Neo.mjs v11.0.0 Release Notes

This is a monumental release, the largest in the project's history, delivering on the AI-Native vision outlined in our roadmap. Over the last six weeks, we have professionalized our AI tooling by shipping three dedicated Model Context Protocol (MCP) servers, fundamentally changing how developers and agents collaborate within the Neo.mjs ecosystem.

This release is also a testament to the power of our community. We are immensely grateful for the incredible contributions from over 20 developers during Hacktoberfest 2025, whose efforts have touched every part of this release.

Release Blog Post: 388 Tickets in 6 Weeks: Context Engineering Done Right

✨ Highlights

🚀 The AI-Native Tooling Suite: 3 New MCP Servers (#7399)

We have officially moved beyond brittle, shell-based scripts to a robust, agent-agnostic server architecture. This professionalizes our AI tooling, providing a stable and structured API for any AI agent to interact with the Neo.mjs development environment. This is configured directly within the agent's settings, making the tools available for any task:

{
    "mcpServers": {
        "chrome-devtools": {
            "command": "npx",
            "args"   : ["-y", "chrome-devtools-mcp@latest"]
        },
        "neo.mjs-github-workflow": {
            "command": "npm",
            "args"   : ["run", "ai:mcp-server-github-workflow"]
        },
        "neo.mjs-knowledge-base": {
            "command": "npm",
            "args"   : ["run", "ai:mcp-server-knowledge-base"]
        },
        "neo.mjs-memory-core": {
            "command": "npm",
            "args"   : ["run", "ai:mcp-server-memory-core"]
        }
    }
}

• Self-Hosting Architecture (#7536): In a powerful demonstration of dogfooding, the MCP servers themselves are built using the Neo.mjs class system. This showcases the framework's versatility for creating robust, scalable backend and CLI applications.
• Hybrid GraphQL & CLI Architecture (#7590): The GitHub Workflow server now uses a powerful hybrid approach. It leverages the official GitHub GraphQL API for all remote data fetching and mutations, providing significant performance and reliability gains. For local repository operations, such as checking out a pull request branch, it continues to use the gh CLI for direct, file-system level interactions.
• Automated & Simplified Setup (#7604): The servers now manage their own database startup and session summarization automatically. This drastically simplifies the agent onboarding process, reducing the agent's setup protocol by over 70%.
• Self-Documenting Tools (#7668): The MCP tools are now self-documenting, allowing agents to dynamically inspect tool capabilities and schemas, making the entire system more resilient and easier to extend.
• Knowledge Base Server: Provides the AI with a deep, semantic understanding of the framework's source code, documentation, and historical tickets.
• Memory Core Server (#7316): Gives our AI agent a persistent, long-term memory. The agent can now recall past conversations, decisions, and outcomes, allowing it to learn from experience and improve over time.
• GitHub Workflow Server (#7364): The crown jewel of our new tooling. This server provides robust, bi-directional synchronization for GitHub issues and release notes, storing them as local markdown files. This enables agents (and humans) to interact with them as part of the local knowledge base while ensuring everything stays in sync with GitHub. It automates the entire issue and pull request lifecycle, empowering the agent to participate directly in the development workflow.

To get started with this new AI-native workflow, please see our guides on Working with Agents and the AI Quick Start.

🧪 Enabling Agent-Driven Quality with Playwright (#7262)

To enhance stability and enable true AI-driven development, we have completed the migration of our entire unit test suite from the browser-based Siesta to the Node.js-based Playwright runner.

• Agent Self-Verification: The most significant benefit of this migration is that AI agents can now run npm test to validate their own changes. This is a critical step toward a fully autonomous, quality-driven development loop and a prerequisite for future CI/CD integration.
• Comprehensive Migration: This epic involved the migration of over 30 test suites, ensuring our core logic is protected against regressions.

❤️ A Huge Thank You to Our Community! (#7296)

This release would not have been possible without the incredible energy and contributions from our community, especially during Hacktoberfest 2025. We received over 52 pull requests from more than 20 contributors, a new record for the project.

Our heartfelt thanks go out to: Aki-07, Ayush Kumar, Chisaneme Aloni, Emmanuel Ferdman, Ewelina Bierć, KURO-1125, LemonDrop847, Mahita07, MannXo, Mariam Saeed, Nallana Hari Krishna, Nitin Mishra, PrakhyaDas, Ritik Mehta, Sanjeev Kumar, Sarthak Jain, ad1tyayadav, cb-nabeel, kart-u, nikeshadhikari9, srikanth-s2003. (auto-generated, apologies upfront in case we missed someone => give us a ping)

🏗️ Framework & Documentation Enhancements

• Strategic Vision & Roadmap (#7264): The project's direction has been clarified with a new ROADMAP.md and a rewritten VISION.md, focusing on "Context Engineering" as the core theme for our AI-native strategy.
• NPM Package Optimization: To keep the framework lightweight, a new .npmignore file has been added. This prevents the local issue and release note markdown files from being included in the published package, reducing bloat.

All changes in 1 commit: https://github.com/neomjs/neo/commit/796714cf5126b2744829e62782fd9bc2641a55e9