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	9251
title	Enhance Location Normalizer and Document Macro-Economic Insights
state	Closed
labels	documentationenhancementai
assignees	tobiu
createdAt	Feb 22, 2026, 2:34 PM
updatedAt	Feb 22, 2026, 2:40 PM
githubUrl	https://github.com/neomjs/neo/issues/9251
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Feb 22, 2026, 2:40 PM

Enhance Location Normalizer and Document Macro-Economic Insights

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

Closed v12.0.0 documentationenhancementai

tobiu commented on Feb 22, 2026, 2:34 PM

The DevIndex data reveals striking disparities in open-source contributions across different countries (e.g., Germany vs. India/China). This data tells a powerful macro-economic policy story regarding FOSS funding and ecosystem fragmentation.

Tasks:

Enhance LocationNormalizer.mjs: Expand the cityMap to include major tech hubs in India (Hyderabad, Pune, Chennai, etc.), China (Hangzhou, Chengdu, Guangzhou, etc.), and other global centers. Fix the "Stanford, CA" collision bug where it falsely maps to Canada (CA).
Re-parse the existing users.jsonl database with the updated normalizer to ensure the most accurate country counts.
Update learn/guides/devindex/Introduction.md to highlight the specific macro-economic disparities (using Germany, US, UK, China, and India as examples). Emphasize how this exposes the lack of government support in some regions versus ecosystem fragmentation in others.
Update learn/guides/devindex/data-factory/DataEnrichment.md to explicitly mention that the LocationNormalizer requires continuous curation to avoid Western-centric bias.

tobiu added the documentation label on Feb 22, 2026, 2:34 PM

tobiu added the enhancement label on Feb 22, 2026, 2:34 PM

tobiu added the ai label on Feb 22, 2026, 2:34 PM

tobiu assigned to @tobiu on Feb 22, 2026, 2:34 PM

tobiu referenced in commit a850068 - "feat: Enhance LocationNormalizer and update macro-economic docs (#9251)" on Feb 22, 2026, 2:40 PM

tobiu Feb 22, 2026, 2:40 PM

Input from Gemini 3 Pro:

✦ I have completed the tasks outlined in this issue:

Significantly expanded the LocationNormalizer.mjs cityMap to include major tech hubs across China, India, and global centers, resolving the "Stanford, CA" collision bug by explicitly mapping it to the US.

Wrote and executed a script to re-parse the 50,000 active users in users.jsonl through the updated normalizer, resulting in updated country representations (e.g., DE: 2,659, IN: 1,042, CN: 2,850).

Rewrote the "Data Science Use Cases" section in learn/guides/devindex/Introduction.md to highlight the macro-economic reality check. The section now details the per-capita overperformance of Germany and the UK versus the structural gaps in India and ecosystem fragmentation in China.

Added a "Curatorial Caveat" note to learn/guides/devindex/data-factory/DataEnrichment.md emphasizing the need to continually expand the city map to avoid Western-centric bias.

Changes committed and pushed to the dev branch. Closing the issue.

tobiu closed this issue on Feb 22, 2026, 2:40 PM