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	9224
title	Implement maxUsers cap for DevIndex GitHub Spider
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Feb 21, 2026, 2:50 PM
updatedAt	Feb 21, 2026, 3:36 PM
githubUrl	https://github.com/neomjs/neo/issues/9224
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Feb 21, 2026, 3:04 PM

Implement maxUsers cap for DevIndex GitHub Spider

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

Closed v12.0.0 enhancementai

tobiu commented on Feb 21, 2026, 2:50 PM

The DevIndex user database (users.jsonl) has grown to ~20MB (44k users). We need to implement a user cap (maxUsers) to prevent unbounded growth.

The strategy is to maintain a maximum number of users by pruning those with the lowest total contributions when new, higher-contributing users are discovered.

Tasks:

Configuration: Add maxUsers to apps/devindex/services/config.mjs (e.g., default to 50,000).
Spider Adjustment (Spider.mjs): The Spider currently adds any valid discovered user to the Tracker (tracker.json). If we are at the maxUsers cap, the Spider should only add new candidates if they are likely to displace a bottom-tier user. However, since the Spider doesn't fetch full stats, it might need to add them anyway, leaving the evaluation to the Updater. Alternative: The Spider might need a lightweight check, or we just let the Updater handle all pruning.
Updater Adjustment (Updater.mjs): The Updater is where the actual evaluation happens. After fetching a user's stats, if the user meets the minTotalContributions threshold AND the total tracked users exceed maxUsers, the Updater must:
- Compare the new user's total contributions (tc) against the lowest tc in the current users.jsonl.
- If the new user has more, add the new user and prune the bottom user(s) to maintain the cap.
- If the new user has fewer, discard the new user.
Storage adjustments (Storage.mjs): Ensure the sorting and pruning logic is efficient given the file size.

Note: The exact division of labor between Spider (discovery) and Updater (evaluation) needs to be finalized during implementation.

tobiu added the epic label on Feb 21, 2026, 2:50 PM

tobiu added the ai label on Feb 21, 2026, 2:50 PM

tobiu referenced in commit 23c3a28 - "feat(devindex): Implement maxUsers dynamic cap and pruning (#9224)" on Feb 21, 2026, 3:03 PM

tobiu assigned to @tobiu on Feb 21, 2026, 3:04 PM

tobiu Feb 21, 2026, 3:04 PM

Input from Gemini 3 Pro:

✦ I have implemented the maxUsers cap for the DevIndex GitHub spider and updater as requested.

Key Changes:

Added maxUsers: 50000 to the DevIndex Github configuration in apps/devindex/services/config.mjs and configured a path for threshold.json.

Modified Storage.mjs to automatically extract the total contributions of the lowest user when the users.jsonl file hits the maxUsers ceiling, write this value to threshold.json, and slice the array to the top 50,000 entries. It also performs cleanup of tracker.json and failed.json for pruned users.

Updated Updater.mjs to read from threshold.json via a new helper getLowestContributionThreshold(). This allows the Updater to evaluate candidates against a dynamically raising bar (Math.max(config.github.minTotalContributions, threshold)) without incurring the I/O cost of reading the massive 20MB users.jsonl database directly.

The task is now complete, and the changes have been pushed. Closing this issue.

tobiu closed this issue on Feb 21, 2026, 3:04 PM

tobiu removed the epic label on Feb 21, 2026, 3:36 PM

tobiu added the enhancement label on Feb 21, 2026, 3:36 PM