Coding & Development

AIBrix is an open-source initiative designed to provide essential building blocks for constructing scalable GenAI inference infrastructure. It delivers a cloud-native solution optimized for deploying, managing, and scaling large language model (LLM) inference, tailored specifically to enterprise needs. Key features include high-density LoRA management, an LLM Gateway and Routing for efficient traffic direction, and an LLM App-Tailored Autoscaler for dynamic resource scaling. It also offers a Unified AI Runtime, distributed inference capabilities, distributed KV cache for high-capacity reuse, and cost-efficient heterogeneous serving with SLO guarantees. AIBrix further includes GPU hardware failure detection for proactive issue identification.

altermAInd offers governable AI infrastructure and human readiness solutions specifically designed for the world's most regulated industries. The company provides purpose-built platforms that enable enterprises to govern, scale, and industrialize AI effectively. These platforms are engineered to ensure compliance and robust management of AI systems, addressing the unique challenges faced by highly regulated sectors. altermAInd focuses on delivering advanced products and services that are open, cloud-native, scalable, and secure, providing unique value in the AI and technology space. Their solutions help organizations navigate the complexities of AI adoption while maintaining stringent regulatory standards.

Cloudflare AI Cloud offers a comprehensive infrastructure for scaling AI applications, from storing training data to running inference. It allows users to deploy AI agents and applications on Cloudflare's global network, leveraging serverless inference on GPUs for responses under 100 ms worldwide without managing clusters. The platform includes an Agents SDK for building goal-driven agents, Remote MCP servers for secure tool exposure, and AI Gateway for caching, rate-limiting, and observability. It also provides Vectorize for a globally-replicated vector database and R2 object storage for egress-free data storage. Cloudflare AI is designed for developers to build, deploy, and scale AI agents and applications with battle-tested infrastructure.

Synvertas is an AI Gateway designed to streamline AI API management, offering a single endpoint for popular models like ChatGPT, Claude, and Gemini. It significantly reduces AI API costs by answering repeat questions for free, optimizing resource usage. A key feature is its automatic failover capability, ensuring continuous service even during provider outages, which enhances reliability and uptime. The platform is designed for quick setup, claiming to be operational in just 5 minutes, and offers a free starting point, making it accessible for developers looking to improve their AI infrastructure resilience and cost efficiency.

AliTech Solutions provides comprehensive future tech services, focusing on software development for various business applications such as Workflow Management Software and CRM Systems. Their expertise extends to AI/ML development, DevOps, and UI/UX design, ensuring end-to-end custom solutions. They integrate innovative technologies like cloud computing and artificial intelligence to enhance business operations and drive efficiency. AliTech emphasizes user-centric design, creating intuitive interfaces and user-friendly applications that meet and exceed user expectations. They offer customizable solutions tailored to unique organizational needs, with robust support and maintenance services post-implementation.

Hexometer acts as an AI-powered sidekick, continuously monitoring websites and key services around the clock. It specializes in detecting a wide range of issues including downtime, user experience problems, performance bottlenecks, broken pages, and errors. The tool also monitors SEO optimization, security vulnerabilities, and server configuration issues, providing proactive alerts before they impact business. With features like visual, content, and technology monitoring, Hexometer helps users stay informed about any changes on their web pages. It also includes tools for meta tag analysis, domain WHOIS lookup, broken link checking, and page speed scanning, making it a comprehensive solution for website health and growth.

Furl is a continuous remediation platform designed to address the persistent backlog of cybersecurity vulnerabilities that traditional patch management tools often miss. It integrates with existing scanners like Qualys, Tenable, and Rapid7 to identify findings, then autonomously investigates each issue, generates custom fixes tailored to specific environments, and executes them. Furl maps the environment to understand asset criticality and ownership, ensuring safe, autonomous execution with user-defined guardrails and automatic rollbacks if validation fails. This platform is particularly effective for tackling misconfigurations, hardening gaps, and end-of-life systems that lack standard patches, providing a comprehensive solution for both security and IT teams.

Suppple is a technology company focused on powering Africa's next tech stack by developing AI-native software and scalable infrastructure. Their products are designed to simplify complexity and unlock growth for enterprises, innovators, and creators. Key offerings include Seeek, an AI-native search engine with multi-source indexing and enterprise security; Makerrr, which allows users to build internal tools and dashboards from natural language; and GRIO, a data-to-agent platform that transforms documents into actionable AI agents. Suppple also provides a proprietary system for item identification and traceability, and is developing Data Centre & GPU-as-a-Service to support continental AI needs.

Sahana System Limited is an IT company based in India, specializing in a wide range of technology solutions including AI, cloud, and enterprise services. They provide expertise in areas such as Generative AI, AI and ML, Big Data Analytics, DevOps, CloudOps, MLOPs, Digital Product Engineering, ERP, IoT, Cyber Security, Microsoft solutions, Blockchain, and Embedded Engineering. The company is certified with CMMI Level-5, ISO 9001, and ISO/IEC 27001, ensuring high standards in their service delivery. Sahana System aims to empower businesses with intelligent solutions, focusing on faster time-to-market, lower costs, and higher ROI across various industries like Fintech, Healthcare, Defence, and Manufacturing.

