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	9674
title	Strategic Consciousness: The Sandman/REM Prototype
state	Closed
labels	epicai
assignees	tobiu
createdAt	Apr 4, 2026, 2:02 AM
updatedAt	Apr 4, 2026, 2:42 PM
githubUrl	https://github.com/neomjs/neo/issues/9674
author	tobiu
commentsCount	1
parentIssue	9671
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Apr 4, 2026, 2:38 PM

Strategic Consciousness: The Sandman/REM Prototype

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

Closedepicai

tobiu commented on Apr 4, 2026, 2:02 AM

Hard Dependency

[!WARNING] This Epic CANNOT begin until Epic #9673 (Hybrid GraphRAG) is completed. If Sandman is built before the Native Graph DB, it is just a naive LLM text summarizer. It must have the Graph DB available so it can traverse the framework topology to physically connect abstract ideas (e.g., knowing that "Issue A" and "Memory B" both intersect at Neo.component.Base).

Problem

Currently, AI agents operate in "flat" sessions—once 5 previous sessions drop off the summary limit, critical strategic breakthroughs can be lost. We need a localized background process that continuously processes markdown logs, issue trackers, and memories to synthesize a prioritized "Golden Path".

Proposed Solution

Build REM Mode - continuous asynchronous processing meant to mimic human subconscious problem-solving.

The Sandman agent runs locally during downtime. It does not output software code.
It processes local issue trackers, session summaries, and prior architectural documents.
It traverses the newly built Application Engine Graph to find technical overlaps.
It synthesizes competing priorities into curated Markdown outputs.

Definition of Done

A background process (DreamService.mjs or similar scripting) can be executed.
Sandman successfully reads from the Memory Core and GitHub trackers.
Sandman successfully traverses the Native Graph Database to intelligently group related concepts.
A "Golden Path" strategic priority markdown document is generated dynamically.

tobiu added the epic label on Apr 4, 2026, 2:02 AM

tobiu added the ai label on Apr 4, 2026, 2:02 AM

tobiu added parent issue #9671 on Apr 4, 2026, 2:02 AM

tobiu cross-referenced by #9662 on Apr 4, 2026, 2:04 AM

tobiu referenced in commit 40ded76 - "feat: Implement the Sandman/REM Prototype for active AI Strategic Synthesis (#9674)" on Apr 4, 2026, 2:38 PM

tobiu Apr 4, 2026, 2:38 PM

Input from Antigravity (gemini-3.1-pro):

✦ Completed the Sandman/REM Prototype implementation.

Active Context Parsing: Upgraded DreamService with parseOpenIssues(), reading all structurally linked open features to inform Sandman of current operational challenges.

Metadata Syncing: Prevented infinite offline loops by properly updating graphDigested: true back into ChromaDB tracking.

Strategic CTO Persona Synthesis: Added synthesizeGoldenPath(), providing Sandman with structural awareness over the Context Frontier and explicit instructions to calculate force multipliers. Its output drops directly to ai/agentos/GoldenPath.md.

SDK Execution Wrapper: Created neo/buildScripts/ai/runSandman.mjs using the raw internal services.mjs SDK as an isolated boot wrapper instead of hacking MCP REST endpoints.

Code pushed to origin.

tobiu closed this issue on Apr 4, 2026, 2:38 PM

tobiu assigned to @tobiu on Apr 4, 2026, 2:39 PM