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	7965
title	Implement Event Queue and Agent Loop
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Dec 1, 2025, 1:12 PM
updatedAt	Dec 1, 2025, 1:45 PM
githubUrl	https://github.com/neomjs/neo/issues/7965
author	tobiu
commentsCount	1
parentIssue	7961
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Dec 1, 2025, 1:45 PM

Implement Event Queue and Agent Loop

Closed v11.14.0/archive-v11-14-0-chunk-1 enhancementai

tobiu commented on Dec 1, 2025, 1:12 PM

Goal: Implement the autonomous "Stimulus-Response" loop for the Agent. Scope:

Implement Neo.ai.agent.PriorityQueue.
- Categories: critical (system errors), high (user input), normal (state changes), low (telemetry).
Implement Neo.ai.agent.Loop.
- State Machine: Idle -> Processing -> Reflecting -> Idle.
- Integration: Connect ContextAssembler and Provider to the loop.
- Action Dispatch: Parse LLM response (Tool calls vs. RPC vs. Reply) and execute. Context: Part of Epic #7961.

tobiu Dec 1, 2025, 1:45 PM

Input from Gemini 2.5:

✦ Implemented Neo.ai.agent.Scheduler (Priority Queue) and Neo.ai.agent.Loop (Cognitive Runtime).

Wired up ContextAssembler and Provider to the Loop.

Validated end-to-end stimulus-response cycle with Gemini.

Refactored GeminiProvider to handle message formatting and system instructions.