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	10456
title	chore(docs): audit and update README with real LOC metrics (The Million-Line Organism)
state	Closed
labels	documentationai
assignees	neo-opus-ada
createdAt	Apr 28, 2026, 2:40 AM
updatedAt	May 1, 2026, 1:26 PM
githubUrl	https://github.com/neomjs/neo/issues/10456
author	neo-gemini-pro
commentsCount	0
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	May 1, 2026, 1:26 PM

chore(docs): audit and update README with real LOC metrics (The Million-Line Organism)

Closed v13.0.0/archive-v13-0-0-chunk-6 documentationai

neo-gemini-pro commented on Apr 28, 2026, 2:40 AM

Context / Problem

The current README.md states the framework is ~170,000 lines of curated code + documentation. However, this severely underrepresents the true scope of the Neo.mjs substrate.

Neo is a digital organism and an operating system, not just a framework. A massive portion of its "code" is actually cognitive content that the swarm feeds on (issues, discussions, PR reviews, agent skills).

The Real Size (Estimates vs Current)

Component	Estimated Lines	What It Is
Core source (`/src`)	~170k	The engine — workers, components, managers
AI infrastructure (`/ai`)	~20k	MCP servers, daemons, Memory Core, Neural Link
Examples & apps	~150k+	Live demonstrations, harness prototypes
Tests	~100k+	Playwright suites, unit tests
Themes & build	~60k+	CSS, build scripts, tooling
Subtotal (code)	~500k+
Synced GitHub issues	~100k+	Markdown files in `resources/content/issues/`
Discussions	~50k+	Markdown files in `resources/content/discussions/`
PR conversations & reviews	~300k+	Markdown files in `resources/content/pulls/`
Agent skills & protocols	~50k+	`.agent/skills/` references and workflows
Subtotal (content)	~500k+
Total	~1M+ lines	A million-line organism.

Solution / Approach

Audit the actual line counts across the designated directories using bash scripting / cloc to get empirical data.
Update the "A Platform at Scale" section in the README to reflect these accurate, holistic metrics.
Explicitly frame the cognitive content (issues, PRs, skills) as structural code that the swarm relies upon.

Acceptance Criteria

Line counts for code and cognitive content are empirically verified.
README is updated to present the "Million-Line Organism" metric.

tobiu removed the epic label on Apr 30, 2026, 2:16 AM

tobiu added the ai label on Apr 30, 2026, 2:16 AM

tobiu referenced in commit 9f4bb24 - "chore(docs): audit README scale section with empirical LOC across substrate layers (#10456) (#10571) on May 1, 2026, 1:26 PM

tobiu closed this issue on May 1, 2026, 1:26 PM