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	9794
title	[Memory Core] Fix UUID Graph Corruption and Stream Truncation Bug in REM Pipeline
state	Closed
labels	bugaicore
assignees	tobiu
createdAt	Apr 8, 2026, 8:37 PM
updatedAt	Apr 8, 2026, 8:37 PM
githubUrl	https://github.com/neomjs/neo/issues/9794
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Apr 8, 2026, 8:37 PM

[Memory Core] Fix UUID Graph Corruption and Stream Truncation Bug in REM Pipeline

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

Closedbugaicore

tobiu commented on Apr 8, 2026, 8:37 PM

Architectural Adjustments for Autonomous REM Pipeline Stability

Context: The autonomous Memory Core processes legacy knowledge natively using headless background daemons (DreamService -> FileSystemIngestor -> GraphService). The reliability of the background memory ingestion pipeline hinges upon strict dataset determinism and payload parsing.

1. Deterministic Edge Topology (`globalThis.crypto.randomUUID()`)

Issue: The SQLite Edge Graph Database utilized Neo.getId('edge') and Neo.getId('node') to assign relationship IDs. Because internal ID managers reset on every spin-up of the process execution block (e.g. testInferenceSpeed, runSandman), newly ingested edges inherited overlapping numerical IDs (e.g., e_1, e_2), triggering immediate corruption inside the memory database via overwrites.

Resolution: Transitioned all ID managers operating inside backend DB logic (Database.mjs, FileSystemIngestor.mjs, GraphService.mjs) to leverage V8's native UUID v4 Generator (globalThis.crypto.randomUUID()). Every edge entity now retains a fully pseudo-random ID ensuring safe ingestion regardless of Node environment.

2. Persistent Stream TCP Repair

Issue: Server-Sent Events (SSE) parsed by OpenAiCompatible.mjs frequently chunk data packets irregularly down the TCP network pipe. The parser evaluated streaming JSON output recursively, occasionally discarding mid-string chunked artifacts from the LLM, silently dropping REM extractions.

Resolution: Introduced an isolated line-length buffer to aggregate incomplete bytes across disjointed chunk borders consistently formatting the string parsing sequence for native JSON.parse().

tobiu added the bug label on Apr 8, 2026, 8:37 PM

tobiu added the ai label on Apr 8, 2026, 8:37 PM

tobiu added the core label on Apr 8, 2026, 8:37 PM

tobiu referenced in commit b52ef2f - "fix: UUID Graph Corruption and Stream Truncation Bugs in pipeline (#9794)" on Apr 8, 2026, 8:37 PM

tobiu assigned to @tobiu on Apr 8, 2026, 8:37 PM

tobiu Apr 8, 2026, 8:37 PM

Input from Antigravity (Gemini 3.1 Pro):

✦ The structural identifiers and TCP chunking constraints have been resolved seamlessly across the primary engine architecture. Edges and Nodes use strictly determined universally unique identifiers via V8's native API. The LLM Stream utilizes buffered tracking to circumvent SSE chunking limitations across nodes.

Marking this Definition of Done as complete natively inside GitHub and closing!

tobiu closed this issue on Apr 8, 2026, 8:38 PM

[Memory Core] Fix UUID Graph Corruption and Stream Truncation Bug in REM Pipeline

Architectural Adjustments for Autonomous REM Pipeline Stability

1. Deterministic Edge Topology (globalThis.crypto.randomUUID())

2. Persistent Stream TCP Repair

1. Deterministic Edge Topology (`globalThis.crypto.randomUUID()`)