AI Agents & Automation

Brevitas is an open-source PyTorch library designed for neural network quantization, offering support for both post-training quantization (PTQ) and quantization-aware training (QAT). This tool enables developers and researchers to optimize and compress neural networks, making them more efficient for deployment on various hardware platforms. It provides quantized implementations of common PyTorch layers, such as QuantConv1d, QuantConv2d, and QuantLSTM, allowing individual tuning of quantization settings for different tensors. Brevitas is a research project from Xilinx, providing examples for ImageNet classification models to demonstrate PTQ under various configurations.

Luru's AI SDR acts as an automated sales development representative, designed to streamline and scale sales outreach efforts across inbound, outbound, and unbound channels. It leverages AI to identify ideal customer profiles, enrich prospect information with intent data, and craft hyper-personalized, human-quality messages. The platform supports multi-channel outreach via email, LinkedIn, and phone calls, ensuring messages reach prospects where they are most likely to respond. Luru also features AI calling agents that qualify leads and book meetings, and a self-learning model that continuously optimizes campaigns based on performance and human feedback. It integrates seamlessly with existing CRMs to manage leads effectively.

DrugCards offers AI-powered solutions for comprehensive literature screening and pharmacovigilance, streamlining drug safety routines for pharmaceutical companies, Contract Research Organizations (CROs), and freelancers. The platform automates literature monitoring, regulatory intelligence, and adverse event management, significantly reducing the time spent on manual tasks. It supports over 100 languages and covers medical journals from 121+ countries, continuously monitoring more than 2200 local journals. DrugCards aims to improve compliance, enhance traceability, and provide accurate, complete, and holistic data. It is designed to be scalable, multi-language, multi-region, and cost-effective, offering up to 60% time savings compared to human-only approaches.

Yatai (屋台, food cart) is a Kubernetes deployment operator specifically designed for BentoML, enabling model deployment at scale. It allows DevOps teams to seamlessly integrate BentoML services into their existing GitOps workflows, facilitating the deployment and scaling of machine learning models on any Kubernetes cluster. Yatai is cloud-native and DevOps-friendly, utilizing a Kubernetes-native workflow with its BentoDeployment CRD (Custom Resource Definition). This approach makes it easy to fit BentoML-powered services into existing operational pipelines. The tool provides documentation for installation and offers a quick tour to try it locally in a minikube cluster, along with components for image building and deployment.

MM-EUREKA is a cutting-edge project exploring the frontiers of multimodal reasoning through rule-based reinforcement learning. It introduces powerful models such as MM-Eureka-Qwen-7B and MM-Eureka-Qwen-32B, which significantly advance performance in multidisciplinary K12 and mathematical reasoning tasks. The project has iterated on model architecture, algorithms, and data, moving from InternVL to the more robust Qwen2.5-VL base models. Key improvements include enhanced online filtering, adaptive online rollout adjustment (ADORA), and novel RL algorithms like Clipped Policy Gradient Optimization with Policy Drift (CPGD). MM-EUREKA also open-sources a comprehensive pipeline, including self-collected MMK12 datasets, to foster further research and development in multimodal AI.

ReMind is an AI memory agent designed to capture, index, and summarize your digital activities directly on your device. It records screenshots, audio, and other digital interactions, then transcribes text from captured screenshots. Utilizing advanced AI models and vector databases, ReMind indexes this information, provides detailed summaries of daily activities, and allows users to interact with the application via a chat interface to query their digital history. This tool is ideal for individuals seeking to effortlessly manage and recall their digital footprint, offering a personalized and local artificial memory solution.

The NVIDIA Data Loading Library (DALI) is a GPU-accelerated library designed to optimize data loading and pre-processing for deep learning applications. It offers a collection of highly optimized building blocks and an efficient execution engine, specifically tailored for processing image, video, and audio data. DALI addresses the common bottleneck of CPU-bound data pipelines by offloading these tasks to the GPU, significantly enhancing performance and scalability for training and inference. It supports various data formats and is portable across popular deep learning frameworks like TensorFlow, PyTorch, and PaddlePaddle. Key features include prefetching, parallel execution, batch processing, and extensibility for custom operators, making it a versatile solution for accelerating complex deep learning workflows.

