AI Agents & Automation

LMDrive is an open-source, closed-loop, end-to-end autonomous driving framework that leverages large language models (LLMs). It is designed to interact with dynamic environments by processing multi-modal and multi-view sensor data, alongside natural language instructions. This framework facilitates the development and research of advanced autonomous driving systems. Key features include vision encoder pre-training to generate visual tokens from sensor inputs and an instruction finetuning stage to align language instructions with control signals. The project provides a comprehensive dataset collected in the CARLA simulator, including sensor data, navigation instructions, and human notice instructions, making it a robust platform for researchers and developers in the autonomous driving domain.

mistral-inference is an official open-source inference library developed by Mistral AI, designed to provide minimal code for running their large language models. This library supports a wide range of Mistral models, including Mistral 7B, Mixtral 8x7B, Mixtral 8x22B, Codestral 22B, Codestral Mamba 7B, and Mathstral 7B, as well as newer models like Mistral Large 2 and Mistral Small 3.1. It facilitates local installation via PyPI or direct cloning from GitHub, with model weights available for direct download or from the Hugging Face Hub. Users can interact with these models through a command-line interface for demos and interactive chat, supporting both single and multi-GPU setups. The library also provides Python APIs for instruction following, multimodal instruction following, and function calling, making it a versatile tool for developers working with Mistral's AI models.

Barbara is an Edge AI platform designed for industrial companies to deploy, run, and monitor Edge Applications and AI models directly on-site. It offers a simplified approach to managing industrial infrastructure compared to traditional cloud solutions. The platform provides container orchestration, industrial connectors for various assets, and ecosystem integration, allowing users to deploy Docker-based apps and integrate with existing development environments. For AI/ML developers, Barbara facilitates model deployment to Edge Nodes and offers an Apps Marketplace for off-the-shelf tools. Edge Infrastructure Managers benefit from effortless device lifecycle management, professional-grade network connectivity, and zero-touch provisioning for faster deployments. The platform emphasizes cybersecurity, IT/OT convergence, and MLOps capabilities to optimize and package trained models for efficient inference.

Elevatus is an AI hiring operating system designed for enterprise-scale recruitment, offering autonomous recruiting from requisition to onboarding without requiring any coding. The platform provides solutions like EVA-REC for streamlining recruitment, EVA-SSESS for pinpointing top performers through assessments, and EVA-BOARD for initiating onboarding before day one. It caters to various industries including education, financial services, and government, and is built for speed, scale, and complexity. Elevatus ensures full compliance, offers deployment in under one week, and integrates seamlessly with over 2000 tools like LinkedIn, Zoom, Slack, and SAP. It also features built-in intelligence for every stage of recruitment, supporting diverse hiring, first-class candidate experiences, dynamic analytical reports, and multilingual support.

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.

Osprey is a cutting-edge computer vision tool that enhances multimodal large language models (MLLMs) by incorporating pixel-wise mask regions into language instructions. This innovative approach enables fine-grained visual understanding, allowing Osprey to generate detailed semantic descriptions, including both short and elaborate explanations, based on specific input mask regions. It seamlessly integrates with Segment Anything Model (SAM) in various modes like point-prompt, box-prompt, and segmentation everything, to extract and describe semantics associated with particular parts or objects within an image. Osprey is built upon the LLaVA-v1.5 codebase and is designed for researchers and developers working on advanced visual instruction tuning and pixel-level image analysis.

PyTorch-BayesianCNN provides an implementation of Bayesian Convolutional Neural Networks (CNNs) with variational inference, specifically utilizing Bayes by Backprop, within the PyTorch framework. This tool allows researchers and developers to build CNNs that can infer intractable posterior probability distributions over weights, offering a significant advantage over traditional frequentist approaches by providing uncertainty estimations. It includes two types of Bayesian layer implementations: BBB (Bayes by Backprop) and BBB_LRT (Bayes by Backprop with Local Reparametrization Trick), which enhances sampling efficiency. The repository supports standard datasets like MNIST, CIFAR10, and CIFAR100, and includes implementations of common models such as AlexNet and LeNet, making it a valuable resource for experimenting with Bayesian deep learning and understanding model uncertainty.

pytorch_active_learning is an open-source PyTorch library designed for active learning, accompanying the "Human-in-the-Loop Machine Learning" book. It offers a range of active learning methods, including Least Confidence, Margin of Confidence, Ratio of Confidence, and Entropy sampling. The library also supports more advanced techniques like Model-based Outlier sampling, Cluster-based sampling, and various forms of Active Transfer Learning. It is suitable for researchers and practitioners looking to experiment with and apply active learning strategies in computer vision and natural language processing, with a focus on real-world diversity to avoid bias. The code is stand-alone and can be easily integrated with existing PyTorch installations.

