AI Agents & Automation

SMOKE is an open-source, real-time monocular 3D object detector specifically designed for autonomous driving applications. It utilizes a single-stage approach via keypoint estimation to achieve efficient and accurate 3D object detection from a single camera. The system boasts a runtime of approximately 30ms on an NVIDIA TITAN XP GPU. SMOKE's performance has been evaluated on the KITTI 3D detection dataset, showing competitive results for detecting cars, pedestrians, and cyclists. The project provides pretrained weights and detailed setup instructions for researchers and developers, building upon components from CenterNet, maskrcnn-benchmark, and Detectron2.

Moonlite AI delivers high-performance AI infrastructure designed for enterprise-grade performance and compliance, specifically targeting demanding AI workloads such as computational research, distributed model training, and large-scale data processing. The platform offers the flexibility to deploy infrastructure within existing data center facilities or in Moonlite's own facilities, combining bare-metal performance with cloud-native simplicity. Key features include purpose-built compute infrastructure optimized for parallel processing and distributed workloads, high-performance networking with RDMA and InfiniBand, and tiered storage solutions. Moonlite also emphasizes compliance by design, with built-in network isolation, enterprise controls, and certifications like SOC 2, ISO 27001, and ISO 42001, ensuring regulatory requirements are met.

HumanGO AI is an innovative AI-powered training platform designed to enhance human potential through personalized health solutions. It offers hyper-personalized adaptive training plans that adjust to an individual's schedule, goals, and progress. The platform integrates with various wearable devices to monitor key health metrics and predict fitness levels. A standout feature is Hugo, the AI coach, who provides instant feedback, guidance, and even engages in 'lively debates' to ensure optimal training. HumanGO caters to athletes, coaches, and teams, helping them set goals, track progress, and achieve peak performance, whether for a specific race or general fitness improvement. It aims to simplify training plan creation, making effective training accessible to everyone.

OpenChem is a deep learning toolkit specifically designed for computational chemistry and drug design research, built with a PyTorch backend. Its primary goal is to simplify the application of deep learning models for researchers in these fields. Key features include a modular design with a unified API, allowing for easy combination of different modules, and the ability to build new models using only a configuration file. The toolkit supports fast training with multi-GPU capabilities and provides utilities for data preprocessing. It also integrates with Tensorboard for visualization. OpenChem handles various tasks such as classification, regression, multi-task learning, and generative models, supporting data types like character sequences (SMILES, amino acids) and molecular graphs, with automatic conversion of SMILES to graphs.

PortableDocs is a comprehensive PDF suite designed for secure and efficient document management. It allows users to convert PDFs to Word, add watermarks, insert page numbers, merge and split files, compress, rotate, and reorder pages. The platform also offers robust security features like 256-bit encryption, redaction of sensitive information, and repair for broken PDF files. A standout feature is its AI chat capability, enabling users to have conversations with their PDFs, ask questions, get summaries, and extract insights instantly. PortableDocs emphasizes privacy with no data storage, ensuring files disappear after processing, and operates entirely online without requiring downloads or installations.

text_gcn is an open-source implementation of Graph Convolutional Networks (GCNs) specifically designed for text classification tasks. This tool provides the necessary code to reproduce the results presented in the paper "Graph Convolutional Networks for Text Classification" from the AAAI 2019 conference. It requires Python 2.7 or 3.6 and Tensorflow >= 1.4.0, making it accessible for those familiar with these environments. The repository includes scripts for data preparation, graph building, and model training, along with examples for various datasets like 20ng, R8, R52, ohsumed, and mr. An inductive version, fast_text_gcn, is also available for scenarios where test documents are not included in the training process.

Gemini Business2API functions as an OpenAI-compatible API gateway, enabling users to leverage Gemini Business capabilities through a familiar interface. This tool is designed with multi-account load balancing, ensuring efficient distribution of requests across multiple Gemini Business accounts. It supports advanced multimodal features, including image and video generation, as well as comprehensive file parsing. The platform includes a built-in management panel for streamlined administration, allowing for unified management of account pools, system settings, and operational status. Key features like account import/export, batch operations, and status filtering enhance usability. It also offers flexible deployment options via Docker Compose or an interactive installation script, making it accessible for various technical setups.

Myko AI functions as an operating system for field teams, enabling them to interact with CRMs like Salesforce and Veeva using natural language. This AI tool automates administrative tasks such as logging calls, placing orders, and sending quotes, significantly reducing the time spent on CRM updates. It ensures data cleanliness and compliance with existing business rules by reviewing every action before it touches the CRM. Myko AI integrates with Salesforce, Veeva, Dynamics, and other internal data sources, allowing for multi-step workflows and complex approvals by voice. The platform also features a proprietary search algorithm for accurate record finding, even with typos, and offers fast customization for rules and automations.

