What is the 'Neural Link'?

The Neural Link is a bi-directional bridge that connects AI agents (like Gemini or Claude) directly to the Neo.mjs runtime. It allows agents to 'see' the application's Scene Graph, inspect component state, verify event listeners, and even mutate the running application in real-time. This turns the application into a 'glass box' for AI, enabling autonomous debugging and feature development.

Why is Neo.mjs called an 'Application Engine' instead of a framework?

Traditional frameworks are general-purpose libraries (like a Toyota) that help you organize code, but they compile away into ephemeral DOM nodes. Neo.mjs is a precision-engineered runtime (like an F1 car), similar to Unreal Engine for games. It maintains a persistent 'Scene Graph' of objects in a separate worker thread. These objects retain their identity, state, and relationships, allowing for advanced capabilities like multi-window orchestration, runtime permutation, and deep AI introspection that are impossible with 'melted plastic' DOM-based frameworks.

What is 'Context Engineering'?

Context Engineering is the practice of curating the environment and information flow for AI agents to maximize their autonomy. In Neo.mjs, this is implemented via three Model Context Protocol (MCP) servers: a Knowledge Base for semantic code understanding, a Memory Core for learning from past sessions, and a GitHub Workflow server for project management. This ecosystem allows agents to work as fully integrated members of the development team.

What is 'Object Permanence' in the context of Neo.mjs?

In Neo.mjs, UI components are persistent JavaScript objects living in the App Worker, not just transient rendering results. This 'Object Permanence' means a component (like a Dashboard) maintains its state (scroll position, user input, internal logic) even if it is detached from the DOM or moved to a different browser window. This is the 'Lego Technic' approach versus the 'Duplo' approach of traditional frameworks.

What is an 'Agent Operating System'?

Neo.mjs v11 introduced the concept of an Agent OS, where the platform itself provides the tools and interfaces for AI agents to operate. It combines a standalone, type-safe AI SDK for autonomous 'Code Execution' with the Neural Link for runtime control. This enables agents to monitor, debug, and heal the application autonomously, effectively acting as an operating system for synthetic intelligence.

How does Neo.mjs handle multi-window applications?

Neo.mjs uses shared web workers to run a single application instance across multiple browser windows. All windows share the same application state and data in real-time. Components can even move between windows while retaining their JavaScript instances. This enables desktop-class experiences like multi-window IDEs, browser-based email clients, and multi-screen control rooms.

What makes Neo.mjs different from React, Angular, or Vue?

Neo.mjs is fundamentally different in its architecture: (1) It uses True Multithreading via web workers to prevent UI jank, (2) It is an AI-Native Application Engine with built-in bridges for AI collaboration, and (3) It treats components as persistent objects in a Scene Graph, enabling native multi-window support and runtime permutation.

Frontmatter

id	7843
title	[AI] Implement Runtime Type Safety for AI SDK via OpenAPI Wrappers
state	Closed
labels	enhancementdeveloper-experienceairefactoring
assignees	tobiu
createdAt	Nov 21, 2025, 3:14 PM
updatedAt	Nov 21, 2025, 3:31 PM
githubUrl	https://github.com/neomjs/neo/issues/7843
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Nov 21, 2025, 3:31 PM

[AI] Implement Runtime Type Safety for AI SDK via OpenAPI Wrappers

Name: Neo.mjs Application Engine
Author: Neo.mjs

Closed v11.8.0 enhancementdeveloper-experienceairefactoring

tobiu commented on Nov 21, 2025, 3:14 PM

Objective Implement a mechanism to ensure runtime type safety for direct SDK service calls (ai/services.mjs) without introducing a compilation step.

Current State

MCP tools are type-safe because toolService.mjs validates incoming requests against Zod schemas generated from openapi.yaml.
Direct SDK usage (importing services directly) bypasses this validation, creating a "safety gap" where incorrect shapes can be passed to services.

Proposed Solution Refactor the existing validation logic into a shared OpenApiValidator utility and use it to create a "Safe SDK" wrapper.

Extract Validator: Move the buildZodSchema and schema caching logic from ai/mcp/server/toolService.mjs into a new ai/mcp/validation/OpenApiValidator.mjs module.
Create Service Wrapper: Implement a factory function (e.g., createSafeService) that:
- Accepts a raw service object and the OpenAPI spec.
- Iterates over the service methods.
- Wraps each method with Zod validation logic derived from the OpenAPI Operation ID.
Update SDK Export: Modify ai/services.mjs to export these wrapped, validated service instances instead of the raw ones.

Benefits

DRY: Single source of truth (OpenAPI) for both MCP and SDK validation.
Zero-Build: Maintains the project's pure ESM / no-compile philosophy.
Robustness: Prevents runtime errors due to invalid arguments when agents use the SDK directly.

Acceptance Criteria

ai/mcp/validation/OpenApiValidator.mjs exists and contains the extracted Zod logic.
ai/services.mjs exports validated service instances.
Passing invalid arguments to an SDK method throws a clear Zod validation error.
Existing MCP tool functionality remains unchanged (regression test).

tobiu added the enhancement label on Nov 21, 2025, 3:14 PM

tobiu added the developer-experience label on Nov 21, 2025, 3:14 PM

tobiu added the ai label on Nov 21, 2025, 3:14 PM

tobiu added the refactoring label on Nov 21, 2025, 3:14 PM

tobiu assigned to @tobiu on Nov 21, 2025, 3:18 PM

tobiu referenced in commit 9cc5337 - "[AI] Implement Runtime Type Safety for AI SDK via OpenAPI Wrappers #7843" on Nov 21, 2025, 3:31 PM

tobiu Nov 21, 2025, 3:31 PM

tobiu closed this issue on Nov 21, 2025, 3:31 PM