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	7376
title	Define Hybrid API vs. Knowledge Base Workflow for Agent
state	Closed
labels	documentationenhancementhelp wantedgood first issuehacktoberfestai
assignees	kart-u
createdAt	Oct 5, 2025, 3:02 PM
updatedAt	Oct 24, 2025, 11:39 AM
githubUrl	https://github.com/neomjs/neo/issues/7376
author	tobiu
commentsCount	3
parentIssue	7364
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Oct 24, 2025, 11:39 AM

Define Hybrid API vs. Knowledge Base Workflow for Agent

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

Closed v11.0.0 documentationenhancementhelp wantedgood first issuehacktoberfestai

tobiu commented on Oct 5, 2025, 3:02 PM

The agent will have access to two sources of information for issues and PRs: the real-time GitHub API (via gh) and the local, semantic-search-optimized knowledge base. To prevent confusion and ensure optimal performance, the agent needs a clear, documented strategy on when to use each. This ticket is to create that "Discover, then Verify" protocol.

Acceptance Criteria

A new workflow is added to AGENTS.md.
The workflow instructs the agent to use the local knowledge base (ai:query) for broad, contextual, or semantic searches (Discovery).
The workflow instructs the agent to use the GitHub CLI (gh) to get the real-time status (e.g., open/closed, assignees, labels) of a specific issue or PR that it has already discovered (Verification).
The protocol should include a clear example of this two-step "Discover, then Verify" process.

tobiu added the documentation label on Oct 5, 2025, 3:02 PM

tobiu added the enhancement label on Oct 5, 2025, 3:02 PM

tobiu added parent issue #7364 on Oct 5, 2025, 3:02 PM

tobiu added the help wanted label on Oct 5, 2025, 3:02 PM

tobiu added the good first issue label on Oct 5, 2025, 3:02 PM

tobiu added the hacktoberfest label on Oct 5, 2025, 3:02 PM

tobiu added the ai label on Oct 5, 2025, 3:02 PM

ksanjeev284 cross-referenced by PR #7374 on Oct 5, 2025, 3:22 PM

tobiu cross-referenced by #7367 on Oct 5, 2025, 3:28 PM

tobiu assigned to @kart-u on Oct 5, 2025, 4:17 PM

tobiu Oct 5, 2025, 4:17 PM

sure. Gemini input:

✦ This ticket is similar to the other documentation task (ticket-update-agent-ticket-creation-workflow.md).

Analysis

The task is to write a new strategic protocol in AGENTS.md. It needs to explain the concept of using ai:query for discovery and gh commands (like gh issue view) for verification.

A contributor working on this does not need to execute the gh commands themselves. They only need to understand the concept and write it down clearly. The existence of the gh CLI and its public documentation is enough information for them to formulate the workflow.

Conclusion

Yes, someone can start on this ticket immediately.

There are no technical blockers for this task. It is a documentation and workflow definition ticket that can be worked on in parallel with the other implementation tickets.

tobiu Oct 24, 2025, 11:39 AM

Hi @kart-u,

Thank you for your interest in this ticket during Hacktoberfest.

This ticket was for updating the AGENTS.md file with a new strategic protocol. The project's architecture and the agent's core workflow have evolved significantly since this ticket was created, making this specific protocol obsolete.

We're closing this ticket as it is no longer relevant. The upcoming rewrite of AGENTS.md (covered in #7630) will include a new, more streamlined workflow. Thanks again for your willingness to contribute!

tobiu closed this issue on Oct 24, 2025, 11:39 AM