What is the Neural Link?

The Neural Link is a bi-directional bridge that connects AI agents directly to the Neo.mjs runtime. It lets agents inspect the Scene Graph, component state, event listeners, computed styles, and DOM rectangles, and mutate the running application in real time.

Why is Neo.mjs called an Application Engine instead of a framework?

Neo.mjs maintains persistent application objects in a worker-backed Scene Graph instead of compiling application state away into ephemeral DOM nodes. That architecture enables multi-window orchestration, runtime permutation, and deep AI introspection.

What is Context Engineering?

Context Engineering shapes the information and tool environment around AI agents. Neo.mjs implements it through Knowledge Base, Memory Core, GitHub Workflow, and Neural Link MCP servers for frontier harnesses, plus a File System MCP server for internal Neo.ai.Agent local loops.

What is the Neo.mjs Agent OS?

The Neo.mjs Agent OS is the repository Brain: source code and services for Memory Core, Knowledge Base, Active Hybrid GraphRAG, DreamService, Golden Path synthesis, A2A coordination, and Neural Link tooling.

Frontmatter

id	9994
title	Align Guide Gap Inference with Concepts instead of Files
state	Closed
labels	enhancementai
assignees	neo-gpt
createdAt	Apr 14, 2026, 10:19 AM
updatedAt	Jun 7, 2026, 6:28 PM
githubUrl	https://github.com/neomjs/neo/issues/9994
author	tobiu
commentsCount	0
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jun 7, 2026, 6:28 PM

Align Guide Gap Inference with Concepts instead of Files

Closed v13.0.0/archive-v13-0-0-chunk-4 enhancementai

tobiu commented on Apr 14, 2026, 10:19 AM

Description

The current GUIDE_GAP inference incorrectly maps architectural guides 1-to-1 with isolated structural files. This is fundamentally disconnected from how learning materials are generated: we need learning section guides for concepts (e.g., "Reactivity", "Shared Canvas"), not purely files. For instance, Canvas has multiple related guides mapped in learn/tree.json.

Objective

Refactor Guide Gap detection in DreamService to target the semantic learn/tree.json topics and high-level architectural concepts.
Ensure complex concepts like "Reactivity" or "Shared Canvas" can conceptually satisfy gap requirements across multiple interconnected network topologies in the Graph.

tobiu added the enhancement label on Apr 14, 2026, 10:19 AM

tobiu added the ai label on Apr 14, 2026, 10:19 AM

tobiu referenced in commit 60150a8 - "docs(agentos): align guide gap docs with concept ontology (#9994) (#12681)" on Jun 7, 2026, 6:28 PM

tobiu closed this issue on Jun 7, 2026, 6:28 PM