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	8203
title	Optimizing `SummaryService.listSummaries` with Two-Phase Fetch
state	Closed
labels	enhancementairefactoringperformance
assignees	tobiu
createdAt	Dec 29, 2025, 11:13 PM
updatedAt	Dec 29, 2025, 11:24 PM
githubUrl	https://github.com/neomjs/neo/issues/8203
author	tobiu
commentsCount	2
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Dec 29, 2025, 11:24 PM

Optimizing `SummaryService.listSummaries` with Two-Phase Fetch

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

Closed v11.18.0 enhancementairefactoringperformance

tobiu commented on Dec 29, 2025, 11:13 PM

ChromaDB lacks a native ORDER BY clause for metadata. The current implementation fetches all documents (limit 50), which prevents accessing older sessions and is unscalable.

Proposed Solution: Two-Phase Fetch Pattern To achieve efficient, SQL-like pagination without native DB support:

Phase 1 (Lightweight): Fetch ids and metadatas for ALL sessions.
- Note: This scales well because we avoid fetching the heavy document (text) field.
In-Memory Sort: Sort the metadata array by timestamp (DESC).
Pagination: Apply offset and limit to the sorted array to identify the target IDs.
Phase 2 (Targeted): Fetch the full documents for ONLY the sliced IDs.

Benefits:

Accuracy: Guaranteed to return the true "latest" sessions.
Performance: Significantly reduces network payload and memory usage by only transferring necessary text data.
Scalability: Supports paging through the entire history, not just the random first 50.

tobiu added the enhancement label on Dec 29, 2025, 11:13 PM

tobiu added the ai label on Dec 29, 2025, 11:13 PM

tobiu added the refactoring label on Dec 29, 2025, 11:13 PM

tobiu added the performance label on Dec 29, 2025, 11:13 PM

tobiu assigned to @tobiu on Dec 29, 2025, 11:13 PM

tobiu Dec 29, 2025, 11:14 PM

cross reference link: https://github.com/chroma-core/chroma/issues/469 => it is sad to see that the ordering feature never got implemented.

tobiu referenced in commit f562965 - "Refactor(Memory): Implement two-phase fetch for global sorting in listSummaries (#8203)" on Dec 29, 2025, 11:24 PM

tobiu Dec 29, 2025, 11:24 PM

Implemented the two-phase fetch strategy to ensure correct global sorting and pagination of session summaries. Phase 1 fetches lightweight metadata for sorting, and Phase 2 fetches the full documents for the target slice, using a Map for O(1) re-assembly to preserve order.

tobiu closed this issue on Dec 29, 2025, 11:24 PM

Optimizing SummaryService.listSummaries with Two-Phase Fetch

Optimizing `SummaryService.listSummaries` with Two-Phase Fetch