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	9096
title	Feat: GitHub API Secondary Rate Limit Handling & Concurrency Tuning
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Feb 10, 2026, 9:09 PM
updatedAt	Feb 11, 2026, 3:02 PM
githubUrl	https://github.com/neomjs/neo/issues/9096
author	tobiu
commentsCount	1
parentIssue	8930
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Feb 10, 2026, 9:22 PM

Feat: GitHub API Secondary Rate Limit Handling & Concurrency Tuning

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

Closed v12.0.0 enhancementai

tobiu commented on Feb 10, 2026, 9:09 PM

Objective

Enhance the stability of the DevRank Updater service by implementing smarter handling for GitHub's Secondary Rate Limits (403 Forbidden / Abuse Detection) and tuning concurrency.

Problem

The Updater is experiencing sporadic bursts of 403 errors despite having plenty of primary API quota remaining (e.g., 4700/5000). This indicates we are triggering GitHub's "Abuse Detection" or "Secondary Rate Limit" due to high concurrency (10 parallel requests) or complex GraphQL queries.

Tasks

Tune Concurrency: Reduce Updater.mjs concurrency from 10 to 5. This is a safer baseline for complex GraphQL fetching.
Smart 403 Handling: Update GitHub.mjs:
- Inspect headers on 403. If x-ratelimit-remaining > 0, treat it as a Secondary Limit.
- Implement a specific backoff strategy for Secondary Limits (e.g., wait 30s-60s) instead of the standard short retry.
- Log a distinct warning ("Abuse Detection triggered") to differentiate from quota exhaustion.

References

GitHub Docs: Secondary Rate Limits

tobiu added the enhancement label on Feb 10, 2026, 9:09 PM

tobiu added the ai label on Feb 10, 2026, 9:09 PM

tobiu added parent issue #8930 on Feb 10, 2026, 9:09 PM

tobiu referenced in commit 699b488 - "feat: Enhance GitHub API Concurrency and Rate Limit Handling (#9096)" on Feb 10, 2026, 9:20 PM

tobiu Feb 10, 2026, 9:21 PM

Input from Gemini 3 Pro:

✦ I have implemented the concurrency tuning and smart rate limit handling.

Changes

Updater.mjs: Set concurrency to 8. This is a balanced middle ground between the previous aggressive 10 and conservative 5.

GitHub.mjs: Implemented smart 403 detection. If x-ratelimit-remaining > 0 (indicating secondary limit/abuse detection), the service now logs a warning and backs off for 10 seconds before retrying. This allows the pipeline to "dance" with the API limits rather than crashing or crawling.

This should stabilize the data enrichment process while maintaining high throughput.

tobiu closed this issue on Feb 10, 2026, 9:22 PM

tobiu assigned to @tobiu on Feb 11, 2026, 3:02 PM