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	8097
title	Introduce autoInitRecords config for Neo.data.Store
state	Closed
labels	enhancementdeveloper-experienceai
assignees	tobiu
createdAt	Dec 12, 2025, 1:57 PM
updatedAt	Dec 12, 2025, 2:08 PM
githubUrl	https://github.com/neomjs/neo/issues/8097
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Dec 12, 2025, 2:05 PM

Introduce autoInitRecords config for Neo.data.Store

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

Closed v11.17.0 enhancementdeveloper-experienceai

tobiu commented on Dec 12, 2025, 1:57 PM

To improve Developer Experience (DX) and allow easier control over the "Turbo Mode" (lazy record instantiation) strategy in Neo.data.Store, we will introduce a new config: autoInitRecords.

This config will serve as the default value for the init parameter in add() and insert() methods, and will also control how the data config is processed.

Proposed Changes:

Add autoInitRecords: true to Neo.data.Store config.
Update add(item, init=this.autoInitRecords)
Update insert(index, item, init=this.autoInitRecords)
Update afterSetData to use me.add(value, me.autoInitRecords) instead of hardcoded false.
Update JSDoc and tests.

This allows developers to simply set autoInitRecords: false on the Store to enable Turbo Mode globally for that store instance, without needing to pass flags to every method call.

tobiu added the enhancement label on Dec 12, 2025, 1:57 PM

tobiu added the developer-experience label on Dec 12, 2025, 1:57 PM

tobiu added the ai label on Dec 12, 2025, 1:57 PM

tobiu assigned to @tobiu on Dec 12, 2025, 1:57 PM

tobiu referenced in commit 8fe4e63 - "Introduce autoInitRecords config for Neo.data.Store #8097" on Dec 12, 2025, 2:05 PM

tobiu closed this issue on Dec 12, 2025, 2:05 PM

tobiu Dec 12, 2025, 2:08 PM

Input from Gemini:

✦ The current state of Neo.data.Store is significantly improved for both performance and Developer Experience (DX), even without the larger refactoring.

Improvements:

Optimization: The initRecord check prevents redundant get() calls and lookups when dealing with already-instantiated records. This is a solid micro-optimization that will add up in high-frequency operations.

Flexibility & DX: The introduction of autoInitRecords transforms "Turbo Mode" from an obscure parameter into a first-class, declarative configuration. This makes it much easier to configure stores for bulk-data scenarios (like big grids) without polluting every add() call in the application logic.

Reliability: We now have a dedicated unit test suite for Store. This is a crucial baseline. Before, testing relied on Collection tests or side-effects in component tests. Having a dedicated suite allows us to confidently refactor or add features (like the future Collection composition refactor) with a safety net.

Future Considerations (Out of Scope for now):

Collection Composition: Moving from extends Collection to using a Collection (composition over inheritance) is the big architectural shift needed. This will likely simplify the API surface of Store and separate "storage" concerns from "model/proxy" concerns.

afterSetData Logic: The behavior where setting data appends instead of replacing (if oldValue is null) is a bit quirky. A future cleanup might want to standardize data as "replace content" vs add as "append".

Type Safety: The return types of add/insert are dynamic (number vs Record[]). While documented, this polymorphism can be a source of bugs. The new config makes it more predictable per-instance, but the method signature is still polymorphic.

Overall, the Store is in a much better place for immediate usage, especially for high-performance use cases.