Velona is an advanced AI fleet management platform designed to move beyond simple monitoring to proactive fleet optimization. It employs a suite of specialized AI agents, each trained on extensive fleet operations data, to manage various aspects of a fleet. Key functionalities include predictive maintenance to anticipate failures, real-time fuel fraud detection, driver behavior monitoring for safety, and compliance management. Velona also offers cost analytics to identify savings opportunities and EV charging optimization. The platform simplifies complex data science into conversational insights, providing prioritized tasks with complete context and actionable plans nightly, rather than just alerts. This allows fleet managers to make informed decisions quickly and efficiently.

AttentionDeepMIL offers a PyTorch implementation of Attention-based Deep Multiple Instance Learning, a technique detailed in the paper "Attention-based Deep Multiple Instance Learning" by Ilse, Tomczak, and Welling. This open-source tool is designed for researchers and developers to explore and apply attention mechanisms within deep learning models, particularly in the context of multiple instance learning. It includes code for running MNIST-BAGS experiments and provides guidance for adapting the model to histopathology datasets like Breast Cancer and Colon Cancer. The implementation features a modified LeNet-5 model with Attention-based MIL pooling and uses the negative log-likelihood of the Bernoulli distribution as its objective function. It's a valuable resource for those looking to replicate or extend research in this specialized area of deep learning.

Plantum is an AI-powered mobile application designed to help users identify plants, diagnose plant illnesses, and receive personalized care recommendations. With its extensive database, users can instantly identify over 40,000 plant species, flowers, trees, and herbs by simply taking a picture. The app also features a 'Plant Doctor' to diagnose diseases and suggest treatments, and a 'Plant Care Guide' offering watering, light, and fertilizer recommendations. Users can set care reminders, utilize a light meter to measure sunlight, and even consult with real botanists for expert advice. Plantum aims to simplify plant care for both novice and experienced gardeners, making botany accessible to everyone.

Gemini Rproxy is a Hugging Face Space developed by Moonfanz, designed to serve as a proxy for the Gemini AI model. When accessed, the application displays a loading spinner and logo, indicating that the space is being prepared. Once the setup is complete, the page automatically refreshes, making the Gemini Rproxy ready for use. This tool is hosted on Hugging Face, a popular platform for sharing AI models and applications, and is currently paused. Users interested in utilizing this space are directed to the community tab to request its restart from the author.

MULTI·ON, operating under AGI, Inc., is an AI lab focused on bringing superintelligence to the edge, ensuring it is 100% secure, private, and accessible. Their mission is to enable the era of AI-native devices with agents that are fully-private, trustworthy, and run locally, promoting true decentralization of intelligence. Their first product, AGI-0, is a personalized, proactive AI co-worker designed to get tasks done on smartphones, currently available in early access. This includes capabilities for taxi, travel, message, music, order, shopping, and delivery tasks. The company emphasizes its commitment to on-device superintelligence and has collaborations with partners like Qualcomm Technologies to integrate agentic AI into Snapdragon-powered devices.

CodeBaby offers real-time interactive avatars designed to enhance engagement and streamline workflows across diverse sectors such as business, education, and healthcare. The platform allows users to create customized avatars that align with their brand and goals, or utilize turnkey managed solutions for comprehensive support. CodeBaby's AI-powered digital humans are used for applications like guided courses, patient intake assistance, customer and HR support, brand engagement, and venue concierges. The tool emphasizes human connection, delivering emotionally intelligent avatars to revolutionize customer experience journeys. It also supports integration with Proto Hologram technology for advanced solutions and addresses various industry-specific challenges.

openmlsys-zh is the Chinese version of the open-source textbook "Machine Learning Systems: Design and Implementation." This comprehensive resource delves into the core principles and practical implementation experiences of modern machine learning systems. It covers a wide array of topics, including programming interfaces, computation graphs, compilers, and distributed training. The book is designed to be valuable for students looking to deepen their understanding of ML systems, researchers developing custom operators or large models, and engineers responsible for ML infrastructure and performance tuning. The project is hosted on GitHub and provides detailed guidance for building and contributing to the content.

FirstRead is an AI legal associate designed to help law firms scale their practice by efficiently managing legal tasks. This tool acts as a trusted AI associate, handling legal tasks from inception to completion. It focuses on streamlining transactional work and seamlessly integrating into a firm's existing workflows. FirstRead provides access to trusted insights, leveraging a team's best practices to ensure consistent and high-quality output. Its primary goal is to empower legal professionals to grow their practice by automating and optimizing various legal processes, allowing them to focus on more strategic work.