Flexday AI provides an Enterprise AI solution that utilizes autonomous AI agents to orchestrate, analyze, and submit mission-critical insights from your data ecosystem. It offers unified data access, seamlessly connecting to all enterprise data sources, including structured, unstructured, and AI models. The platform facilitates enterprise process flow, delivering the right information to internal teams and external users precisely when needed, with omnichannel accessibility. Flexday AI solutions benefit various teams, including procurement, customer service, human resources, legal, sales & marketing, IT service delivery, supply chain logistics, and education. The platform emphasizes data security with features like encryption, access controls, regular security audits, and secure cloud infrastructure.

ml-on-gcp is a comprehensive resource offering guides and practical recipes for integrating various Machine Learning frameworks with Google Cloud Platform. The primary goal is to simplify the process of bringing ML code to GCP, allowing users to dedicate more time to data exploration, model development, and problem-solving rather than interface management. It includes examples for TensorFlow, scikit-learn, and xgboost, along with tutorials on topics like hyperparameter search on Google Kubernetes Engine, running TensorFlow inference at scale with TensorRT, and inferring models from Google Cloud Functions. The repository also links to other Google Cloud ML resources, such as AI Platform samples and Google Cloud AI Developer Relations content.

APIpie.ai, developed by Neuronic AI, is an AI super aggregator designed to simplify access to a vast array of AI services from leading providers. It offers a unified API, allowing developers to integrate hundreds of language, vision, embedding, and voice models with a single subscription. The platform features automatic API routing to ensure optimal performance and cost-efficiency, along with deep observability tools for monitoring AI service usage, availability, latency, and cost. APIpie.ai aims to eliminate the need for multiple subscriptions and complex integrations, providing a turnkey solution for building AI-powered applications with built-in internet search, chat memory, and real-time analytics.

Skymizer is a company focused on advanced compilation technology, specifically designed to support AI chip manufacturers. They offer a comprehensive suite of software products and tools aimed at enhancing the performance and efficiency of AI hardware. Their offerings include various techniques, robust platforms, and complete turn-key solutions, all geared towards optimizing software for the unique demands of artificial intelligence hardware. Skymizer is recognized for its expertise in this specialized field, providing critical infrastructure for the development and deployment of high-performance AI systems.

NetSpeek is an AI-powered platform designed to automate and manage Audio Visual (AV) and Unified Communications (UC) environments at scale. Built for enterprises, Managed Service Providers (MSPs), and vendors, it significantly reduces operational costs and boosts productivity. The platform features Lena, a Language Enabled Network Administrator, which transforms how collaboration spaces are operated by providing AI-powered troubleshooting and network operations. Lena guides users step-by-step through issue resolution, ensuring problems are truly resolved. NetSpeek offers out-of-the-box compatibility with over 15 leading platforms and vendor ecosystems, ensuring seamless integration and innovation. Its agentic architecture allows for dynamic adaptability and self-adjusting AI within the network, all while maintaining maximum security with 24/7 monitoring and 2FA enabled.

Outerbounds offers a comprehensive platform designed to streamline the entire machine learning lifecycle, from development to secure production deployment. It provides human-centric infrastructure for machine learning, AI, and data science, enabling teams to develop agents and AI systems rapidly, built for production from day one. The platform supports experimentation and evaluation of new models, data, and code through branches, PRs, and CI/CD, with support for popular AI and agent frameworks. Outerbounds leverages Metaflow, created at Netflix, for orchestrating systems, including batch workflows, agents, and inference. It integrates seamlessly with top-tier GPU clouds like Nebius and CoreWeave, allowing for easy model fine-tuning and hosting of agents and inference endpoints without infrastructure setup or security policy updates. The platform follows a Bring-Your-Own-Cloud model, ensuring data, metadata, and compute remain in the user's cloud accounts, and offers cost optimization features to reduce cloud expenses.

llama-swap is a robust AI Agents & Automation tool designed for reliable model swapping across local OpenAI and Anthropic compatible servers, including llama.cpp and vllm. It allows users to run multiple generative AI models on their machine and hot-swap between them on demand. Built in Go for performance and simplicity, llama-swap boasts zero dependencies and is incredibly easy to set up with just one binary and one configuration file. It supports a wide range of OpenAI and Anthropic API endpoints, as well as specific endpoints for llama-server and SDAPI. The tool also includes a real-time web UI with a playground for testing models, viewing token metrics, and monitoring logs, making it a comprehensive solution for managing local AI workflows.

