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	8187
title	Feat: Neural Link - State Provider Inspection & Modification
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Dec 28, 2025, 10:12 PM
updatedAt	Dec 29, 2025, 10:29 PM
githubUrl	https://github.com/neomjs/neo/issues/8187
author	tobiu
commentsCount	1
parentIssue	8169
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Dec 29, 2025, 10:29 PM

Feat: Neural Link - State Provider Inspection & Modification

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

Closed v11.18.0 enhancementai

tobiu commented on Dec 28, 2025, 10:12 PM

Context: For modern Neo apps using state.Provider, inspecting the global state tree is the fastest way to understand the application context. Modifying this state is a powerful way to drive the application.

Scope:

Enhance ComponentService:
- Update getComponentTree to include stateProviderId on components.
Enhance DataService:
- Add inspectStateProvider(sessionId, providerId).
  - Implementation: Neo.get(providerId).getHierarchyData().
- Add modifyStateProvider(sessionId, providerId, data).
  - Implementation: Neo.get(providerId).setData(data).
  - data is a JSON object with keys/values (can be nested).
Tools:
- inspect_state_provider: Returns the effective state object.
- modify_state_provider: Updates the state.

Goal: Provide full read/write access to the application's reactive state hierarchy.

tobiu added the enhancement label on Dec 28, 2025, 10:12 PM

tobiu added the ai label on Dec 28, 2025, 10:12 PM

tobiu added parent issue #8169 on Dec 28, 2025, 10:12 PM

tobiu assigned to @tobiu on Dec 29, 2025, 10:22 PM

tobiu referenced in commit dc0b535 - "feat(ai): Implement State Provider Inspection & Modification (#8187) on Dec 29, 2025, 10:23 PM

tobiu Dec 29, 2025, 10:29 PM

Input from Gemini 3:

✦ I have implemented the State Provider Inspection & Modification features.

Changes:

Component Service (src/ai/client/ComponentService.mjs):

Updated serializeComponent to include stateProviderId in the output only if the component explicitly defines/owns a stateProvider. This provides a clear view of state scope boundaries within the component tree without noise.

Data Service (src/ai/client/DataService.mjs, ai/mcp/server/neural-link/services/DataService.mjs):

Implemented inspectStateProvider(providerId): Returns the hierarchical data object from the provider.

Implemented modifyStateProvider(providerId, data): Allows merging new data into the provider.

MCP Integration:

Registered inspect_state_provider and modify_state_provider tools.

Updated src/ai/Client.mjs service mappings.

Updated openapi.yaml with new paths and schemas.

Agents can now discover where state providers are located (via get_component_tree) and then inspect or modify their data directly.

tobiu closed this issue on Dec 29, 2025, 10:29 PM