Coding & Development

Subterranean is an AI-native platform designed to run entire AI teams for businesses. It allows users to set up specialist agent teams, shared workspaces, memory, data, and workflows with minimal setup, eliminating the need for extensive coding experience. The platform features an intuitive interface where users can chat directly with agents or assign tasks. It includes project sandboxes, a virtual filesystem for agent configurations and context, and a built-in database with automatic Postgres tables for structured data. Subterranean aims to accelerate workflows for both non-technical users and developers, enabling the creation of AI-driven applications and business processes.

Cloudangles delivers cloud, AI, data, and quantum innovation to help enterprises scale faster, smarter, and more securely. It provides a unified suite of deep-tech platforms and transformative services, enabling organizations to innovate faster and scale with precision. Key platforms include Cloudoptimax for AI-driven cloud cost optimization, Dangles for simplifying data engineering, mlangles for AI-powered MLOps and LLMOps, and Testingaide for AI-driven software testing. Cloudangles also offers services in product engineering with agentic AI, data management, applied AI, cloud operations, FinOps, cloud migration, and quantum computing solutions like Quantum-as-a-Service and Quantum ML. Their solutions are tailored for various industries including banking, insurance, healthcare, retail, manufacturing, and utilities.

Semantix Corp specializes in transforming complex businesses into intelligent enterprises by leveraging artificial intelligence, big data, and intelligent operations. Their Semantix Intelligent Platform orchestrates this transformation, integrating a proprietary AI Enterprise Suite for measurable business results, robust data foundations for scalable AI, and industrialized enterprise operations for critical environments. With over 15 years of experience, Semantix supports over 500 companies globally, focusing on efficiency, decision-making, and continuous business evolution. They offer solutions across various sectors including finance, industry, health, telecom, and retail, ensuring secure and intelligent operations.

SWE-PR is a specialized tool designed to track and display performance metrics for software engineering agents on GitHub. It offers a comprehensive leaderboard that showcases pull-request, review, and commit numbers, alongside crucial acceptance rates. This platform is invaluable for monitoring the efficiency and impact of AI-driven coding assistants. Users can easily add new assistants to the tracking system, making it a flexible solution for evaluating various agents. By providing clear, quantifiable data, SWE-PR helps development teams and researchers assess the effectiveness of different software engineering AI tools and understand their contributions to the development lifecycle.

8090 Solutions Inc. offers an AI-native software development platform designed to keep business leaders in control of their software projects. The platform, called Software Factory, integrates teams and AI agents into a single system for building software, ensuring full control, visibility, and auditability from specification to deployment. For larger organizations, 8090 Enterprise provides purpose-built applications designed, built, hosted, and maintained by 8090, allowing businesses to own the logic while ensuring quality, control, and consistency. The platform emphasizes documentation, collaboration, and oversight, leveraging institutional knowledge to create a living knowledge graph that survives employee turnover and policy changes. It is built for regulated industries like healthcare, financial services, manufacturing, and federal government, with a focus on compliance and visibility.

Warden is an AI copilot designed to enhance the productivity of security engineers by automating various aspects of security reviews. The tool helps identify security vulnerabilities and streamline workflows, aiming to reduce security backlogs and improve overall system security. Key features include the generation of AI-powered technical architecture diagrams based on project documents and use case questions, which assist engineers in identifying potential issues. Warden also automatically identifies comprehensive risk factors for projects and suggests possible mitigations that security engineers can review, enabling product teams to build more secure products. This comprehensive approach helps organizations save time and ensure maximum security.

Warp Development is a global development partner specializing in custom software development and AI consulting. They assist businesses in designing, building, and running scalable custom software and AI solutions to achieve real business outcomes. Their services span AI Consulting, Enterprise Software Development, IT Infrastructure & Managed Services, Staff Augmentation, and Strategic Technology Advisory. They focus on integrating AI into existing systems to deliver measurable value and provide experienced specialists for continuity and deep expertise across all engagements, from engineers to DevOps. With a global delivery model, they offer access to experienced engineering talent with competitive economics and meaningful overlap across time zones.

CodeShell is a robust series of code large language models developed by PKU-KCL, featuring 7 billion parameters and trained on 500 billion tokens with an 8192 context window. It excels in code evaluation benchmarks like HumanEval and MBPP, outperforming similar-sized models such as CodeLlama and Starcoder. The project offers a comprehensive ecosystem including base models, chat models (with 4-bit quantization for reduced memory), and C++ versions for local deployment without a GPU. CodeShell also provides IDE plugins for VS Code and JetBrains, along with various demo options including Web-UI, CLI, and OpenAI API compatibility, making it a versatile solution for code generation, fill-in-the-middle tasks, and code-related Q&A.

