February 2026 Summaries

Nx has joined the Linux Foundation and the Agentic AI Foundation (AAIF) to contribute to the development of open standards for agentic AI, which is transforming the software development landscape by enabling autonomous systems to plan, coordinate, and act across tools and codebases. By aligning with these organizations, Nx aims to ensure that its intelligent tooling, which supports complex codebases across JavaScript, TypeScript, and other polyglot ecosystems, integrates seamlessly with AI agents that navigate dependency graphs, orchestrate builds, and modify code. The Linux Foundation provides a neutral platform for open-source projects essential to global infrastructure, and the AAIF, established in December 2025, focuses on creating open standards for agentic AI, with foundational projects like Anthropic's Model Context Protocol and OpenAI's AGENTS.md. Through participation in working groups and collaboration with industry leaders such as Anthropic, AWS, Google, and Microsoft, Nx is committed to advancing agentic workflows and ensuring the development tools relied on by developers are compatible with AI-powered advancements.

Monorepos, a software development approach where multiple projects are developed within the same repository, offer significant advantages in terms of code sharing, deployment flexibility, and scaling capabilities when set up correctly. Despite common misconceptions, monorepos do not necessitate simultaneous releases or create unmanageable codebases; rather, they allow for independent project development and structured dependency management. Tools like Nx enhance monorepo efficiency by enabling selective rebuilding and retesting, maintaining code ownership, and supporting AI-driven development through structured project graphs. While monorepos streamline certain processes, they require adjustments such as adopting trunk-based development and sophisticated continuous integration setups to handle large-scale changes effectively. Although transitioning to a monorepo setup can present challenges, modern tooling solutions like Nx Cloud offer features like remote caching, distributed task execution, and self-healing CI to optimize workflow and scalability.

The evolution of AI tools has shifted from using Model-Contextualized Protocols (MCPs) to a more efficient system of skills and subagents, improving the functionality and token efficiency of AI assistants. While MCPs were initially crucial for integrating AI with developer environments by offering tools like project graphs and task pipelines, advancements such as the Claude Code have enabled AI agents to execute commands autonomously, reducing the need for MCPs. Skills, which provide domain-specific knowledge and instructions, have proven to be more effective, allowing agents to utilize command-line interfaces like Nx CLI directly and make informed decisions about tasks such as generator usage and workspace exploration. Despite the decline in MCP usage, it remains valuable for authenticated API interactions and processes that require connectivity beyond the agent's autonomous capabilities. The ongoing development focuses on refining skills, introducing new subagents, and leveraging MCP for tasks that are not easily replicable through skills alone, as demonstrated in benchmarks comparing agent performance with and without these enhancements.

Nx agent skills offer a comprehensive suite of capabilities designed to enhance AI coding agents' effectiveness in monorepos, particularly when used with Nx. This setup, initiated by a simple configuration command, equips AI agents with the necessary skills to understand workspace structures, run tasks efficiently, and bridge local development with CI through real-time monitoring and autonomous workflows. Skills are modular knowledge packets that load only when needed, keeping agents focused and efficient. Key skills include understanding workspace layouts, generating code predictably by combining AI decision-making with consistent generators, and effectively using the Nx CLI for task execution. Additionally, the skills address common monorepo challenges, such as linking packages with different package managers. This initial release aims for continuous expansion, driven by user feedback and contributions, to optimize AI agent performance in Nx and monorepo environments.

Broadcom, a global technology leader, faced challenges managing its complex software application portfolio, particularly with its VMware suite, due to inefficiencies in DevOps and the autonomy of various teams. To address this, Broadcom adopted a monorepo strategy to consolidate projects and streamline workflows, despite initial resistance from teams used to independent operations. They enlisted the help of Nx co-founders Victor Savkin and Jeff Cross, whose platform proved instrumental in this transition. By demonstrating the tangible benefits of a monorepo, such as faster builds and simpler workflows, Broadcom successfully shifted its organizational culture towards collaborative development. As a result, the company has seen significant improvements, including reduced CI times and increased productivity, solidifying the monorepo as a company-wide strategy. The partnership with Nx has facilitated continuous innovation, positioning Broadcom at the forefront of efficient software development practices.

Monorepo architecture has undergone significant evolution, leading to a complex landscape characterized by inconsistent definitions, rapidly changing tools, and varied implementation patterns across different organizations. As AI coding assistants become more prevalent, modern monorepo tooling is proving particularly effective in addressing the coordination challenges that arise, offering potential velocity gains even without a full migration. For engineering leaders, understanding the advantages of monorepos in 2026 can be crucial for navigating this dynamic environment. An upcoming webinar, presented by Jeff Cross and Juri Strumpflohner, aims to provide a clear framework for understanding and leveraging monorepos to achieve measurable impact, especially for organizations aiming to operate at AI-driven speeds.

Nx has experienced significant growth, with monthly NPM downloads increasing by 63% over the past year. The platform has introduced first-party plugins for various technologies like Docker, .NET, and Angular, alongside a new Terminal UI, improved analytics, and a Self-Healing CI system that automatically fixes failures. Looking towards 2026, Nx aims to integrate autonomous AI agents into its platform, leveraging a monorepo architecture to allow these agents to optimize builds and make architectural decisions autonomously. This development is supported by the creation of synthetic monorepos, which enable cross-repo visibility without merging all code into a single repository. The platform also focuses on enhanced task distribution, task sandboxing to prevent cache misconfiguration, and increased support for polyglot environments, including upcoming features for Python and C#. Nx is working on incremental project graph hydration to improve efficiency and is aligning with modern JavaScript tooling trends. Through these innovations, Nx is positioning itself as a pivotal infrastructure for autonomous AI agents in software development.

In 2026, the focus is shifting from agentic tools to fully autonomous AI workflows that can independently manage large tasks, significantly altering workplace dynamics and providing a competitive edge to organizations that adapt swiftly. Autonomous AI agents are now capable of operating across projects without human intervention, exemplified by the "Ralph Wiggum loops," which iteratively complete tasks. However, a major challenge in adopting these workflows is the disconnect between local development and continuous integration (CI) systems, which can hinder full autonomy. Nx addresses this issue by offering modular solutions that enhance communication between local agents and CI processes, utilizing skills like the ci-monitor to maintain context and apply automated fixes through its Self-Healing CI agent. This setup allows AI agents to handle repetitive and error-prone tasks, such as monitoring CI pipelines and implementing verified fixes, thus enabling developers to focus on higher-level decision-making. As AI coding agents become integral to daily workflows, the success of these systems largely depends on the infrastructure, codebase organization, and the integration depth of CI platforms, making Nx a pivotal tool in enhancing productivity through autonomous workflows.