Doc Scan - PDF Scanner is a comprehensive mobile application designed for iPhone and iPad, transforming these devices into versatile document scanners and PDF editors. Users can efficiently scan single or multi-page documents using their device's camera, with AI Recognition technology for auto-detection. The app offers robust editing features, allowing users to annotate, fill forms, add text and pictures, and apply digital signatures. It also includes OCR technology to extract text from scans, convert images to PDF, and merge multiple pages into a single document. Doc Scan supports various sharing options, including email, FAX, SMB, and cloud services like Dropbox and Google Drive, ensuring documents can be easily managed and distributed.

pyannote-audio is an open-source Python toolkit designed for speaker diarization, a process that identifies 'who spoke when' in an audio recording. Built on the PyTorch machine learning framework, it offers robust capabilities for speech activity detection, speaker change detection, and speaker embedding. The toolkit includes pretrained models and pipelines, allowing users to quickly implement and experiment with audio analysis tasks. Furthermore, it supports fine-tuning of these models, enabling users to optimize performance on their specific custom datasets. This makes pyannote-audio a versatile tool for researchers and developers working with audio data.

XVERSE-13B is a multilingual large language model developed by XVERSE Technology Inc. It features a Decoder-only Transformer network structure with an 8K context length, which is extended to 256K in the XVERSE-13B-256K version for handling extensive input content like literature summaries and report analysis. The model was trained on 3.2 trillion tokens across over 40 languages, with a focus on Chinese and English performance. It utilizes a 100,534-token BPE-based tokenizer that supports multiple languages without requiring additional vocabulary expansion. The project also highlights an efficient training framework with high peak computing power utilization. Quantized models (GGUF, GPTQ) are available for inference on MacOS, Linux, and Windows systems.

Self Learning Solutions (SLS) is an advanced AI platform designed to automate complex business processes. It leverages intelligent AI agents and real-time data processing capabilities to enhance operational efficiency and reduce costs. The platform offers a user-friendly low-code/no-code interface, enabling business teams to build and customize workflows without extensive coding knowledge. SLS supports a wide range of applications, including risk and anti-fraud systems, debt collection, loan underwriting, and sales and onboarding processes. Its self-learning capabilities ensure continuous improvement and adaptation, making it suitable for industries like FinTech, manufacturing, and e-commerce.

antigravity-agent is an open-source tool designed for the effortless management of multiple Antigravity accounts. It allows users to quickly switch between accounts with a single click, eliminating the need for repetitive logins. The software automatically identifies and saves current account data, and offers secure backup functionality through password-encrypted export of account configurations, facilitating cross-device migration. A VSCode extension is also available, enabling users to switch accounts and view model quotas directly within their editor. The tool emphasizes security, distributing only through official GitHub Releases to protect sensitive account information.

The website cue.ai is currently a marketplace listing for the domain name "Cue.ai". It is being offered for sale through Snagged Marketplace, with a minimum offer of $100,000. The description suggests the domain is ideal for AI assistants, workflow automation, communication tools, and productivity platforms, highlighting its short, intuitive name that signals prompts, timing, and intelligent responses across various industries. The site provides a form for serious inquiries to make an offer and join a newsletter about domain names.

Twin is an AI company builder that empowers users to create autonomous AI agents using natural language, eliminating the need for coding. These agents can connect to any API, automate browser actions like a human, and run on a schedule or trigger from webhooks, emails, or messages. The platform allows users to brainstorm and refine ideas into working agents, creating integrations in real-time. It's designed for individuals and businesses looking to automate workflows, find clients, manage jobs, and streamline various operational tasks, offering a no-code solution for agent deployment and community sharing.

OpenML is a collaborative online machine learning platform designed to facilitate the sharing and organization of data, machine learning algorithms, and experimental results. It aims to create a frictionless, networked ecosystem where scientists and practitioners can easily integrate their existing processes and tools to collaborate globally. The platform provides significant benefits for science by enabling rapid building upon others' results, answering complex questions quickly through prior experiments, and making larger studies feasible. For scientists, it saves time on routine duties, compares new experiments to the state of the art, and offers potential for new discoveries and publications. OpenML also serves as a valuable learning environment for students and citizen scientists, allowing them to explore state-of-the-art methods and contribute their own work.

PhishGuard Scaffold offers a unified framework for detecting and controlling phishing attacks on social media platforms. Leveraging LLaMA-based modeling, it provides deep semantic understanding and adversarial robustness to identify phishing attempts. The tool also incorporates advanced graph-based intervention strategies to control the propagation of detected phishing content. Key features include LLaMA-2-7B integration, multi-layer semantic projection, LoRA/PEFT support for efficient fine-tuning, and robust preprocessing. It also focuses on adversarial robustness through semantic perturbations and KL divergence training. For propagation control, it builds automated social networks, simulates diffusion with an Independent Cascade Model, and offers targeted intervention using greedy optimization and influence-aware selection. The framework is designed for production readiness with mixed precision training, gradient checkpointing, and comprehensive MLOps integration via MLflow and Ray Tune.

