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	7914
title	Epic: Foundation for Ticket-Driven Agent Orchestration
state	Closed
labels	epicstaleai
assignees	tobiu
createdAt	Nov 29, 2025, 4:07 PM
updatedAt	Mar 14, 2026, 4:37 AM
githubUrl	https://github.com/neomjs/neo/issues/7914
author	tobiu
commentsCount	3
parentIssue	null
subIssues	7926 Feat: Add Cross-Repo Capabilities to GitHub Workflow MCP 7930 Bug: GitHub HealthService fails in standalone SDK scripts
subIssuesCompleted	2
subIssuesTotal	2
blockedBy	[]
blocking	[]
closedAt	Mar 14, 2026, 4:37 AM

Epic: Foundation for Ticket-Driven Agent Orchestration

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

Closed v12.1.0 epicstaleai

tobiu commented on Nov 29, 2025, 4:07 PM

Epic: Foundation for Ticket-Driven Agent Orchestration

This epic captures the strategic initiative to transform Neo.mjs into the "Corporate Headquarters for AI Agents." We are moving from single-agent tool use to a hierarchical swarm of specialized agents (PMs, Developers) that coordinate asynchronously using GitHub Issues as their message bus.

Strategic Goals

Establish the "Ticket-Driven Protocol": Define a strict contract for how agents communicate via GitHub Issues (labels, templates, state transitions).
Enable Cross-Repo Coordination: Empower agents in one repository to queue tasks for agents in another.
Prove the "Feature Factory": Demonstrate a fully autonomous workflow where an Epic is broken down into Tickets (PM Agent) and those Tickets are resolved into PRs (Dev Agent).

Key Deliverables

1. The Protocol (Contract)

Define Agent Task Protocol: Create ai/agents/PROTOCOL.md specifying label schemas (agent-task:pending), issue templates, and handoff rules.

2. The "Headless" Workforce (MVP Agents)

PM Agent MVP: A standalone Node.js script (ai/agents/pm.mjs) that reads an Epic and generates sub-issues based on the protocol.
Dev Agent MVP: A standalone Node.js script (ai/agents/dev.mjs) that picks up a pending issue, attempts a code fix, and submits a PR.

3. Infrastructure

GitHub Workflow Enhancements: Update the MCP server to support cross-repo issue creation and label management required by the protocol.

Success Metric

The "Feature Factory" Experiment: A single command (npm run agent:feature -- --epic=123) successfully triggers the chain: Epic -> PM Agent -> Tickets -> Dev Agent -> PR without human intervention.

tobiu added the epic label on Nov 29, 2025, 4:07 PM

tobiu added the ai label on Nov 29, 2025, 4:07 PM

tobiu cross-referenced by #7913 on Nov 29, 2025, 4:09 PM

tobiu cross-referenced by #7915 on Nov 29, 2025, 4:09 PM

tobiu cross-referenced by #7916 on Nov 29, 2025, 4:09 PM

tobiu cross-referenced by #7917 on Nov 29, 2025, 4:09 PM

tobiu assigned to @tobiu on Nov 29, 2025, 4:12 PM

tobiu added sub-issue #7926 on Nov 29, 2025, 4:22 PM

tobiu added sub-issue #7930 on Nov 29, 2025, 5:23 PM

tobiu Nov 29, 2025, 5:24 PM

Input from Gemini 2.5 Agent:

✦ # Phase 1 Status Report: The "Brain" is Live

We have successfully completed the foundational work for the Ticket-Driven Agent Orchestration.

✅ Completed

Protocol Defined: ai/agents/PROTOCOL.md establishes the label schema (agent-task:pending) and contract templates. (Ticket #7915)

SDK Enhanced: GH_LocalFileService is now exposed in the SDK, enabling "Local First" context fetching. (Ticket #7927)

PM Agent MVP: ai/agents/pm.mjs is operational. It successfully reads an Epic, queries the Knowledge Base, generates a plan, and creates Protocol-compliant child tickets in GitHub. (Ticket #7916)

🚧 In Progress / Next Steps

Bug Fix: GH_HealthService fails in standalone scripts (Ticket #7930). We need to fix this to ensure robust agent startups.

Dev Agent MVP: Building the "Execution" arm (ai/agents/dev.mjs) to pick up the tickets created by the PM Agent. (Ticket #7917)

The "Feature Factory" pipeline is now 50% complete (Epic -> Tickets). The next phase is closing the loop (Tickets -> Code).

@github-actions - 2026-02-28T03:22:12Z

This issue is stale because it has been open for 90 days with no activity.

2026-02-28T03:22:13Z @github-actions added the stale label

@github-actions - 2026-03-14T03:37:26Z

This issue was closed because it has been inactive for 14 days since being marked as stale.

2026-03-14T03:37:27Z @github-actions closed this issue