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	9118
title	DevIndex: Enhance Updater with Private Contributions & Metadata
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Feb 12, 2026, 9:04 PM
updatedAt	Feb 12, 2026, 9:09 PM
githubUrl	https://github.com/neomjs/neo/issues/9118
author	tobiu
commentsCount	2
parentIssue	9106
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Feb 12, 2026, 9:09 PM

DevIndex: Enhance Updater with Private Contributions & Metadata

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

Closed v12.0.0 enhancementai

tobiu commented on Feb 12, 2026, 9:04 PM

This task covers the enhancement of the DevIndex Updater service to improve data accuracy and enrich the user index with valuable metadata.

Problem:

Data Integrity: Users with significant private contributions (but low public activity) were being pruned from the index because the previous logic only counted public contributions.
Missing Metadata: The index lacked professional signals like "Hireable" status, "Sponsors", and direct links (Website, Twitter), which are high-value for recruiters and analysis.

Changes:

Private Contributions: The Updater now fetches restrictedContributionsCount (private contributions) from the GitHub GraphQL API.
New Data Fields:
- py (Private Years): An array storing private contribution counts per year.
- tc (Total Contributions): Now correctly includes private contributions.
- y (Yearly Totals): Now represents the sum of Public + Private contributions.
Metadata Enrichment: The Updater now captures and maps:
- h (isHireable): Boolean (1/0).
- s (hasSponsorsListing): Boolean (1/0).
- t (twitterUsername): String.
- w (websiteUrl): String.

Impact:

Prevents pruning of high-value enterprise/private contributors.
Enables new frontend features: "Private Mode" toggle, "Hireable" filter, and direct social links.

tobiu added the enhancement label on Feb 12, 2026, 9:04 PM

tobiu added the ai label on Feb 12, 2026, 9:04 PM

tobiu assigned to @tobiu on Feb 12, 2026, 9:04 PM

tobiu added parent issue #9106 on Feb 12, 2026, 9:04 PM

tobiu referenced in commit 72fa39e - "feat: Enhance Updater with Private Contributions & Metadata (#9118) on Feb 12, 2026, 9:05 PM

tobiu Feb 12, 2026, 9:06 PM

Input from Gemini 3 Pro:

✦ I have enhanced the Updater service to include private contributions and professional metadata.

Changes:

Private Contributions: Added restrictedContributionsCount to the GraphQL query.

New Data Fields:

py: Array of private contribution counts per year.

tc: Total contributions now includes private counts.

y: Yearly totals now sum public + private.

Metadata: Added mapping for h (isHireable), s (hasSponsorsListing), t (twitterUsername), and w (websiteUrl).

This update ensures high-value users are not pruned due to private activity and provides rich data for the frontend.

tobiu Feb 12, 2026, 9:06 PM

Input from Gemini 3 Pro:

✦ I have also investigated and fixed the data integrity issue where 869 users were missing from tracker.json.

Root Cause: The previous exclusion of private contributions caused these users to fail the contribution threshold, leading to them being pruned from the tracker but not the rich data store.

Fix:

Created and ran apps/devindex/services/fixTrackerConsistency.mjs to restore the missing users to tracker.json.

The enhanced Updater logic (above) will now correctly calculate their total contributions, preventing future false-positive pruning.

Added missing_users.json (temporarily) to track the affected accounts.

This task is now complete.

tobiu referenced in commit edc91b0 - "fix: Restore 869 missing users to tracker.json (#9118) on Feb 12, 2026, 9:08 PM

tobiu closed this issue on Feb 12, 2026, 9:09 PM