Swooped is an AI-powered job search platform designed to help job seekers land their dream roles faster. It offers a suite of AI tools including an AI Resume Builder that generates perfectly formatted and keyword-optimized resumes, and an AI Cover Letter Generator that creates compelling, job-specific cover letters. The platform also features ATS Optimization to ensure resumes pass digital gatekeepers, a Free Resume Grader for actionable feedback, and AI Interview Practice. Swooped streamlines the application process with One-Click Applications and a Job Application Tracker, and even includes a Networking AI to connect users with industry insiders. Trusted by over a million job seekers, Swooped aims to accelerate job searches, increase interview rates, and achieve high ATS pass rates.

TDK AIsight is a core technology platform developed by TDK that focuses on building the fundamental technologies for generative AI glasses. It enables context-aware vision, memory, and low-power on-device intelligence for next-generation smart glasses. The platform integrates core hardware components and a modular subsystem architecture for performance, flexibility, and scalability. It employs a multi-modal feedback architecture, distributing system output across visual, audio, haptic, and display subsystems. The intelligence behind AIsight, eyeGI™ and eyeGenI™, delivers low-power, real-time perception and contextual understanding, supporting a wide range of context-aware experiences for work, learning, travel, and shopping.

Aira Security offers a crucial enforcement layer for AI agents, designed to prevent malicious or accidental actions that could lead to data leaks or regulatory violations. This runtime security solution monitors agent behavior in real time, ensuring that all actions align with predefined security policies. By proactively blocking unsafe operations, Aira Security helps enterprises deploy AI agents confidently, maintaining compliance and data integrity without compromising performance. It acts as a vital safeguard, providing a robust security framework for the increasingly complex landscape of AI-driven operations.

mader is an open-source trajectory planner specifically designed for use in multi-agent and dynamic environments. It has been accepted for publication in the IEEE Transactions on Robotics (T-RO), highlighting its academic rigor and practical applicability. The tool facilitates trajectory planning for robotic systems, including single-agent and multi-agent simulations, with features like obstacle avoidance and dynamic environment handling. Users can set up and run simulations using ROS, with options for both Docker and non-Docker installations. It supports backend optimizers like Gurobi and NLOPT, providing flexibility for different computational needs. The project is hosted on GitHub by MIT-ACL, making it accessible for researchers and developers in the robotics community.

AviaVox provides world-leading automated passenger announcement systems specifically designed for airports and airlines. Utilizing advanced AI, the system delivers crystal-clear, grammatically correct announcements in over 40 native languages and dialects. Beyond just voice output, AviaVox solutions are engineered to improve passenger flow, enhance regulatory compliance, and deliver significant operational and financial benefits. This includes reducing passenger and employee stress, increasing on-time departures, lowering operating costs, and supporting 'silent airport' policies. The system handles both dynamic, flight-related announcements and static safety messages, catering to terminal-wide needs for airports and local gate announcements for airlines.

Dilseheal is an AI-powered hospital recommendation system designed to connect patients with the most suitable healthcare providers. It leverages artificial intelligence to recommend hospitals based on various factors including medical condition, financial status, valid user reviews, and hospital background checks. The platform aims to streamline the process of finding the right treatment by offering information about hospitals near the user. Beyond recommendations, Dilseheal allows users to track health issues through vaccination and monitoring records, and facilitates the creation, editing, and sharing of medical records for controlled collaboration between doctors. It emphasizes verified hospitals, expert consultation, 24/7 support, and a patient community.

sherpa is an open-source speech-to-text inference framework built with PyTorch, designed for deploying pre-trained models to transcribe speech. It specializes in end-to-end models, particularly transducer- and CTC-based architectures, offering high-performance speech recognition capabilities. Developers can integrate sherpa into their projects using either C++ or Python APIs, making it versatile for various development environments. The framework is ideal for those looking to implement custom speech-to-text solutions, leverage advanced AI models for audio processing, or contribute to the open-source AI community. Its focus on inference means it's optimized for efficient deployment of trained models.

Penny App is an AI-powered platform designed to transform social selling for direct sellers and network marketers. It provides an intelligent mobile assistant that streamlines daily operations, automates follow-ups, and centralizes contact management to significantly boost productivity. Users benefit from AI-driven daily action lists, high-performance script generation, and customized learning modules tailored to their business needs. Penny helps sellers with new business growth, exceptional customer care, and repeat business by building repeatable behaviors. The platform also offers solutions for corporations, including revenue acceleration programs, digital transformation, and business intelligence, ensuring global deployments and continuous success.