The platform emphasizes emergent behavior, where users can observe their AI counterparts meeting new people and making memories without direct intervention. This tool provides a novel way to explore AI agent interactions and personality simulation within a playful and creative context, showcasing how AI can develop and maintain social connections in a virtual environment. Users are invited to drop their number to be notified when the service goes live, indicating an upcoming launch.

Zulu OpenClaw App is an autonomous AI agent platform built on open-source foundations, designed to make powerful AI accessible and production-ready without complex setup or security risks. It allows users to connect with services like Gmail, Google Sheets, Calendar, and Analytics to automate tasks such as clearing inboxes, managing schedules, tracking leads, and surfacing website insights. The platform supports full agent capabilities including coding, browsing, file management, and persistent memory, going beyond simple chat. It's available through WhatsApp, Telegram, a native app, or API, and offers transparent billing with token-based usage, ensuring no surprise costs. OpenZulu bridges the gap between powerful open-source AI and a managed, secure, and easy-to-use platform for businesses and individuals.