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	9875
title	Docs: Refine AI infrastructure scale and boundaries in CodebaseOverview
state	Closed
labels	documentationenhancementai
assignees	tobiu
createdAt	Apr 11, 2026, 10:21 AM
updatedAt	Apr 12, 2026, 7:01 PM
githubUrl	https://github.com/neomjs/neo/issues/9875
author	tobiu
commentsCount	0
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Apr 11, 2026, 10:26 AM

Docs: Refine AI infrastructure scale and boundaries in CodebaseOverview

Closed v13.0.0/archive-v13-0-0-chunk-3 documentationenhancementai

tobiu commented on Apr 11, 2026, 10:21 AM

Description

The CodebaseOverview.md guide is outdated regarding the current AI infrastructure topology and scale.

Proposed Changes

Enhance the MCP Server section to outline the expansion from 3 to 5 active servers (adding the Neural Link server and the File System server specifically optimized for Neo local agents, distinguishing them from generic Claude/Gemini CLI file tools).
Explicitly document the architectural boundary between the Browser-based Frontend Application Engine and the Node.js Agent OS SDK, clarifying that they remain isolated and bridge exclusively via the Neural Link using JSON-RPC.
Enhance Neural Link details to encompass Whitebox E2E testing capabilities along with standard introspection.
Update the Memory Core/DreamService overview to detail the Hybrid RAG implementation, the transition to the SQLite-based Native Graph DB, and the integration of local SLMs like gemma4-31b for Subagents and the Librarian daemon.

tobiu added the documentation label on Apr 11, 2026, 10:21 AM

tobiu added the enhancement label on Apr 11, 2026, 10:21 AM

tobiu added the ai label on Apr 11, 2026, 10:21 AM

tobiu referenced in commit 0374e0a - "docs: Refine AI infrastructure scale and boundaries in CodebaseOverview (#9875)" on Apr 11, 2026, 10:22 AM

tobiu cross-referenced by PR #9876 on Apr 11, 2026, 10:22 AM

tobiu closed this issue on Apr 11, 2026, 10:26 AM

tobiu referenced in commit d1aa13a - "Docs: Refine AI infrastructure scale and boundaries in CodebaseOverview (#9876) on Apr 11, 2026, 10:26 AM

tobiu cross-referenced by #9892 on Apr 11, 2026, 9:23 PM

tobiu cross-referenced by PR #9897 on Apr 12, 2026, 10:10 AM

tobiu assigned to @tobiu on Apr 12, 2026, 7:01 PM