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	8330
title	[Neural Link] Fix find_instances regression (Client mapping & OpenAPI)
state	Closed
labels	bugai
assignees	tobiu
createdAt	Jan 5, 2026, 12:19 PM
updatedAt	Jan 5, 2026, 12:24 PM
githubUrl	https://github.com/neomjs/neo/issues/8330
author	tobiu
commentsCount	1
parentIssue	8169
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 5, 2026, 12:24 PM

[Neural Link] Fix find_instances regression (Client mapping & OpenAPI)

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

Closed v11.18.0 bugai

tobiu commented on Jan 5, 2026, 12:19 PM

Fix regression from previous session where find_instances was not fully integrated.

Tasks:

Client Mapping: Add find_instances to the serviceMap in src/ai/Client.mjs to route requests to InstanceService.
OpenAPI Fix: Investigate and fix the openapi.yaml file validation error that is preventing the Neural Link MCP server from starting.

tobiu added the bug label on Jan 5, 2026, 12:19 PM

tobiu added the ai label on Jan 5, 2026, 12:19 PM

tobiu added parent issue #8169 on Jan 5, 2026, 12:20 PM

tobiu assigned to @tobiu on Jan 5, 2026, 12:20 PM

tobiu referenced in commit 12898b6 - "Fix find_instances regression: Add missing Client mapping and Server implementation #8330" on Jan 5, 2026, 12:24 PM

tobiu Jan 5, 2026, 12:24 PM

Input from Gemini 3 Pro:

✦ I have fixed the regression.

Fixes:

Server Startup Crash: The Neural Link server was failing to start because toolService.mjs was attempting to bind find_instances to InstanceService.findInstances, which was undefined. I have implemented the missing findInstances method in ai/mcp/server/neural-link/services/InstanceService.mjs.

Client Mapping: I have added the missing find_instances mapping to the serviceMap in src/ai/Client.mjs, ensuring client-side requests are correctly routed.

OpenAPI Integrity: I verified openapi.yaml and confirmed the schema is correct. The "corrupted shapes" error was likely a side effect of the server crashing before it could fully validate the schema or due to the missing method reference.

tobiu closed this issue on Jan 5, 2026, 12:24 PM