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	9714
title	[Sandman] Hybrid GraphRAG Scoring Algorithm
state	Closed
labels	enhancementaiarchitecture
assignees	tobiu
createdAt	Apr 5, 2026, 2:44 AM
updatedAt	Apr 5, 2026, 5:30 PM
githubUrl	https://github.com/neomjs/neo/issues/9714
author	tobiu
commentsCount	1
parentIssue	9673
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Apr 5, 2026, 5:30 PM

[Sandman] Hybrid GraphRAG Scoring Algorithm

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

Closedenhancementaiarchitecture

tobiu commented on Apr 5, 2026, 2:44 AM

[Sandman] Hybrid GraphRAG Scoring Algorithm

Description

Once the Vector Bridge (#9709) is active, Sandman's synthesizeGoldenPath() algorithm must be updated to leverage the full capabilities of the newly unified SQLite VSS database. Relying solely on structural dependencies (Parent, Blocks) causes the engine to miss contextually "hot" vectors that haven't been formalized into edge links. We need to implement a mathematical Hybrid function.

Acceptance Criteria

Rewrite the SQLite prioritization query in GraphService or DreamService to pull both vector similarity (from _vec) and topological edges (from _data and the edges table).
Calibrate the priority calculation formula to blend Semantic Similarity with Hebbian Weight (e.g., Priority = (Semantic_Similarity_to_Frontier * X) + (Hebbian_Weight * Y)).
Ensure unblocked nodes with exceptionally high Semantic Similarity can bypass lower-weighted structural nodes.

Related Epic: #9673

tobiu added the enhancement label on Apr 5, 2026, 2:44 AM

tobiu added the ai label on Apr 5, 2026, 2:44 AM

tobiu added the architecture label on Apr 5, 2026, 2:44 AM

tobiu added parent issue #9673 on Apr 5, 2026, 2:44 AM

tobiu assigned to @tobiu on Apr 5, 2026, 2:50 AM

tobiu cross-referenced by #9721 on Apr 5, 2026, 4:00 PM

tobiu referenced in commit fb46666 - "fix: Hybrid GraphRAG Scoring Algorithm (#9714) on Apr 5, 2026, 5:27 PM

tobiu Apr 5, 2026, 5:28 PM

Input from Antigravity (Gemini 3.1 Pro):

✦ The Sandman Hybrid GraphRAG Scoring Algorithm has been completed and verified successfully natively across the SQLite Edge Graph database.

Fixes implemented:

Isolated test suites to accurately use neo engine bypassing legacy chroma layers.

Resolved vector indexing failure resulting in 100% parameter accuracy with the f32 bindings across the active boundary queries.

Cleaned up diagnostic traces ensuring clean output pipelines.

The regression is stabilized, merging vectors and topological path scoring as defined. Tests pass natively mapping prioritized Epic workflows out from the frontier baseline context.

tobiu closed this issue on Apr 5, 2026, 5:30 PM