Self-Driving-Car-in-Video-Games is an open-source project featuring a supervised deep neural network designed to learn autonomous driving within video games, specifically Grand Theft Auto V. The model, named T.E.D.D. 1104, is trained using extensive human-labeled data, recording gameplay and key inputs to teach it how to navigate various vehicles under different weather conditions. It approaches the task as a classification problem, taking a sequence of five images as input and predicting the correct keyboard or Xbox controller inputs. The project provides pretrained models of varying sizes (XXL, M, S) and includes all necessary files for data generation, training, and real-time inference, primarily supporting Windows 10/11 for gameplay interaction.

FocusFr is a free AI-powered cover letter generator specifically designed for freshers, students, and job seekers. It enables users to create high-impact, personalized cover letters in minutes, significantly increasing their chances of landing interviews. The platform focuses on helping individuals at the early stages of their careers, including those applying for internships. By leveraging AI, FocusFr streamlines the application process, allowing users to quickly generate professional pitches tailored to specific job opportunities. It's an ideal tool for anyone looking to enhance their job application materials efficiently and effectively.

TensorFlow Federated (TFF) is an open-source framework designed for machine learning and other computations on decentralized data. It specifically supports Federated Learning (FL), an approach where a shared global model is trained across many participating clients while their sensitive training data remains local. This framework enables developers to utilize included federated learning algorithms with their existing TensorFlow models and data, or to experiment with novel algorithms. TFF provides both a high-level Federated Learning (FL) API for applying federated training and evaluation, and a lower-level Federated Core (FC) API for expressing new federated algorithms. It includes a single-machine simulation runtime for experiments, making it suitable for researchers and developers exploring privacy-preserving machine learning.

Thesis is an AI-native platform designed for data science and machine learning, offering an environment where researchers can build and deploy frontier models. The platform allows ML research scientists to run experiments and train models autonomously and at scale within its datacenters. Key features include an intuitive interface for managing datasets, experiments, and models, as well as tools for exploratory data analysis (EDA) and lineage tracking for model development. Thesis aims to accelerate AI R&D, making it easier for data scientists to turn curiosity into consequential discoveries. It offers both a free Spark plan and a 'Pay as you go Ultra' option for production workloads.

Veles is a distributed platform designed for rapid deep learning application development, released under the Apache 2.0 license. It comprises several key components, including the core Veles platform, the Znicz Plugin which serves as a neural network engine, and Mastodon, a bridge facilitating integration between Veles and Java-based systems like Hadoop. Additionally, it features a SoundFeatureExtraction library for audio processing. This platform is ideal for developers and researchers looking to build and deploy deep learning applications in a distributed environment, offering tools for both model development and data processing.

TransmogrifAI (pronounced trăns-mŏgˈrə-fī) is an open-source AutoML library written in Scala, designed to run on Apache Spark. Developed by Salesforce, it focuses on enhancing machine learning developer productivity by automating various stages of the ML workflow, from feature engineering and validation to model selection. The library enforces compile-time type-safety, modularity, and reusability, enabling the creation of robust machine learning applications in a fraction of the time compared to traditional hand-tuned methods. It supports building models with minimal machine learning expertise, making advanced ML accessible to a broader range of developers. TransmogrifAI is particularly useful for structured data and offers flexibility for users who require more control over their ML pipelines.

TPVFormer is an academic project offering a Tri-Perspective View (TPV) representation for vision-based 3D semantic occupancy prediction, serving as an alternative to Tesla's Occupancy Network for autonomous driving research. It addresses the limitations of traditional bird's-eye-view (BEV) representations by incorporating two additional perpendicular planes, allowing for a more fine-grained description of 3D scenes. The tool features a transformer-based TPV encoder (TPVFormer) to effectively obtain TPV features by aggregating image features. It demonstrates that camera inputs alone can achieve performance comparable to LiDAR-based methods on LiDAR segmentation tasks. The project also includes resources for semantic scene completion and comparisons with Tesla's Occupancy Network.

Tetris-deep-Q-learning-pytorch is an open-source Python project that demonstrates the application of Deep Q-learning for training an AI agent to play the classic game Tetris. Developed with PyTorch, this tool serves as a foundational example of reinforcement learning in action. Users can leverage the provided source code to train their own Tetris-playing models from scratch or test pre-trained models. The project includes all necessary scripts for training and testing, making it accessible for those interested in understanding and experimenting with AI agents and deep learning techniques in a practical gaming context. It's an excellent resource for students and developers exploring the basics of reinforcement learning.

