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	9125
title	DevIndex: Stop Cleanup.mjs from pruning orphaned tracker users
state	Closed
labels	bugai
assignees	tobiu
createdAt	Feb 12, 2026, 11:08 PM
updatedAt	Feb 12, 2026, 11:26 PM
githubUrl	https://github.com/neomjs/neo/issues/9125
author	tobiu
commentsCount	2
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Feb 12, 2026, 11:26 PM

DevIndex: Stop Cleanup.mjs from pruning orphaned tracker users

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

Closed v12.0.0 bugai

tobiu commented on Feb 12, 2026, 11:08 PM

The Cleanup.mjs service currently deletes users from tracker.json if they have a lastUpdate timestamp but are missing from users.json. This logic was intended to prune "low value" users. However, with the new "Penalty Box" feature (#9121), users who fail to update (e.g. 502/504) also get a lastUpdate timestamp but are not added to users.json. Result: Cleanup.mjs deletes these failed users, causing them to be lost from the queue. When rediscovered by the spider, they are treated as "new" and re-scanned immediately, wasting API quota.

Solution:

Stop pruning orphaned users from tracker.json.
Keep them in the tracker to ensure they are processed according to their lastUpdate timestamp (i.e., at the back of the queue).
Add logging to identify these orphaned users for debugging.

tobiu added the bug label on Feb 12, 2026, 11:08 PM

tobiu added the ai label on Feb 12, 2026, 11:08 PM

tobiu referenced in commit 8bd44bd - "feat: Implement 'Penalty Box' via sidecar file for failed updates (#9125) on Feb 12, 2026, 11:24 PM

tobiu Feb 12, 2026, 11:25 PM

Input from Gemini 3 Pro:

✦ I have implemented the "Penalty Box" logic using a sidecar file (failed.json) instead of bloating the tracker.

Changes:

Storage: Added failed.json (defaults to []) and methods getFailed() / updateFailed().

Updater:

When a user update fails, they are added to failed.json.

When a user update succeeds, they are removed from failed.json.

Users are still pushed to the back of the tracker queue (timestamp updated).

Cleanup:

Re-enabled "Active Pruning" for orphaned users (those in tracker but not in users).

Crucially, added a check: if an orphan is in failed.json, they are KEPT in the tracker (protected).

Logs explicit warnings when keeping a failed user or pruning a non-failed orphan.

Data Recovery: I manually identified the 27 users who were about to be pruned in the previous run and added them to failed.json to ensure they are not lost.

This approach keeps tracker.json lean while ensuring robust retry logic for problematic users.

tobiu assigned to @tobiu on Feb 12, 2026, 11:25 PM

tobiu Feb 12, 2026, 11:26 PM

Input from Gemini 3 Pro:

✦ I am closing this issue as I have implemented the fix and pushed the changes. I have also verified the fix by running the cleanup script with the manually populated failed.json list, confirming that the users are now correctly identified and kept in the tracker.

tobiu closed this issue on Feb 12, 2026, 11:26 PM