Thazen is a certified HUBZone small business offering modern software development and cloud solutions tailored for federal, defense, and commercial sectors. Their expertise spans agile software development, scalable cloud-native architectures using Kubernetes and Docker, and robust DevSecOps pipelines for continuous integration and deployment. Thazen also specializes in web and mobile application development, AI & Machine Learning for intelligent systems, and the modernization of legacy systems. They bring over 15 years of commercial cloud and software technology experience to government projects, ensuring a security-first approach with secure cloud solutions and Zero Trust principles. Their cohesive engineering and leadership teams have over a decade of experience, ensuring consistent quality and seamless project execution.

FastDeploy is an open-source, high-performance inference and deployment toolkit built on PaddlePaddle, designed for Large Language Models (LLMs) and Vision Language Models (VLMs). It provides production-ready deployment solutions with key features like load-balanced PD decomposition, unified KV cache transmission, and compatibility with OpenAI API services and vLLM. The toolkit supports a wide range of quantization formats including W8A16, W8A8, W4A16, W4A8, W2A16, and FP8. It also incorporates advanced acceleration technologies such as speculative decoding, multi-token prediction (MTP), and chunked prefilling. FastDeploy supports various hardware platforms including NVIDIA GPUs, Kunlunxin XPUs, Hygon DCUs, and Intel Gaudi, making it a versatile tool for AI developers and machine learning engineers.

nndeploy is a comprehensive AI deployment framework designed for both ease of use and high performance. It addresses the critical challenge of deploying AI algorithms across a wide range of devices, including desktop (Windows, macOS), mobile (Android, iOS), edge computing devices (NVIDIA Jetson, Ascend310B, RK), and single-machine servers (RTX series, T4, Ascend310P). The framework leverages a visual workflow interface and multi-end inference capabilities, enabling more efficient and higher-performance deployment of AI algorithms. For large models exceeding 10 billion parameters, such as large language models and AIGC generative models, nndeploy serves as an effective visualization workflow tool. It features drag-and-drop nodes for deployment, real-time adjustable parameters, and support for custom Python/C++ nodes, ensuring seamless integration and one-click deployment across various platforms.

Cencurity is a comprehensive security gateway designed to protect AI systems, specifically LLM agents, with enterprise-grade precision. It prevents prompt leakage and unauthorized access by acting as a real-time security layer. The platform offers a centralized security dashboard that provides a single pane of glass for monitoring all agent calls, including requests, responses, latency, policy hits, redactions, and blocks. Cencurity automatically detects and blocks secrets, PII, and risky output before it reaches users or models, ensuring real-time protection. It also provides real-time log analysis, allowing users to trace every agent interaction end-to-end, search, filter, and correlate requests, responses, and policy decisions to pinpoint risks quickly. The tool is compatible with leading AI providers and IDE workflows, integrating seamlessly without requiring rewrites.

Inference.ai provides access to popular open and closed AI models at significantly reduced costs. The platform achieves this by optimizing GPU pooling and intelligently orchestrating workloads, maximizing GPU utilization which typically averages only 10-30%. By packing multiple models onto the same GPU, Inference.ai offers more compute for less money without compromising on latency. This approach leads to average savings of 30% for customers compared to direct pricing. The service supports model training and fine-tuning, utilizing enterprise-grade accelerators from leading vendors like NVIDIA and AMD, including the latest B300 Blackwell and MI355X CDNA 4 GPUs.

InstantKnow is a powerful website monitoring tool designed to help users track changes on their favorite web pages effortlessly. It provides a page monitor that continuously checks for updates, ensuring users never miss important modifications. The platform offers features like AI analysis and summarization, targeted monitoring, instant alerts, and visual result comparison. Users can monitor website content changes, track competitor prices, policy shifts, and even web design alterations. InstantKnow is ideal for staying competitive, adapting quickly to market changes, and optimizing business strategies. It integrates a powerful database and offers instant email notifications to keep users informed.

Lessthan3 is an infrastructure expert partner offering DevOps, FinOps, and SecOps solutions enhanced with its proprietary AI-powered Observability platform. The platform is designed to optimize business operations by cutting costs and boosting efficiency across technological infrastructures. It supports transformation journeys by improving performance, security, and sustainability. Key offerings include DevOps-as-a-Service for cloud journey support, FinOps for ROI optimization and cost management, SecOps for robust security and compliance, and GreenOps for managing environmental impact and refining energy consumption. The AI-powered platform aims to revolutionize monitoring and troubleshooting, moving clients from reactive to proactive monitoring to prevent failures and drive DevOps excellence.

Arrikto offers an Enterprise Kubeflow distribution, functioning as a comprehensive MLOps platform designed to streamline the delivery of scalable machine learning models. It significantly reduces operational costs and accelerates the transition of models from development environments to production. The platform addresses the critical need for robust storage and data management in AI workloads, which often face bottlenecks with traditional storage solutions. Arrikto's storage is built from the ground up for AI, optimized for Kubernetes, and designed for hybrid and multi-cloud environments. It leverages new kernel APIs and a novel storage architecture combining NVMe and object storage with P2P federation for efficient data syncing. This approach results in storage that is up to 8x faster and 3.5x cheaper than comparable cloud block storage offerings, all while being software-only and requiring no changes to existing infrastructure.

