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.

Neo.mjs - Self-Evolving Software Organism

Frontmatter

title	>-
feat	Implement Autonomous Agent Orchestrator with Golden Path Directive
author	tobiu
state	Merged
createdAt	Apr 12, 2026, 2:48 PM
updatedAt	Apr 12, 2026, 3:20 PM
closedAt	Apr 12, 2026, 3:20 PM
mergedAt	Apr 12, 2026, 3:20 PM
branches	`dev` ← `agent/9842-orchestrator`
url	https://github.com/neomjs/neo/pull/9918

Merged

tobiu commented on Apr 12, 2026, 2:48 PM

Description

This PR fulfills the requirements for the Autonomous Orchestrator, enabling a headless daemon to act natively over the Neo.ai.Agent stack without human prompting.

Changes

Created ai/agent/Orchestrator.mjs to parse the Sandman Handoff manifest and intelligently inject system:golden-path directives into the cognitive scheduler queue.
Bound the script lifecycle closely with MCP capabilities enforcing a tight context decay (maxSubAgentLifespan: 20).
Exposed the interface natively via npm run ai:agent pointing to buildScripts/ai/runAgent.mjs.
Supported testing with --dry-run.
Authored semantic unit tests validating regex targeting mechanisms in Orchestrator.spec.mjs.

Graph Telemetry

Resolves #9842 Unblocks #9844 Unblocks #9843

tobiu commented on Apr 12, 2026, 3:18 PM

Input from Antigravity (Gemini 3.1 Pro):

✦ # PR Review Summary

Status: Approved

Thanks for putting this together! Great pivot from a raw runner script to a proper Neo.ai.agent.Orchestrator base class. This establishes strong class topology for our autonomous executions.

📊 Evaluation Metrics

[ARCH_ALIGNMENT]: 95 - Adhered perfectly to Neo.core.Base class hierarchy rules after refactoring the ad-hoc script into an orchestration class.

[CONTENT_COMPLETENESS]: 90 - "Fat Ticket" protocol followed within the PR body and code includes standard JSDoc tags.

[EXECUTION_QUALITY]: 95 - Playwright tests confirm Semantic extraction Regex correctly handles complex Markdown boundaries locally without instantiating global state.

[PRODUCTIVITY]: 100 - Successfully unblocks #9844 by hooking Sandman into the operational plane natively.

[IMPACT]: 90 - Tremendous leap ensuring full closed-loop autonomy for multi-agent swarm deployments.

[COMPLEXITY]: 40 - Moderate string manipulation logic attached to standard component boot sequences.

[EFFORT_PROFILE]: Architectural Pillar - Bridges the Dream Daemon RLAIF output into physical agent orchestration.

🕸️ Context & Graph Linking

Target Epic / Issue ID: Resolves #9842

Related Graph Nodes: #9844, #9843

🧠 Graph Ingestion Notes

[RETROSPECTIVE]: The transition to runAgent.mjs natively importing a formal Orchestrator base class underscores the value of maintaining pure OOP hierarchy for runtime AI services over loose bash/node bindings.

📋 Required Actions

To proceed with merging, please address the following:

Initial PR Review Completed

Since this is mathematically solid and tests are green, it is fully approved for a squash merge into dev.