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	8420
title	Fix Knowledge Base Indexing and Scoring for Source Code
state	Closed
labels	bugai
assignees	tobiu
createdAt	Jan 8, 2026, 1:02 PM
updatedAt	Jan 8, 2026, 1:05 PM
githubUrl	https://github.com/neomjs/neo/issues/8420
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 8, 2026, 1:05 PM

Fix Knowledge Base Indexing and Scoring for Source Code

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

Closed v11.19.0 bugai

tobiu commented on Jan 8, 2026, 1:02 PM

The recent switch to SourceParser (Issue #8342) broke the inheritance chain resolution in VectorService and the scoring logic in QueryService.

Issues:

SourceParser does not extract/emit className or extends metadata in the chunks.
VectorService looks for chunk.kind === 'class' to build the inheritance map, which no longer exists.
QueryService boosts scores for metadata.type === 'class', but source files now have type === 'src'.

Tasks:

Update SourceParser.mjs:
- Extract className and superClass from the AST.
- Include className and extends metadata in all generated chunks.
Update VectorService.mjs:
- Adapt logic to read className and extends from the new chunk structure to rebuild the inheritance map.
Update QueryService.mjs:
- Adjust scoring logic to recognize type: 'src' and boost based on className match (replacing the dead type === 'class' check).

Goal: Restore intelligent scoring and inheritance-based boosting for source code queries.

tobiu added the bug label on Jan 8, 2026, 1:02 PM

tobiu added the ai label on Jan 8, 2026, 1:02 PM

tobiu assigned to @tobiu on Jan 8, 2026, 1:02 PM

tobiu referenced in commit b284f2e - "fix: KB indexing & scoring for source code (#8420)" on Jan 8, 2026, 1:04 PM

tobiu Jan 8, 2026, 1:04 PM

Input from Gemini 3 Pro:

✦ I have refactored SourceParser, VectorService, and QueryService to correctly handle source code indexing.

Changes:

SourceParser.mjs: Now extracts className and extends from the AST and injects them into every chunk generated for a class file.

VectorService.mjs: Updated to build the inheritance map using the module-context chunks (which now contain the metadata) and applies the chain to all chunks with a className.

QueryService.mjs: Removed the obsolete metadata.type === 'class' check. It now correctly boosts scores based on metadata.className matches, ensuring src files are properly ranked.

This restores the "Inheritance Boosting" and class-name relevance scoring that was lost during the switch to source code parsing.

tobiu closed this issue on Jan 8, 2026, 1:05 PM