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	9822
title	Fix Regression in DreamService Golden Path Inference Tests
state	Closed
labels	bugai
assignees	tobiu
createdAt	Apr 9, 2026, 1:54 PM
updatedAt	Apr 9, 2026, 2:48 PM
githubUrl	https://github.com/neomjs/neo/issues/9822
author	tobiu
commentsCount	2
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Apr 9, 2026, 1:54 PM

Fix Regression in DreamService Golden Path Inference Tests

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

Closedbugai

tobiu commented on Apr 9, 2026, 1:54 PM

Problem Context

During the recent DreamService migration to a background daemon, the test file DreamService.spec.mjs was moved and its tests were updated to include native Golden Path Guide Gaps. However, there were remnants of tests using the deprecated file system proxy approach (e.g. expect(appendedContent.length)), and the deduplication test was failing to accurately trigger synthesizeGoldenPath().

Fix Description

Merged the Golden Path duplicates/idempotence check directly into the correctly mocked synthesizeGoldenPath unit test to prevent SQLiteVectorManager crash.
Transitioned capability gap assertions to read from the strictly typed native SQLite Db properties (GraphService.db.nodes.get().properties.capabilityGap) instead of the mock file array proxy.
Verified final export pipeline in ai/services.mjs for the migrated DreamService daemon to prevent pipeline failures for upstream agents.

tobiu added the bug label on Apr 9, 2026, 1:54 PM

tobiu added the ai label on Apr 9, 2026, 1:54 PM

tobiu referenced in commit f29e49b - "fix: Resolve DreamService Golden Path test drift and SDK export pipeline (#9822)" on Apr 9, 2026, 1:54 PM

tobiu assigned to @tobiu on Apr 9, 2026, 1:54 PM

tobiu Apr 9, 2026, 1:54 PM

Successfully resolved Golden Path deduplication regression in DreamService.spec.mjs by accurately targeting SQLite graph properties instead of legacy file I/O mocks. Migrated DreamService is now exposed natively via the ai/services.mjs SDK.

tobiu closed this issue on Apr 9, 2026, 1:54 PM

tobiu referenced in commit ace94ae - "fix(ai): Stable DreamService Memory Core integration (#9822)" on Apr 9, 2026, 2:47 PM

tobiu Apr 9, 2026, 2:48 PM

Input from Gemini 3.1 Pro (Antigravity):

✦ The DreamService vector fallback errors and capability gap reporting have been fully resolved with native local processing.

Key Changes:

Migrated legacy QueryService calls to a direct lexical matched search within the SQLite GraphService.db.nodes.items list, retaining LLM semantic validation from local .md sources directly rather than querying the ChromaDB layer.

Fixed a boolean error in [TEST_GAP] evaluation (n.label -> n.type) which caused aggressive false positives resulting from empty array outputs.

Synchronized terminal output to properly reference Memory Core instead of ChromaDB as per new architectural rules.

Included an idempotent deduplication filter inside synthesizeGoldenPath() outputs.

The execution was verified completely successful through the Sandman runner module npm run ai:run-sandman, showing full local resolution and avoiding legacy failure warnings. This successfully achieves our "100% Native Edge Graph" directive!