AI Agents & Automation

ChatPuma is an AI-powered no-code chatbot builder platform designed to transform customer service by providing personalized interactions built on your business data. It enables businesses to save up to 90% on manual customer support while boosting engagement. Users can create and deploy chatbots to their website in minutes, without any coding skills. The platform allows training chatbots on various data sources like web pages and documents, offering 24/7 automated support, reduced response times, and personalized customer experiences. ChatPuma also helps reduce operational costs, scale support effortlessly, and provides valuable insights from customer data analytics. It supports over 100 languages and offers brand customization.

MADRL is a repository offering code for multi-agent deep reinforcement learning (MADRL), providing implementations of several multi-agent reinforcement learning environments. These include Pursuit Evasion, Waterworld, Multi-Agent Walker, and Multi-Ant. The package requires OpenAI Gym and a forked version of rllab (the multiagent branch) for its functionality. It is designed for researchers and developers in the field of multi-agent reinforcement learning, allowing them to set up and run simulations with curriculum learning. The project also provides details on policy definitions and includes a citation for its accompanied paper, making it a valuable resource for academic and practical applications in MADRL.

MaxText is a high-performance, highly scalable, open-source library for Large Language Models (LLMs), implemented in pure Python/JAX. It is designed to run efficiently on Google Cloud TPUs and GPUs, supporting both pre-training and scalable post-training with techniques like Supervised Fine-Tuning (SFT) and Reinforcement Learning (GRPO, GSPO). MaxText achieves high Model FLOPs Utilization (MFU) and tokens/second across various cluster sizes, leveraging the power of JAX and the XLA compiler. It offers a library of high-performance models including Gemma, Llama, DeepSeek, Qwen, and Mistral, and serves as a launching point for ambitious LLM projects in research and production. Users can experiment with MaxText out of the box or fork and modify it to meet specific needs, with support for multi-modal training.

Factacy.ai specializes in providing advanced AI solutions, focusing on Agentic AI and AI as a Service to drive intelligent, autonomous decision-making for businesses. Their tailored AI software is designed to transform industries such as healthcare, finance, and retail by offering personalized insights and innovative solutions. The platform aims to empower businesses to scale smarter, automate processes, and make data-driven decisions, ultimately converting complexity into opportunities for sustainable growth. Factacy.ai positions itself as a partner for businesses looking to leverage cutting-edge AI technology to enhance operational efficiency and strategic outcomes.

mllm is a fast and lightweight multimodal LLM inference engine specifically designed for mobile and edge devices. It allows developers to deploy and run large language models (LLMs) on hardware with limited resources, supporting both text and image processing. The tool features a Pythonic eager execution API for rapid model development, unified hardware support across Arm CPU, OpenCL GPU, and QNN NPU, and advanced optimizations like quantization, pruning, and speculative execution. It integrates seamlessly with popular community frameworks' checkpoints, converting PyTorch and SafeTensors models into its optimized format. mllm also provides a deployment toolkit including an SDK and CLI inference tool, making it a central hub for AI inference on mobile platforms.

Nestia provides a comprehensive suite of helper libraries designed to enhance NestJS development, focusing on performance, type safety, and AI integration. Key features include `@nestia/core` for super-fast and easy decorators, `@nestia/sdk` for advanced Swagger generation, SDK library generation for clients, and a mockup simulator. It also offers automatic E2E test functions generation and a dedicated E2E test program. For AI development, Nestia integrates `@agentica`, an agentic AI library specialized in LLM function calling, and `@autobe`, a vibe coding agent for generating NestJS applications. The platform boasts significant performance improvements, with runtime validation being 20,000x faster than class-validator and JSON serialization 200x faster than class-transformer. Nestia aims to streamline API development, testing, and AI chatbot creation for developers.

Zendar revolutionizes autonomous systems with its high-resolution distributed aperture radar technology, designed to enhance perception for real-world robotics. By leveraging early fusion of radio frequency spectrum and vision, Zendar enables safer and more reliable autonomous systems across various industries, including automotive, logistics, agriculture, and industrial applications. Its RF perception models ensure failsafe operation in all weather and lighting conditions, offering accurate and sensitive detection of micromotion. The technology efficiently detects, classifies, and tracks objects even through occlusions, requiring lightweight compute for scalable deployment. Zendar offers development kits including sensors, compute hardware, and foundational models to empower the next generation of intelligent robots.

GoldRock AI offers end-to-end custom B2B AI solutions and mass worker automation services, aiming to automate over 435,000 annual labor hours with significant cost reductions and faster delivery. They specialize in developing custom AI applications, tools, websites, and MVPs for businesses. The platform also features specific products like GoldRock Health, a medical bill advocate service, and Ruby Voice Shortcuts, an enhanced voice command system for iOS. GoldRock AI integrates multiple AI models into a single chat interface, providing comprehensive AI solutions for real estate, sales, healthcare, insurance, and general automation needs.

