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	7832
title	Expansion: Unified AI SDK for Memory and GitHub Services
state	Closed
labels	enhancementdeveloper-experienceai
assignees	tobiu
createdAt	Nov 21, 2025, 1:50 AM
updatedAt	Nov 21, 2025, 1:56 AM
githubUrl	https://github.com/neomjs/neo/issues/7832
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Nov 21, 2025, 1:56 AM

Expansion: Unified AI SDK for Memory and GitHub Services

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

Closed v11.8.0 enhancementdeveloper-experienceai

tobiu commented on Nov 21, 2025, 1:50 AM

Objective Expand the recently created AI SDK (ai/services.mjs) to include services from the Memory Core and GitHub Workflow MCP servers. This creates a unified "Agent OS" API that allows agents to interact with all project infrastructure programmatically.

Context The initial PoC (#7831) proved the viability of the "Code Execution" pattern using the Knowledge Base services. To fully realize the "Thick Client" vision, agents need access to long-term memory and GitHub operations within the same SDK.

Tasks

Update SDK: Modify ai/services.mjs to export MemoryService, SessionService, IssueService, etc.
Namespace Management: Implement a prefixing strategy (KB_, Memory_, GH_) to avoid naming collisions (e.g., HealthService).
Update Manifest: Expand ai/sdk-manifest.md to document the new capabilities.
Verify: Ensure the existing smart-search example still works with the updated SDK.

Deliverables

Updated ai/services.mjs
Updated ai/sdk-manifest.md
Verified ai/examples/smart-search.mjs

tobiu added the enhancement label on Nov 21, 2025, 1:50 AM

tobiu added the developer-experience label on Nov 21, 2025, 1:50 AM

tobiu added the ai label on Nov 21, 2025, 1:50 AM

tobiu assigned to @tobiu on Nov 21, 2025, 1:55 AM

tobiu Nov 21, 2025, 1:56 AM

Input from Gemini 2.0 Flash:

✦ I have completed the objectives of this ticket.

Deliverables:

Unified SDK (ai/services.mjs): Refactored to export services from Knowledge Base, Memory Core, and GitHub Workflow MCP servers. Implemented prefixing (KB_, Memory_, GH_) to handle naming collisions.

SDK Manifest (ai/sdk-manifest.md): Created a comprehensive API documentation file for agent discovery.

Verification: Updated ai/examples/smart-search.mjs to use the new SDK structure and verified it runs successfully against the local knowledge base.

The "Agent OS" infrastructure is now in place. Closing this ticket to proceed with building advanced demos (Self-Healing Repository).

tobiu closed this issue on Nov 21, 2025, 1:56 AM

tobiu cross-referenced by #7833 on Nov 21, 2025, 1:56 AM

tobiu referenced in commit 191502b - "feat(ai): Expand AI SDK to include Memory and GitHub services (#7832)" on Nov 21, 2025, 9:51 AM