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	8217
title	AI: Migrate Knowledge Base to gemini-embedding-001
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Dec 30, 2025, 12:42 PM
updatedAt	Dec 30, 2025, 3:16 PM
githubUrl	https://github.com/neomjs/neo/issues/8217
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Dec 30, 2025, 3:16 PM

AI: Migrate Knowledge Base to gemini-embedding-001

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

Closed v11.18.0 enhancementai

tobiu commented on Dec 30, 2025, 12:42 PM

Objective: Migrate the Knowledge Base embedding model from text-embedding-004 to gemini-embedding-001 to comply with the discontinuation notice.

Tasks:

Update Config: Modify ai/mcp/server/knowledge-base/config.mjs to set embeddingModel: 'gemini-embedding-001'.
Reset Database: The Knowledge Base is stateless (generated from source). The migration strategy is a full reset:
- Stop the server.
- Delete the chroma-neo-knowledge-base directory.
- Restart the server.
- Run sync_database to rebuild the index with the new model.

tobiu added the enhancement label on Dec 30, 2025, 12:42 PM

tobiu added the ai label on Dec 30, 2025, 12:42 PM

tobiu assigned to @tobiu on Dec 30, 2025, 12:54 PM

tobiu referenced in commit aecc0d6 - "AI: Migrate Knowledge Base to gemini-embedding-001 #8217" on Dec 30, 2025, 3:16 PM

tobiu Dec 30, 2025, 3:16 PM

Input from Gemini 2.5 pro:

✦ Optimization Update:

To balance the RPM (Requests Per Minute) and RPD (Requests Per Day) limits of the Gemini Free Tier, the configuration has been tuned to:

batchSize: 50 (Reduced total requests to ~153, saving daily quota)

batchDelay: 10000 ms (10s delay ensures ~6 RPM, safe within 15 RPM limit)

Rationale:

Previous batchSize: 10 generated ~764 requests, risking the 1,000 RPD limit.

Previous batchSize: 100 hit the RPM limit.

50 items with 10s delay is the sweet spot.

Next Steps:

Distribute a pre-built Knowledge Base artifact to avoid this 75-minute sync for end users.

PR ready for merge.

tobiu closed this issue on Dec 30, 2025, 3:16 PM