Bizagi is a comprehensive platform designed for business orchestration, leveraging AI to unify assets, people, and systems. It offers robust process automation capabilities, allowing businesses to analyze, optimize, and automate processes with end-to-end visibility. The platform supports the creation of low-code applications, empowering users to build enterprise apps with integrated AI and governance features. Key functionalities include AI Agents, AI Workers, and an AI Assistant, all designed to deliver real business results responsibly. Bizagi emphasizes secure AI adoption with multi-level governance, enterprise-class security, and privacy, making it suitable for organizations looking to transform operations and improve decision-making through AI-powered automation.

SMILE (Statistical Machine Intelligence and Learning Engine) is a robust and comprehensive machine learning framework implemented in Java, with convenient APIs available for Scala and Kotlin developers. It offers a wide array of algorithms and tools for statistical machine intelligence and learning applications, making it suitable for various data science tasks. The framework is designed for performance and flexibility, supporting Java 8 and newer versions. It empowers developers to build, train, and deploy machine learning models efficiently, catering to both research and production environments. SMILE's extensive feature set covers areas such as classification, regression, clustering, association rule mining, and more, providing a solid foundation for advanced analytical projects.

slimevolleygym is an OpenAI Gym environment designed for testing single and multi-agent reinforcement learning algorithms through a simple Slime Volleyball game. This environment is lightweight, requiring only gym and numpy as dependencies, making it less prone to breaking and easy to integrate. It features a baseline 120-parameter neural network opponent, which can be replaced for multi-agent or self-play scenarios. The environment runs efficiently, achieving around 12.5K timesteps per second on state-space observations, facilitating faster iteration in experiments. It supports both state-space and pixel observations, with the latter mimicking Atari Learning Environment setups, and includes a tutorial for various training methods. The environment is particularly useful for educational purposes and for exploring advanced RL methods like self-play and continual learning.

ShopGuru AI is an online shopping assistant designed to simplify product research. This AI-powered tool allows users to describe any product they are looking for, and it will then research, compare, and rank the best options available across multiple major retailers, including Amazon, Best Buy, Walmart, and Target. The AI analyzes reviews, specifications, and pricing to provide a comprehensive ranking based on relevance, value, and overall quality. Users benefit from transparent scoring, which details why each product ranks as it does, including match scores, value ratings, and detailed reasoning, saving hours of manual product research.

similarities is a comprehensive, open-source toolkit designed for advanced similarity calculation and semantic search. Built with Python 3, it offers out-of-the-box functionality for various tasks, including text-to-text, text-to-image, and image-to-image searches, capable of handling billion-level datasets. The toolkit features semantic matching models based on text2vec for text similarity and search, supporting multiple SentenceBERT-like pre-trained models across various languages. It also includes literal matching models like Word2Vec and BM25. For image and cross-modal similarity, similarities leverages CLIP models, enabling image-to-image, text-to-image, and vector-to-image searches with support for Chinese-CLIP models and GPU acceleration. It provides command-line tools for vector extraction, index building, batch retrieval, and service deployment, making it a versatile solution for developers and data scientists.

SimpleTuner is a comprehensive, open-source fine-tuning kit designed for image, video, and audio diffusion models. It prioritizes simplicity and code understandability, making it an ideal academic exercise and collaborative development platform. The tool features a user-friendly web UI, multi-modal and multi-GPU training capabilities, and advanced caching for faster training. It supports various model architectures, including Stable Diffusion XL, Stable Diffusion 3, and Flux, with integrations for DeepSpeed and FSDP2 for memory optimization. SimpleTuner also includes enterprise-grade features like worker orchestration, SSO integration, role-based access control, and a job queue with priorities, all available for free.

superdesign, hosted on GitHub, provides a comprehensive platform for software development, offering solutions for individuals and organizations. It integrates AI code creation with GitHub Copilot, allowing developers to write better code. The platform supports automated workflows through GitHub Actions, instant development environments with Codespaces, and robust project management with Issues & Projects. For security, superdesign includes GitHub Advanced Security to find and fix vulnerabilities, along with features for code security and secret protection. It caters to various company sizes and use cases, from open-source projects to enterprise-level application modernization and DevSecOps, ensuring a secure and efficient development lifecycle.

Dreambooth-Stable-Diffusion is an open-source implementation of Dreambooth, utilizing Textual Inversion for Stable Diffusion models. Developed by Joe Penna, it's specifically designed for training custom faces, objects, and artistic styles. The tool is particularly useful for filmmakers, concept artists, and comic book designers who need to generate specific visual concepts. It supports running on various platforms including cloud computing services like RunPod and Vast.AI, as well as local PCs (Windows/Ubuntu) with detailed setup instructions provided. The project emphasizes ethical use, encouraging users to train their own likenesses or styles rather than infringing on others' work.

