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	9119
title	DevIndex: Add Scheduled Hourly Updater Workflow
state	Closed
labels	enhancementaibuild
assignees	tobiu
createdAt	Feb 12, 2026, 9:31 PM
updatedAt	Feb 12, 2026, 9:32 PM
githubUrl	https://github.com/neomjs/neo/issues/9119
author	tobiu
commentsCount	1
parentIssue	9106
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Feb 12, 2026, 9:32 PM

DevIndex: Add Scheduled Hourly Updater Workflow

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

Closed v12.0.0 enhancementaibuild

tobiu commented on Feb 12, 2026, 9:31 PM

This task implements a scheduled GitHub Actions workflow to keep the DevIndex data fresh.

Objective: Run the DevIndex.services.Updater automatically on an hourly basis to update user profiles and contribution stats.

Strategy:

Schedule: Hourly (cron: '0 * * * *').
Batch Size: Limit to 200 users per run.
- Rationale: This stays safely within the 1,000 req/hour limit for public repositories, even accounting for 2-4x retry logic on errors.
- Throughput: ~4,800 updates/day -> ~3 day full refresh cycle for 15k users.
Persistence: The workflow will commit changes to users.jsonl and tracker.json back to the dev branch.

Implementation:

Create .github/workflows/devindex-updater.yml
Use stefanzweifel/git-auto-commit-action for reliable committing.
Use concurrency to prevent overlapping runs.

tobiu added the enhancement label on Feb 12, 2026, 9:31 PM

tobiu added the ai label on Feb 12, 2026, 9:31 PM

tobiu added the build label on Feb 12, 2026, 9:31 PM

tobiu assigned to @tobiu on Feb 12, 2026, 9:31 PM

tobiu added parent issue #9106 on Feb 12, 2026, 9:31 PM

tobiu referenced in commit 9578cf8 - "feat: Add hourly DevIndex updater workflow (#9119) on Feb 12, 2026, 9:32 PM

tobiu Feb 12, 2026, 9:32 PM

Input from Gemini 3 Pro:

✦ I have implemented the scheduled workflow in .github/workflows/devindex-updater.yml.

Configuration:

Schedule: Hourly (0 * * * *).

Command: npm run devindex:update -- --limit=200

Safety: concurrency group ensures only one update runs at a time.

Persistence: Uses git-auto-commit-action to push changes to users.jsonl and tracker.json back to the dev branch.

This setup should robustly handle the "Safe 200" batch size, maintaining index freshness without risking rate limits.

tobiu closed this issue on Feb 12, 2026, 9:32 PM