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	7921
title	Feat: Real-time ''Blackboard'' Visualization
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Nov 29, 2025, 4:19 PM
updatedAt	Nov 30, 2025, 9:37 PM
githubUrl	https://github.com/neomjs/neo/issues/7921
author	tobiu
commentsCount	3
parentIssue	7918
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Nov 30, 2025, 9:37 PM

Feat: Real-time 'Blackboard' Visualization

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

Closed v11.14.0 enhancementai

tobiu commented on Nov 29, 2025, 4:19 PM

Feat: Real-time 'Blackboard' Visualization

Context

The Command Center needs a way to visualize the state of the agent swarm in real-time. Since our protocol uses GitHub Issues as the bus, this component must poll (or stream) issue states and render them visually.

Requirements

Data Source: GitHub Issues (filtered by agent-task label).
Visualization: A Kanban-style or Graph-style view.
- Nodes = Issues.
- Edges = Parent/Child relationships (Epic -> Ticket).
- Color = Status (Pending, In-Progress, Blocked, Done).
Tech Stack: Neo.mjs Helix or D3 wrapper for the visualization.

Output

A reusable Neo.mjs component (Neo.ai.ui.Blackboard) that renders this graph.

tobiu added the enhancement label on Nov 29, 2025, 4:19 PM

tobiu added the ai label on Nov 29, 2025, 4:19 PM

tobiu added parent issue #7918 on Nov 29, 2025, 4:22 PM

tobiu Nov 30, 2025, 8:51 PM

Input from Gemini 2.5 Pro:

✦ After architectural review, we have decided to implement the Blackboard visualization using D3.js via Offscreen Canvas.

Rationale:

Scalability: Canvas rendering in a dedicated worker ensures performance remains high even with hundreds of nodes (tickets) and edges (dependencies).

Force-Directed Layout: D3 is ideal for visualizing the complex parent/child and "blocked by" relationships that define the agent swarm's state.

Architecture: This will be implemented as a Neo.component.Canvas subclass, delegating rendering logic to the CanvasWorker to keep the UI thread responsive.

Plan:

Create Neo.ai.ui.Blackboard extending Neo.component.Canvas.

Implement the graph rendering logic (nodes = issues, edges = links) using D3 in the Canvas context.

Implement hit-detection to allow clicking nodes to select them in the UI.

tobiu assigned to @tobiu on Nov 30, 2025, 9:33 PM

tobiu referenced in commit 2c9e991 - "Feat: Implement Blackboard Canvas PoC #7921" on Nov 30, 2025, 9:36 PM

tobiu Nov 30, 2025, 9:36 PM

Input from Gemini 2.5 Pro:

✦ I have implemented the Proof of Concept (PoC) for the Blackboard Canvas visualization.

Technical Achievements:

Canvas Worker Architecture: Established the App Worker <-> Canvas Worker bridge using RemoteMethodAccess.

Offscreen Canvas: Implemented the transfer of the canvas control to the worker thread.

Canvas 2D Renderer: Created a lightweight 2D rendering loop in apps/agent-os/canvas/Blackboard.mjs to draw nodes and links.

Multi-Window Integration: Successfully embedded the Blackboard component into the Swarm (Child) Window.

Current State: The Swarm View now renders a live, animated 2D graph with placeholder nodes ("Root Agent", "Task 1", etc.), confirming the entire rendering pipeline is operational.

Next Steps (New Tickets):

D3 Force Integration: Replace the dummy layout with a real D3 force simulation.

Data Binding: Connect the graph to the live stream of GitHub Issues/Agents.

Interactivity: Implement hit-detection to open the Intervention Panel on node click.

tobiu Nov 30, 2025, 9:37 PM

https://github.com/user-attachments/assets/37b483bf-5511-4e06-a1fd-c0a9efd3a1e6

tobiu closed this issue on Nov 30, 2025, 9:37 PM