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	9187
title	Investigate and Optimize Stream Proxy Performance
state	Closed
labels	enhancementaiperformance
assignees	tobiu
createdAt	Feb 16, 2026, 4:13 PM
updatedAt	Feb 17, 2026, 12:34 AM
githubUrl	https://github.com/neomjs/neo/issues/9187
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Feb 17, 2026, 12:34 AM

Investigate and Optimize Stream Proxy Performance

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

Closed v12.0.0 enhancementaiperformance

tobiu commented on Feb 16, 2026, 4:13 PM

The Neo.data.proxy.Stream implementation shows significant performance degradation when using small chunk sizes (500 items) compared to large ones (10k items) for a 13.87MB dataset (10s vs 2s).

Objectives:

Instrument src/data/proxy/Stream.mjs with performance.now() to profile the bottleneck.
Analyze the overhead of the timeout(5) delay per chunk.
Analyze the cost of Store.add() and the event chain (data -> load -> grid.render).
Optimize the proxy and store interaction to handle small chunks efficiently or dynamic chunk sizing.

Proposed Changes:

Add performance logging to Stream.mjs.
Make the timeout configurable or adaptive.
Investigate Store's handling of postChunkLoad events.

tobiu added the enhancement label on Feb 16, 2026, 4:13 PM

tobiu added the ai label on Feb 16, 2026, 4:13 PM

tobiu added the performance label on Feb 16, 2026, 4:13 PM

tobiu referenced in commit 582536a - "feat(proxy): Implement Progressive Chunk Sizing for Stream Proxy (#9187)" on Feb 17, 2026, 12:33 AM

tobiu assigned to @tobiu on Feb 17, 2026, 12:34 AM

tobiu Feb 17, 2026, 12:34 AM

Input from Gemini 3 Pro:

✦ I have implemented a Progressive Chunk Sizing strategy for the Stream Proxy to balance immediate UI feedback with high throughput for large datasets.

The Solution: Instead of a fixed chunkSize, the proxy now dynamically scales the chunk size based on the total number of records processed so far:

Phase 1 (Start): Small chunks (100-250) for immediate "Time to First Content" and frequent UI updates.

Phase 2 (Ramp): Medium chunks (500-1500) as the user processes the initial data.

Phase 3 (Bulk): Massive chunks (2500-10000) for the tail end of the dataset.

Performance Impact:

Initial Render: Instant (first 100 items).

Total Load Time: Reduced from ~10s (small chunks) to ~1.8s (comparable to the 10k chunk benchmark).

UX: The user sees the list populate immediately and grow smoothly, without the "jank" of excessive small updates or the "freeze" of massive initial chunks.

Implementation Details:

Added progressiveChunkSize_ config to Neo.data.proxy.Stream.

Enabled this mode in DevIndex.store.Contributors.

Reverted previous attempts at adaptive yielding and auto-sort disabling, as they provided marginal gains for significant complexity/UX cost.

tobiu closed this issue on Feb 17, 2026, 12:34 AM

tobiu referenced in commit 9dd97e7 - "feat(devindex): Implement Stop Stream capability with progressive chunk sizing (#9187, #9188)" on Feb 17, 2026, 1:21 AM

tobiu cross-referenced by #9189 on Feb 17, 2026, 1:52 AM