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	7407
title	MCP Server: Implement Memory Server Scaffold
state	Closed
labels	enhancementhelp wantedgood first issuehacktoberfestai
assignees	SiddharthJiyani
createdAt	Oct 7, 2025, 12:19 PM
updatedAt	Oct 11, 2025, 7:30 PM
githubUrl	https://github.com/neomjs/neo/issues/7407
author	tobiu
commentsCount	5
parentIssue	7399
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Oct 11, 2025, 7:30 PM

MCP Server: Implement Memory Server Scaffold

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

Closed v11.0.0 enhancementhelp wantedgood first issuehacktoberfestai

tobiu commented on Oct 7, 2025, 12:19 PM

This is the foundational ticket for the new Memory Core MCP server. The task is to create the basic Node.js server application, set up the project structure, and implement the initial /healthcheck endpoint.

This ticket must be completed before any other endpoint implementation tickets for the memory server can be started.

Acceptance Criteria

A new Node.js server application is created (e.g., using Express.js) within a new ai/mcp/server/memory/ directory.
The server implements a GET /healthcheck endpoint that returns a 200 OK status if it can successfully connect to the ChromaDB instance on port 8001.
A new script, npm run ai:server-memory-mcp, is added to package.json to start the server.
The server uses a library (e.g., swagger-ui-express) to serve interactive API documentation from the OpenAPI specification file at a /docs endpoint.
Basic error handling and logging are in place.

Agent Instructions

To work on this ticket, please start your session with the following prompt:

Please follow the instructions in @AGENTS.md.

Once you are initialized, I want to work on a sub-task for the "Architect AI Tooling as a Model Context Protocol (MCP) Servers" epic.

My task is to implement: MCP Server: Implement Memory Server Scaffold

You will need to read the epic context from @.github/ISSUE/epic-architect-ai-tooling-as-mcp.md and the specific ticket details from @.github/ISSUE/ticket-implement-memory-server-scaffold.md before we begin.

tobiu added the enhancement label on Oct 7, 2025, 12:19 PM

tobiu added the help wanted label on Oct 7, 2025, 12:19 PM

tobiu added parent issue #7399 on Oct 7, 2025, 12:19 PM

tobiu added the good first issue label on Oct 7, 2025, 12:19 PM

tobiu added the hacktoberfest label on Oct 7, 2025, 12:19 PM

tobiu added the ai label on Oct 7, 2025, 12:19 PM

SiddharthJiyani Oct 8, 2025, 5:34 PM

I would love to work on this. Can I start the work ?

tobiu assigned to @SiddharthJiyani on Oct 8, 2025, 5:55 PM

tobiu Oct 8, 2025, 5:56 PM

Hi, and thanks for your interest. Assigned. Please make sure to read the parent epic first: https://github.com/neomjs/neo/issues/7399

Phase 1 just got completed, so the baseline for phase 2 is now in place.

@Aki-07 - 2025-10-10T19:40:16Z

Hi @tobiu! I'm currently assigned to ticket #7409 (implement memory query endpoints), but I've discovered it depends on this scaffold ticket which hasn't been started yet. I see this was assigned 2 days ago. Is the assignee still actively working on it? If not, I'd like to take this on as well so I can unblock my query endpoints ticket. I have time today to implement both the scaffold and the query endpoints together in a single PR. Let me know if I should proceed or if I should wait for the current assignee! Happy to coordinate either way.

tobiu Oct 10, 2025, 9:58 PM

We actually had this case just yesterday(?) where someone asked if a ticket could get reassigned. From a fairness perspective, I came up with "after a week yes", since this always includes one weekend. I added it here: https://github.com/neomjs/neo/blob/dev/CONTRIBUTING.md (item 3.2)

For the meantime, there definitely is an almost infinite amount of items which you could work on instead. My guess is that we could easily create 100+ more files which should get unit tested, another 100+ for component based testing (although i think for this one i probably should resolve phase 1 on my own, to provide a solid starting point. Unless someone wants it as a learning experience).

You could also just ask an ai agent after following the agents.md instructions to suggest new work items for you. Ideally mention hacktoberfest, and the agent should ask you what could be items that match your interests. Of course I will add the hacktoberfest label on every self-generated new ticket.

2025-10-10T20:14:12Z @Aki-07 cross-referenced by PR #7450
2025-10-10T20:46:26Z @Aki-07 cross-referenced by PR #7455

@Aki-07 - 2025-10-10T20:50:36Z

Thanks for the clarification @tobiu! I completely understand the one-week fairness rule. Apologies...In the meantime, I've gone ahead and created the implementation for all three dependent tickets as a PR to keep momentum going and learn the codebase:

PR #7455: Memory server scaffold + /healthcheck + Read endpoints (GET /memories, GET /summaries) + Query endpoints (POST /memories/query, POST /summaries/query) - my original assignment

To had complete the query endpoint had to work on the memory server as well as on the GET apis. I understand these may need to wait for the original assignee or the one-week mark, but I wanted to have the work ready so there's no delay once we can proceed. I ll go on and try to work on the other things which you have posted

2025-10-11T14:57:45Z @Aki-07 cross-referenced by PR #7462

tobiu closed this issue on Oct 11, 2025, 7:30 PM