Sellinger AI provides autonomous AI LinkedIn outreach, automating the entire sales outreach process from targeting decision-makers to driving meetings and sign-ups. The AI crafts human-quality conversations at scale, nurturing leads to booked calls, allowing users to focus on closing deals. Key features include deep lead research, human-like communication, and multi-purpose agents that adapt to prospect cues. It also offers frictionless scalability for managing thousands of concurrent conversations across multiple accounts, lead magnet posts, inbound interaction handling, and lead import/search capabilities. The platform learns your tone and optimizes messages for credibility and impact, while also providing lead journey analytics and custom goal setting.

Finster AI is an enterprise-grade AI platform designed specifically for finance professionals in investment banking and asset management. It acts as an AI research partner, accelerating analysis, automating workflows, and unlocking potential with AI built for the rigor and demands of the modern financial services firm. The platform offers personalized intelligence by adapting to user data, roles, and workflows, producing tailored outputs. It is proactive, anticipating needs and recommending next best actions. Finster AI prioritizes privacy and security, meeting rigorous standards with data controls maintained at the user or organization level within the firm’s governance perimeter. It provides precise, traceable insights at deal speed, automating data synthesis, analysis, and presentation for banking workflows.

Arabic Tokenizer Arena is a specialized platform designed for in-depth analysis of Arabic text tokenization. Users can input their own Arabic text or select from pre-made samples, then choose one or more tokenizers to observe how they split the text. The tool offers comprehensive metrics such as token count, fertility, and Out-Of-Vocabulary (OOV) rate, providing valuable insights into the tokenization process. Additionally, it generates visual representations to help users understand the tokenization results more intuitively. This tool is particularly useful for researchers, developers, and linguists working with Arabic language processing, offering a robust environment for comparing and evaluating different tokenization strategies.

Una by Polydom is an advanced AI host specifically designed for the hospitality industry, including Airbnb, short-term rentals, long-term rentals, and hotels. It operates 24/7, handling guest communications across multiple channels such as phone calls (inbound and outbound), live chat via website widgets, email auto-responses, and messengers like WhatsApp, Telegram, and Facebook. Una integrates seamlessly with existing Property Management Systems (PMS) and Channel Managers to manage bookings in real-time, including creating, modifying, and canceling reservations. Beyond communication and bookings, it also coordinates tasks like housekeeping and maintenance for staff, tracking their completion. This AI solution aims to significantly reduce operational costs by providing an AI employee at a fraction of the cost of human staff.

Scrapling is a powerful and adaptive web scraping framework designed for both single requests and full-scale, concurrent crawls. It features an intelligent parser that learns from website changes, automatically relocating elements when pages update, ensuring data extraction remains robust. The framework includes advanced fetchers capable of bypassing anti-bot systems like Cloudflare Turnstile and offers full browser automation. Scrapling supports multi-session crawls with pause/resume functionality, automatic proxy rotation, and real-time streaming of scraped items. It also integrates AI capabilities through an MCP server for assisted web scraping, optimizing data extraction and reducing token usage for AI models. Built for performance, it boasts high speed, memory efficiency, and battle-tested architecture with extensive test coverage.

The LangChain-Chinese-Getting-Started-Guide is an open-source tutorial designed to help Chinese speakers learn and utilize the powerful LangChain framework. It covers essential concepts such as LLM invocation, prompt management, document loaders, text splitters, vector stores, chains, and agents. The guide provides practical examples, including performing Q&A with OpenAI models, integrating with Serpapi for internet searches, and summarizing long texts. It also addresses common challenges like API token limits and offers solutions using LangChain's features. The tutorial is actively maintained on GitHub, with updates and code examples available for hands-on learning.

Matey AI provides real AI solutions for attorneys, transforming legal operations by accelerating investigations and automating complex reviews with unmatched speed, accuracy, and transparency. The platform allows users to upload all case data, including video, audio, witness statements, emails, and texts, enabling AI to connect facts and find crucial evidence. It helps legal teams rapidly extract valuable insights, find hidden connections, automate processes, build timelines, and prep for trials. Matey AI ensures data security and compliance through enterprise-grade security, including encryption and adherence to recognized standards like ISO 27001. It is designed for seamless integration with existing legal workflows and software, and offers comprehensive support and training from AI specialists. Matey AI is scalable for both small firms and large legal departments, with a specific offering, CrimD™, designed to be affordable for individual criminal defense attorneys.

Shift-AI-models-to-real-world-products is an Open Source repository offering comprehensive guides and references for transitioning AI models from research and development into practical, real-world products and projects. It provides insights into various stages of AI product development, including machine learning project processes, team composition, product manager challenges, pre-sales solutions, data management, model training and deployment, and MLOps. The resource is particularly valuable for those looking to understand the engineering and productization aspects of AI, especially within B/G (Business/Government) markets and computer vision applications. It aims to bridge the gap between theoretical AI models and their successful implementation in commercial or governmental settings.