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	7663
title	Feat: Implement GitHub API-based ''list_issues'' Tool
state	Closed
labels	enhancementhacktoberfestai
assignees	MannXo
createdAt	Oct 26, 2025, 1:11 PM
updatedAt	Nov 1, 2025, 7:22 PM
githubUrl	https://github.com/neomjs/neo/issues/7663
author	tobiu
commentsCount	2
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Nov 1, 2025, 7:22 PM

Feat: Implement GitHub API-based 'list_issues' Tool

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

Closed v11.0.0 enhancementhacktoberfestai

tobiu commented on Oct 26, 2025, 1:11 PM

This ticket is a feature request to implement a new tool in the github-workflow MCP server.

Motivation: The pr-workflow.md guide (which is now largely obsolete) contained instructions for using gh issue list. Currently, there is no corresponding GitHub API-based tool to list issues from the repository. The existing get_local_issue_by_id tool only allows for local lookup. Implementing a list_issues tool would provide a complete set of GitHub interaction tools for agents.

Implementation Details:

GraphQL Query: The FETCH_ISSUES_FOR_SYNC GraphQL query (located in ai/mcp/server/github-workflow/services/queries/issueQueries.mjs) is already comprehensive and can likely be re-used as the basis for this new tool.
Service Method: A new method will need to be added to an appropriate service (e.g., IssueService.mjs) to encapsulate the logic for calling the GraphQL API and processing the results.
Tool Registration: The new tool (list_issues) must be registered in ai/mcp/server/github-workflow/services/toolService.mjs, mapping it to the newly created service method.
OpenAPI Specification: A complete and accurate definition for the list_issues tool, including its input parameters and output shape, must be added to github-workflow/openapi.yaml. Tiny spec errors can break tools completely, so precision is crucial.

Functionality: The new list_issues tool should provide a way to query GitHub's API to retrieve a list of issues, similar to how list_pull_requests works for pull requests.

Parameters: Consider parameters such as limit, state (e.g., open, closed, all), and potentially labels or assignee for filtering.

Documentation: The tool's description in openapi.yaml should be comprehensive and self-explanatory, following the guidelines established in #7659.

tobiu added the enhancement label on Oct 26, 2025, 1:11 PM

tobiu added the ai label on Oct 26, 2025, 1:11 PM

MannXo Oct 27, 2025, 1:27 PM

Can I work on this one @tobiu ?

tobiu Oct 27, 2025, 1:56 PM

@MannXo Sure. This one should be quite straight forward. Hint: all 3 MCP servers should now be fully functional, and I updated the AGENTS.md file => with a fresh/updated fork definitely worth some testing.

tobiu assigned to @MannXo on Oct 27, 2025, 1:56 PM

tobiu added the hacktoberfest label on Oct 27, 2025, 1:56 PM

MannXo referenced in commit 7f720ed - "feat(mcp/github-workflow): add list_issues tool, OpenAPI path/schemas and verification tests on Oct 28, 2025, 10:24 AM

MannXo cross-referenced by PR #7678 on Oct 28, 2025, 10:31 AM

tobiu closed this issue on Nov 1, 2025, 7:22 PM

tobiu referenced in commit be4f244 - "feat(mcp/github-workflow): add list_issues tool, OpenAPI path/schemas and verification tests on Nov 1, 2025, 7:22 PM