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	6610
title	main.addon.OpenStreetMaps
state	Open
labels	enhancementno auto close
assignees	tobiu
createdAt	Apr 1, 2025, 10:01 PM
updatedAt	Aug 3, 2025, 2:27 PM
githubUrl	https://github.com/neomjs/neo/issues/6610
author	tobiu
commentsCount	2
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]

main.addon.OpenStreetMaps

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

Openenhancementno auto close

tobiu commented on Apr 1, 2025, 10:01 PM

The first step is to verify that we can get a public key (or use it without a key)
We just need support for a basic map and markers

In case this is the case, I would like to create a new addon which is roughly on feature parity with main.addon.GoogleMaps.

tobiu added the enhancement label on Apr 1, 2025, 10:01 PM

tobiu added the no auto close label on Apr 1, 2025, 10:01 PM

tobiu assigned to @tobiu on Apr 1, 2025, 10:01 PM

tobiu cross-referenced by #6611 on Apr 1, 2025, 10:02 PM

TomDakan Aug 3, 2025, 7:21 AM

I think this can be done with the OpenLayers library. The markers would be created as a vector layer on top of a tile layer pulled from OpenStreetMaps as described in this example. It appears that there's no need for an api key to pull tiles from OSM.

I would be interested in working on this.

tobiu Aug 3, 2025, 2:27 PM

@TomDakan You are very welcome to give it a try! I think this specific topic should be fun (a great learning experience), since it covers a wrapper component, a new main thread addon, RPC based cross-thread communication, and the potential for using the new intercept remotes pattern for addons (e.g. easily queue a request to create a map instance until the map lib is loaded).

It might even work to use LLMs (like Gemini CLI) here.

I did use MapboxGL (also based on top of OSM) for the Covid Apps. Feel free to explore existing addons and wrapper components first, and explore how they work (or feed an LLM with it).

One very strong recommendation when it comes to PRs: Keep them as small and targeted as possible. E.g. create sub tickets, like "create the addon base class file" => PR, accepted. Next sub: "add logic for adding markers" => PR.

Submitting a massive PR which would e.g. resolve 8 tickets, but introduce 2 new bugs might end up in a lot of reasoning back and forth to get to a merge-ready state. This could lead to frustration, which can easily get avoided with smaller PRs.

Feel free to ask questions on Slack / Discord, and I can give you more pointers.

Best regards, Tobias