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	9763
title	Migrate DreamService to MLX-Native OpenAI-Compatible Server
state	Closed
labels	enhancementaiagent-role:devperformance
assignees	tobiu
createdAt	Apr 7, 2026, 9:57 PM
updatedAt	Apr 8, 2026, 1:03 AM
githubUrl	https://github.com/neomjs/neo/issues/9763
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Apr 7, 2026, 10:01 PM

Migrate DreamService to MLX-Native OpenAI-Compatible Server

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

Closedenhancementaiagent-role:devperformance

tobiu commented on Apr 7, 2026, 9:57 PM

Currently, the autonomous REM sleep pipeline (DreamService.mjs) uses the Ollama provider. Calculating num_ctx dynamically for a 31B model creates massive memory bandwidth saturation and forces frequent KV cache resizing, resulting in monumental prefill IO overhead on Apple Silicon M-series chips.

Scope:

Create a generic OpenAiCompatible.mjs provider inside src/ai/provider/.
Refactor DreamService.mjs to target this new provider instead of Ollama, abandoning individual num_ctx manipulations and deferring dynamic KV-Cache paging to MLX.
Add API connection settings to config.mjs.

tobiu added the enhancement label on Apr 7, 2026, 9:57 PM

tobiu added the ai label on Apr 7, 2026, 9:57 PM

tobiu added the agent-role:dev label on Apr 7, 2026, 9:57 PM

tobiu added the performance label on Apr 7, 2026, 9:57 PM

tobiu referenced in commit 0e315c4 - "feat: Migrate DreamService to MLX-Native OpenAI-Compatible Server (#9763) on Apr 7, 2026, 10:00 PM

tobiu Apr 7, 2026, 10:01 PM

Input from Antigravity (Gemini 3.1 Pro):

✦ Task Completed!

The autonomous infrastructure migration to native MLX support is finished.

Summary of Modifications:

A new OpenAiCompatible.mjs API provider adapter has been implemented which binds specifically to /v1/chat/completions API JSON structures.

num_ctx logic has been surgically stripped from all DreamService.mjs execution loops (Tri-Vector Synthesis, Topology Conflict Reconciliation, Capability Gap Extraction).

KV-cache management has effectively been handed back over to Apple Native Paged Attention structures.

Note: The server expects the runner (such as mlx_lm.server) to exist on port :8000 via the new openAiCompatible config setting.

Code has been committed and physically pushed to the active development branch. I am proceeding to close this ticket structurallly.

tobiu closed this issue on Apr 7, 2026, 10:01 PM

tobiu assigned to @tobiu on Apr 8, 2026, 1:03 AM