What is the Neural Link?

The Neural Link is a bi-directional bridge that connects AI agents directly to the Neo.mjs runtime. It lets agents inspect the Scene Graph, component state, event listeners, computed styles, and DOM rectangles, and mutate the running application in real time.

Why is Neo.mjs called an Application Engine instead of a framework?

Neo.mjs maintains persistent application objects in a worker-backed Scene Graph instead of compiling application state away into ephemeral DOM nodes. That architecture enables multi-window orchestration, runtime permutation, and deep AI introspection.

What is Context Engineering?

Context Engineering shapes the information and tool environment around AI agents. Neo.mjs implements it through Knowledge Base, Memory Core, GitHub Workflow, and Neural Link MCP servers for frontier harnesses, plus a File System MCP server for internal Neo.ai.Agent local loops.

What is the Neo.mjs Agent OS?

The Neo.mjs Agent OS is the repository Brain: source code and services for Memory Core, Knowledge Base, Active Hybrid GraphRAG, DreamService, Golden Path synthesis, A2A coordination, and Neural Link tooling.

Frontmatter

id	7804
title	Add CLI argument parsing and Config refactoring to Memory Core MCP Server
state	Closed
labels	enhancementairefactoring
assignees	tobiu
createdAt	Nov 19, 2025, 12:12 PM
updatedAt	Nov 19, 2025, 12:18 PM
githubUrl	https://github.com/neomjs/neo/issues/7804
author	tobiu
commentsCount	0
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Nov 19, 2025, 12:18 PM

Add CLI argument parsing and Config refactoring to Memory Core MCP Server

Closed v11.6.0/archive-v11-6-0-chunk-1 enhancementairefactoring

tobiu commented on Nov 19, 2025, 12:12 PM

Apply the same configuration and CLI argument parsing improvements to the Memory Core MCP server as were done for the GitHub Workflow server.

Tasks:

Refactor ai/mcp/server/memory-core/config.mjs to:
- Use the Proxy pattern to expose configuration data.
- Implement a load(filePath) method that supports both JSON and JS/MJS files.
- Store configuration values in a data property on the singleton instance.
Update ai/mcp/server/memory-core/mcp-stdio.mjs to:
- Use commander for CLI argument parsing.
- Support -c, --config <path> to load a custom configuration file.
- Support -d, --debug to enable debug logging (and update aiConfig.data.debug).
Update ai/mcp/server/memory-core/logger.mjs (if applicable/similar to GitHub workflow) to rely solely on aiConfig.debug.

Goal: Standardize the configuration and startup logic across MCP servers for better maintainability and flexibility.

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

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

tobiu added the refactoring label on Nov 19, 2025, 12:12 PM

tobiu assigned to @tobiu on Nov 19, 2025, 12:16 PM

tobiu referenced in commit 4120324 - "Add CLI argument parsing and Config refactoring to Memory Core MCP Server #7804" on Nov 19, 2025, 12:17 PM

tobiu closed this issue on Nov 19, 2025, 12:18 PM