Aracor is an AI-native platform designed to perfect dealmaking by providing a secure, connected environment for documents, decisions, and stakeholders. It ensures information is verified, structured, and continuously in sync for M&A, legal, and investment teams. Key features include real-time insights, automated term sheet verification, and expert workflows for due diligence. The platform keeps deals current by automatically syncing changes across documents, tracing every finding to its source, and maintaining alignment among legal, finance, and deal teams. Built for confidential transactions, Aracor offers zero data retention, isolated environments, and legal-grade security, making it ideal for investment funds, in-house legal, corporate development, and law firms.

Nlprule is a fast, low-resource Natural Language Processing and Text Correction library written in Rust. It implements a rule- and lookup-based approach, leveraging resources from LanguageTool for its NLP tasks. Key features include rule-based grammatical error correction with thousands of rules, a comprehensive text processing pipeline covering sentence segmentation, part-of-speech tagging, lemmatization, chunking, and disambiguation. The library supports English, German, and Spanish, with spellchecking currently in progress. Nlprule is designed for speed and efficiency, making it suitable for pre/post-processing in more sophisticated AI approaches, background application tasks with low overhead, or client-side execution via WebAssembly.

Recatch.cc automates the inbound sales pipeline by providing tools for lead capture, routing, and direct booking. It features routable forms that can be embedded on websites or shared via links, instantly converting leads into opportunities. The Lead Router allows users to design custom pipelines without code, setting rules to automatically qualify leads so sales teams can focus on engaging with the most promising prospects. Additionally, it offers direct booking with personalized booking pages to triple meeting conversion rates. Upcoming features include lead data enrichment for pre-populating buyer information and real-time data updates, making it a comprehensive solution for B2B sales automation.

Solda.AI offers fully automated sales departments designed for B2C businesses, handling the entire sales cycle through both voice and text communication. The platform scales instantly, allowing businesses to expand their sales operations with a click of a button. It optimizes conversion rates through A/B testing and manages all aspects of communication, including follow-ups, callbacks, and incoming calls. Solda.AI aims to provide a top-performing salesperson capable of speaking any language, as demonstrated by its case studies in credit card sales, SMB outreach, debt collection, and card activation. It can even qualify needs and introduce AI agents.

Complexio offers an intelligence layer designed for enterprise AI, connecting an organization's data, people, and systems into a unified operational view. It builds a live map of how work happens, called the Event Knowledge Graph (EKG), providing real-time insights. The Context Broker links this EKG to existing systems and teams, ensuring all insights and actions are grounded in a shared understanding of operational reality. Users can ask questions in natural language through Stevie and receive answers based on their real operations. Additionally, the Automated Automations Engine (AAE) identifies patterns and orchestrates executable workflows, turning observations into automated actions with traceability and control.

WeDLM is an open-source diffusion language model developed by Tencent, designed for high-speed inference. It uniquely reconciles diffusion language models with standard causal attention, enabling native KV cache compatibility with technologies like FlashAttention and PagedAttention. This approach allows for direct initialization from pre-trained autoregressive models such as Qwen2.5 and Qwen3, delivering significant real speedups compared to vLLM-optimized baselines. WeDLM achieves 3-6x speedup on tasks like math reasoning and up to 10x on sequential/counting tasks, while maintaining competitive accuracy. It includes an inference engine, evaluation suite, and a fine-tuning framework, making it a powerful tool for developers and researchers focused on efficient language model deployment.

Interloom Technologies provides an AI-driven platform designed to supercharge back office operations by leveraging AI that learns how businesses actually run. Unlike most automation platforms built for developers, Interloom empowers subject matter experts to design workflows, set governance, and build automations without needing to write code. The platform utilizes a 'context graph' that accumulates knowledge from every case resolved, enriching a living record of decisions and outcomes. AI agents then act on this context to handle tasks like extraction, triage, and follow-ups, ensuring actions are grounded in business-specific knowledge rather than generic data. Interloom integrates with existing tools like SharePoint, Salesforce, SAP, Microsoft Teams, Confluence, Google Workspace, ServiceNow, Jira Service Management, and Slack, reading, writing, and syncing data across the tech stack.

ZeroWork is a powerful no-code automation tool designed to streamline repetitive tasks across various online platforms. It excels in web scraping, allowing users to extract data from websites like Google Maps, LinkedIn, and Amazon, with features for data enrichment, deduplication, and scheduled monitoring. Beyond scraping, ZeroWork facilitates web interactions such as auto-posting comments, sending DMs, filling forms, and integrating AI for content creation and personalized responses. The tool emphasizes anti-bot detection prevention and offers unlimited runtime, API calls, and webhooks, making it a robust solution for automating complex multi-step processes like end-to-end sales jobs. Its visual drag-and-drop interface makes it accessible for non-coders, while also supporting custom JS and API calls for advanced users.