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	9131
title	Fix Spider Bio-Signal Search Query 422 Error
state	Closed
labels	bugai
assignees	tobiu
createdAt	Feb 13, 2026, 2:29 AM
updatedAt	Feb 13, 2026, 2:36 AM
githubUrl	https://github.com/neomjs/neo/issues/9131
author	tobiu
commentsCount	1
parentIssue	9106
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Feb 13, 2026, 2:36 AM

Fix Spider Bio-Signal Search Query 422 Error

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

Closed v12.0.0 bugai

tobiu commented on Feb 13, 2026, 2:29 AM

The Spider's "Bio Signals" discovery strategy fails with a 422 Unprocessable Entity error when executing the search query.

Error:

[Spider] Search Query: topic:women-in-tech OR topic:pyladies OR topic:django-girls OR topic:rails-girls stars:>5 (Sort: updated desc)
[GitHub] REST Request Failed (...): REST Error: 422 Unprocessable Entity

Cause: The query string construction in Spider.js manually concatenates parameters while also using encodeURIComponent on the query itself. However, the GitHub.js service also expects a clean endpoint. The specific combination of OR operators and topic qualifiers in the q parameter, when passed through the existing GitHub.rest method, results in a malformed request URL that the GitHub API rejects.

Fix: Refactor Spider.mjs to construct the search URL correctly, ensuring the q parameter is properly encoded but the surrounding API parameters (sort, order, per_page) remain valid structure. We should likely verify if GitHub.rest handles encoding or if we need to pre-encode the query string safely.

Specifically, we need to ensure the space-separated OR operators are encoded as %20 or +, but not double-encoded or malformed.

tobiu added the bug label on Feb 13, 2026, 2:29 AM

tobiu added the ai label on Feb 13, 2026, 2:29 AM

tobiu assigned to @tobiu on Feb 13, 2026, 2:29 AM

tobiu added parent issue #9106 on Feb 13, 2026, 2:29 AM

tobiu referenced in commit 423ec20 - "fix(devindex): Resolve Bio-Signal search 422 error (#9131)" on Feb 13, 2026, 2:35 AM

tobiu Feb 13, 2026, 2:35 AM

Input from Gemini 3 Pro:

✦ I have fixed the 422 Unprocessable Entity error in the Spider's "Bio Signals" strategy.

The Fix:

Removed encodeURIComponent: In Spider.mjs, runSearch was modified to pass the query string directly to GitHub.rest without double-encoding.

Simplified Query: I replaced the topic:a OR topic:b pattern with a direct a OR b keyword search (e.g., women-in-tech OR pyladies). My verification using gh api confirmed that:

topic:a OR topic:b returns a 422 error.

a OR b works correctly and returns thousands of relevant results (3185 for this specific case).

This approach ensures the query is valid and successfully retrieves the desired diversity-focused repositories.

tobiu closed this issue on Feb 13, 2026, 2:36 AM