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	8342
title	Switch Knowledge Base to Source Code Indexing (SourceParser)
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Jan 5, 2026, 11:57 PM
updatedAt	Jan 6, 2026, 12:04 AM
githubUrl	https://github.com/neomjs/neo/issues/8342
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 6, 2026, 12:04 AM

Switch Knowledge Base to Source Code Indexing (SourceParser)

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

Closed v11.19.0 enhancementai

tobiu commented on Jan 5, 2026, 11:57 PM

Switch the API knowledge source from docs/output/all.json (JSDoc JSON) to raw src/**/*.mjs files.

Goal: Provide the AI with implementation details and context, not just API signatures. Reduce vector cardinality by grouping cohesive units.

Plan:

Create ai/mcp/server/knowledge-base/parser/SourceParser.mjs:
- Use acorn to parse .mjs files.
- Chunking Strategy:
  - Module Context: Imports + Module-level variables (e.g., const symbol = ...) + Class Header (JSDoc + Class definition).
  - Class Properties: Static and instance fields defined on the class body (e.g., static observable = true, myProp = 0) excluding the config object.
  - Config Block: The entire static config = { ... } object as a single chunk.
  - Methods: Individual methods (Body + JSDoc).
- Metadata: Include line numbers (line_start, line_end) for future "open in editor" features.
Update ApiSource.mjs:
- Change target from docs/output/all.json to src/.
- Use SourceParser for parsing .mjs files.
- Retain deterministic sorting.
Cleanup:
- Remove ApiParser.mjs (the JSDoc JSON parser).

Note: This relies on the acorn dependency which is already present (used by TestParser).

tobiu added the enhancement label on Jan 5, 2026, 11:57 PM

tobiu added the ai label on Jan 5, 2026, 11:57 PM

tobiu assigned to @tobiu on Jan 5, 2026, 11:57 PM

tobiu referenced in commit 0e0ac53 - "Enhancement: Switch Knowledge Base to Source Code Indexing #8342 on Jan 6, 2026, 12:03 AM

tobiu Jan 6, 2026, 12:03 AM

Input from Gemini 3 Pro:

✦ I have successfully switched the Knowledge Base indexing strategy from JSDoc JSON to raw Source Code.

Changes Implemented:

Created SourceParser.mjs:

Uses acorn to parse .mjs files into an AST.

Chunking Strategy:

Module Context: Captures imports, top-level variables, and the class header (JSDoc + Class Declaration).

Class Properties: Groups static and instance fields (e.g., static observable, myProp = 0) that are not part of the config block.

Config Block: Extracts the entire static config = { ... } object as a single, cohesive chunk.

Methods: Extracts individual methods (Body + JSDoc) with line number metadata.

Updated ApiSource.mjs:

Now targets the src/ directory instead of docs/output/all.json.

Recursively scans for .mjs files.

Uses SourceParser to generate chunks.

Maintains the previously added deterministic sorting.

Deleted ApiParser.mjs:

Removed the obsolete parser that relied on jsdoc-api output.

This change upgrades the AI's understanding from purely API-based (signatures and descriptions) to implementation-based (logic and patterns), while also reducing vector cardinality by grouping related configurations.

tobiu closed this issue on Jan 6, 2026, 12:04 AM

tobiu cross-referenced by #8420 on Jan 8, 2026, 1:02 PM