MachineLearningNotebooks is a GitHub repository offering Python notebooks filled with machine learning and deep learning examples, specifically designed for use with the Azure Machine Learning Python SDK. This resource provides practical demonstrations for various tasks, including building, training, and deploying machine learning models within the Azure ecosystem. While this repository focuses on the v1 SDK, it serves as a valuable historical reference for developers and data scientists working with Azure ML. Users are encouraged to explore the v2 SDK samples repository for the most current and enhanced examples, as this v1 repository is deprecated and no longer actively monitored or updated.

long-context-attention, also known as Unified Sequence Parallelism (USP) or Hybrid Sequence Parallelism, offers a novel approach to training and inference for long context Large Language Models (LLMs). This open-source project synergizes the strengths of DeepSpeed-Ulysses-Attention and Ring-Attention, addressing their individual limitations. Ulysses-Attention is sensitive to the number of attention heads and less suitable for GQA/MQA scenarios, while Ring-Attention can be less efficient in computation and communication. LongContextAttention provides a more general, versatile, and performant solution. It supports various FlashAttention versions (v2, v3) and can even run without FlashAttention for NPUs. The tool includes functionalities for setting process groups, extracting local tensors, and offers different ring implementation types like 'zigzag' and 'basic'. It has been verified in Megatron-LM and applied in several other projects, providing a robust solution for researchers and developers working with long context generative AI.

Data-science-on-aws is an open-source resource designed to educate users on implementing AI and Machine Learning solutions within the Amazon Web Services (AWS) ecosystem. It provides comprehensive examples for constructing end-to-end AI/ML pipelines, leveraging powerful tools such as Kubeflow, Amazon EKS, and Amazon SageMaker. The resource is structured around an O'Reilly book, offering practical, hands-on demonstrations. Users will learn to train and tune BERT models for natural language processing, perform hyper-parameter tuning, A/B testing, and set up real-time streaming analytics. It covers data ingestion, exploration, preparation, model training, optimization, deployment, and security, making it ideal for those looking to master data science workflows on AWS.

Deep-Learning-in-Production is a comprehensive GitHub repository curated by ahkarami, designed to serve as a valuable resource for deploying deep learning-based models in production environments. The repository compiles useful notes and references across various deep learning frameworks, including PyTorch, TensorFlow, Keras, and MXNet. It covers essential topics such as model conversion (e.g., PyTorch to C++, Keras to C++), model serving with tools like Flask, TorchServe, and TensorFlow Serving, and deployment on platforms like AWS Lambda and Kubernetes. Additionally, it provides insights into model quantization, speed optimization, and general deep learning deployment toolkits like OpenVINO and NVIDIA Triton Inference Server. The repository also includes resources for front-end and back-end development, mobile/embedded device deployment, and MLOps, making it a holistic guide for machine learning engineers and data scientists looking to operationalize their models.

deep-learning-wizard offers open-source guides and code for mastering deep learning, from foundational concepts to production deployment. The resource covers a wide array of topics including machine learning, deep learning, deep reinforcement learning, data engineering, and general programming. It provides tutorials on PyTorch, Python, Apptainer, and other relevant libraries, making it suitable for both beginners and those looking to deepen their expertise. The platform is designed to be mobile and tablet-friendly, ensuring accessibility for learners on various devices. It also includes sections on language models, HPC containers, and optimization techniques, aiming to provide a comprehensive learning experience for deep learning practitioners.

Mirage Persistent Kernel (MPK) is a compiler and runtime system designed to optimize large language model (LLM) inference by transforming it into a single, high-performance megakernel. This end-to-end GPU fusion approach significantly reduces LLM inference latency, offering improvements of 1.2× to 6.7× with minimal developer effort. MPK allows users to compile LLMs from the Hugging Face model zoo into a megakernel using Python, abstracting away complex CUDA/Triton programming. It provides an API for instantiating persistent kernels, attaching existing PyTorch tensors, and defining computation graphs by chaining fused operations. The tool is open source and aims to simplify the deployment of efficient LLM inference.

Comfy Deploy is a platform designed to streamline the deployment and management of ComfyUI workflows for teams. It allows users to share ComfyUI workflows via links, run them instantly in the cloud, or create simplified user interfaces. The platform facilitates one-click deployment of production APIs, ensuring effortless scaling without requiring extensive engineering knowledge. Key features include the ability to install custom nodes and models, share multiple environments, and leverage powerful auto-scaling GPUs like H100s and A100s for parallel cloud generation. Comfy Deploy also offers full version history for workflows, making collaboration and iteration easy, and provides a playground for testing and refining workflows with auto-generated UIs.

EMPRESS is an observability platform specifically designed for AI agents, enabling users to track every action an AI agent takes in xAPI format. This comprehensive tracking helps prove compliance with regulations like the EU AI Act, optimize agent performance, and scale AI operations with confidence. The platform records what agents do, why they do it, and the resulting outcomes, providing a full decision history and audit-ready logs. It allows users to search and filter decisions instantly, understand the reasoning behind each action, and export complete audit trails for compliance reports. EMPRESS also offers hundreds of pre-built skills to help users build and deploy agents for various tasks, from account management to content moderation, ensuring explainable decisions and improved agent behavior.