Tensorlake offers Lightspeed AI native sandboxes designed for durable agentic loops and isolated tool/code execution. Its core functionality includes stateful compute, allowing users to pause and resume operations in the exact state they left them. The platform provides dynamic resource allocation, enabling users to specify CPU, memory, and disk on every API call without predefined VM templates. Key features include the ability to snapshot, clone, and replicate running sandboxes, as well as live-migrate named sandboxes across hosts. Tensorlake supports customizable runtimes for various needs, from minimal sandboxes for latency-sensitive tool calls to environments with systemd for Docker and Linux software. It also offers orchestration capabilities for agents, including application endpoints, distributed fan-out, and durable primitives for long-running agentic flows. The platform emphasizes security with Firecracker isolation and compliance with SOC 2 Type II and HIPAA standards.

Gradio 🤝 TGI integrates Gradio and Text Generation Inference (TGI) within a unified environment, simplifying the process of deploying and testing AI models. This setup is particularly useful for developers and researchers who need to quickly create interactive web interfaces for their text generation models. By packaging both Gradio, a popular library for building UI components for machine learning models, and TGI, an optimized solution for serving large language models, this tool aims to streamline AI development workflows. It allows for efficient experimentation and demonstration of AI capabilities without the complexity of managing separate infrastructures for UI and model serving.

Swish.ai redefines IT operations by moving beyond managing tickets to preventing them, transforming IT from reactive to proactive. It combines self-service, automation, and intelligent ticket creation to ensure faster resolutions and seamless workflows. The platform integrates effortlessly with existing ITSM systems, using Agentic AI to deliver results quickly. Swish.ai's Core Data Enablement layer organizes unstructured tickets into intelligent clusters, uncovering hidden patterns and providing actionable insights. This enables teams to resolve issues faster and eliminate redundancies. It also offers Intelligence Process Analysis for a comprehensive view of ITSM workflows, pinpointing inefficiencies and optimizing operations. Swish.ai aims to deliver double-digit ITSM performance gains, including up to 25% reduction in operational costs, over 35% reduction in Mean Time to Resolution (MTTR), and up to 50% acceleration in Backlog Burnrate.

DeepGrove is at the forefront of developing highly efficient AI models specifically designed for edge computing environments. The company's core mission is to democratize frontier intelligence, making advanced AI capabilities accessible on a wide range of devices. By focusing on optimizing AI models, DeepGrove addresses the critical need for powerful yet resource-conscious artificial intelligence solutions that can operate directly on edge devices, reducing latency and reliance on cloud infrastructure. This approach is poised to revolutionize various industries by enabling real-time, on-device AI processing, which is crucial for applications where immediate decision-making and data privacy are paramount.

PixelVirt Technology provides a comprehensive multi-tenant cloud platform designed for managing OpenStack and Kubernetes clusters. This unified portal simplifies the orchestration of multiple clusters, offering full tenant isolation and robust infrastructure automation. Key features include a unified dashboard for OpenStack, Kubernetes, alerts, and inventory, alongside AI-powered operations. The platform integrates built-in automation for provisioning and configuration management using Ansible or Python, enterprise-grade data backup services, and deep infrastructure visibility with monitoring and intelligent alerting. PixelVirt also offers a one-click Kubernetes deployment tool and includes secret and inventory management, making it an all-in-one solution for private cloud infrastructure needs.

Stable Diffusion WebUI Forge is an open-source platform that enhances the capabilities of Stable Diffusion WebUI, focusing on improving development workflows, optimizing resource management, and accelerating inference speeds. Inspired by 'Minecraft Forge,' it aims to become the definitive 'Forge' for SD WebUI. The platform is currently based on SD-WebUI 1.10.1 and synchronizes with the original WebUI periodically. It offers features like GPU memory management, support for various LoRAs, preprocessors, ControlNets, and IP-Adapters. Forge also integrates Gradio 4 UIs and provides one-click installation packages for different CUDA/Pytorch versions, making it accessible for users to quickly set up and run the environment.

0PTIKUBE is an AI-powered tool designed to optimize and manage Kubernetes clusters. It offers real-time monitoring through a custom dashboard, allowing users to visualize resource usage per pod or get an overview of the entire cluster. The platform leverages AI to identify resource bottlenecks and provide recommendations for infrastructure optimization, leading to better performance. 0PTIKUBE aims to simplify the understanding and management of complex Kubernetes environments, making it easier for users to maintain efficient and well-performing systems.

agentic_coding_flywheel_setup is an open-source tool designed to quickly set up a multi-agent AI development environment on a fresh Ubuntu VPS. In just 30 minutes, it configures essential components including coding agents, session management, safety tools, and coordination infrastructure. This tool is ideal for developers looking to rapidly deploy a fully configured agentic coding VPS, transforming a standard Ubuntu server into a powerful AI-powered development hub. It streamlines the setup process, allowing users to focus on AI development rather than environment configuration.