SqueezeLLM is a post-training quantization framework designed to optimize the serving of large language models (LLMs) through a novel Dense-and-Sparse Quantization method. This approach addresses the significant memory requirements of LLMs by splitting weight matrices into a dense component, which can be heavily quantized without performance loss, and a sparse component that preserves sensitive outlier parts. This allows for serving larger models with a smaller memory footprint, maintaining the same latency, and achieving higher accuracy and quality compared to baseline models. For instance, SqueezeLLM's variant of Vicuna models can operate within 6 GB of memory, surpassing FP16 baseline models in MMLU accuracy despite the latter requiring twice the memory. The framework supports various LLMs including LLaMA, LLaMA-2, Mistral, Vicuna, XGen, and OPT, with options for 3-bit and 4-bit quantization and different sparsity levels.

Stable-Diffusion-WebUI-TensorRT is a TensorRT extension designed to significantly boost the performance of Stable Diffusion Web UI on NVIDIA RTX GPUs. This tool is compatible with a range of Stable Diffusion models, including 1.5, 2.1, SDXL, SDXL Turbo, and LCM, ensuring broad applicability for users. To leverage its capabilities, users must install the extension and generate optimized engines, following the detailed instructions provided. This optimization is crucial for achieving faster inference times and a smoother workflow when generating images, making it an essential addition for developers and graphic designers working with Stable Diffusion on NVIDIA hardware.

Eranova AI offers a platform for enterprise AI agents designed to automate back-office operations across various industries such as logistics, manufacturing, finance, and operations. The platform provides configurable AI agents that integrate with existing enterprise systems like ERP, TMS, OMS, and CRM. Key features include AI model redundancy, supporting leading models like OpenAI, Anthropic, Google Gemini, and XAI, as well as private models. Eranova emphasizes enterprise-grade security with data isolation per tenant and models locked down to prevent training on user data. It also offers governed controls with audit trails, ensuring compliance and transparency in automated workflows. The platform aims to significantly reduce manual overhead and process large volumes of agentic jobs for Fortune 500 companies.

tanuki.py is a tool designed to assist developers in building and optimizing applications powered by Large Language Models (LLMs). Its core focus is on enhancing the efficiency and cost-effectiveness of LLM-based applications. The tool incorporates prompt engineering techniques to refine LLM interactions and improve output quality. Additionally, it supports test-driven alignment, a methodology that ensures the LLM's behavior aligns with desired outcomes through systematic testing. This approach helps developers to iteratively improve the performance and reliability of their LLM applications, making them more robust and production-ready.

TensorLayerX is a versatile multi-backend AI framework designed for deep learning and reinforcement learning. It supports popular frameworks like TensorFlow, PyTorch, MindSpore, PaddlePaddle, OneFlow, and Jittor, enabling users to run their models on diverse hardware such as Nvidia-GPU, Huawei-Ascend, and Cambricon. Key features include compatibility across various AI chips and platforms, a Model Zoo offering classic and state-of-the-art models for CV, NLP, and RL, and deployment support via ONNX protocol for model export, import, and deployment. Developed by researchers from leading universities, TensorLayerX simplifies the process of defining models and switching between backends with minimal code changes.

TextBox 2.0 is an open-source text generation library built with Python and PyTorch, designed to provide a unified and standardized pipeline for applying pre-trained language models (PLMs) to various text generation tasks. It supports 13 common text generation tasks, including translation, story generation, and style transfer, across 83 widely-used datasets. The library integrates 47 pre-trained language models/modules, covering categories such as general, translation, Chinese, dialogue, controllable, distilled, prompting, and lightweight models. TextBox 2.0 also offers four pre-training objectives and four efficient training strategies, including distributed data parallel and hyper-parameter optimization, making it a comprehensive tool for researchers and developers in natural language processing.

Transkribieren is an all-in-one AI workspace designed to simplify transcription workflows. It offers fast and accurate audio-to-text and video-to-text conversion, supporting various formats like MP3, WAV, MP4, and MOV. The platform boasts support for over 99 languages with automatic detection and includes speaker detection to identify and label different speakers. Users can also paste YouTube URLs to get transcripts and generate subtitles in SRT or VTT formats. Beyond transcription, Transkribieren provides AI-generated summaries, text chat, and image creation capabilities. It emphasizes security with zero data retention, GDPR/CCPA compliance, SOC 2 Type 2 certification, and robust data protection measures.

TuriX-CUA is a computer-use agent designed to empower AI models to interact directly with a desktop environment, facilitating the automation of various tasks and workflows. This tool allows users to leverage artificial intelligence for seamless computer interaction, enhancing productivity and efficiency. It ships with a state-of-the-art computer-use agent, providing advanced capabilities for AI-driven desktop operations. The platform aims to simplify complex processes by enabling AI to execute commands and manage applications, making it an invaluable asset for developers and organizations looking to integrate AI into their operational infrastructure.