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	8220
title	AI: Implement Knowledge Base Upload Script
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Dec 30, 2025, 4:41 PM
updatedAt	Dec 30, 2025, 4:50 PM
githubUrl	https://github.com/neomjs/neo/issues/8220
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Dec 30, 2025, 4:50 PM

AI: Implement Knowledge Base Upload Script

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

Closed v11.18.0 enhancementai

tobiu commented on Dec 30, 2025, 4:41 PM

Context: The migration to gemini-embedding-001 has significantly increased the time required for initial Knowledge Base synchronization (~75 mins due to rate limits). To ensure a smooth onboarding experience ("Zero-Setup DX"), we decided to distribute the pre-built Knowledge Base as a GitHub Release artifact rather than committing it to the repo (which would cause bloat).

Objective: Create a script to automate the packaging and uploading of the local Knowledge Base to the current GitHub Release.

Tasks:

Create Script: ai/examples/upload_knowledge_base.mjs
- Zip: Compress the chroma-neo-knowledge-base directory into chroma-neo-knowledge-base.zip.
- Upload: Use the GitHub CLI (gh) to upload the zip to the release tag matching the version in package.json.
- Command: gh release upload v${version} chroma-neo-knowledge-base.zip --clobber
Add NPM Script: Add "ai:upload-kb": "node ./ai/examples/upload_knowledge_base.mjs" to package.json.
Verification: Execute the script to upload the current Knowledge Base to the existing v11.17.1 release.

Prerequisites:

User must have gh (GitHub CLI) installed and authenticated.
User must have a fully synced chroma-neo-knowledge-base locally.

tobiu added the enhancement label on Dec 30, 2025, 4:41 PM

tobiu added the ai label on Dec 30, 2025, 4:41 PM

tobiu assigned to @tobiu on Dec 30, 2025, 4:45 PM

tobiu referenced in commit f1286e9 - "AI: Implement Knowledge Base Upload Script #8220" on Dec 30, 2025, 4:49 PM

tobiu Dec 30, 2025, 4:49 PM

Input from Gemini 2.5 pro:

✦ Zero-Setup DX Implementation Complete

The Knowledge Base distribution workflow is now operational.

Artifact:

Uploaded chroma-neo-knowledge-base.zip (92.53 MB) to Release 11.17.1.

Link: https://github.com/neomjs/neo/releases/download/11.17.1/chroma-neo-knowledge-base.zip

Scripts:

Upload: npm run ai:upload-kb (zips and uploads to GH Releases matching package version).

Download: npm run ai:download-kb (fetches and unzips).

Auto-Setup: prepare script in package.json runs the download automatically for repo contributors.

Verification: The upload script successfully pushed the artifact to the current release.

Ready for merge.

tobiu closed this issue on Dec 30, 2025, 4:50 PM