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	10006
title	DreamService: Semantic Edge Injection into Native Graph
state	Closed
labels	enhancementaiarchitecture
assignees	[]
createdAt	Apr 14, 2026, 5:16 PM
updatedAt	Apr 16, 2026, 8:44 PM
githubUrl	https://github.com/neomjs/neo/issues/10006
author	tobiu
commentsCount	1
parentIssue	10014
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[x] 10002 Universal Macro Overlay DB Topology
blocking	[]
closedAt	Apr 16, 2026, 8:44 PM

DreamService: Semantic Edge Injection into Native Graph

Closed v13.0.0/archive-v13-0-0-chunk-4 enhancementaiarchitecture

tobiu commented on Apr 14, 2026, 5:16 PM

Objective

Augment the Native Edge Graph by automatically injecting physical edges (relates_to, impacts) between autonomous structural nodes based on their macroscopic semantic distance.

Tasks

Refactor DreamService to iterate through isolated nodes (e.g., newly ingested GitHub Tickets, Pull Requests, or orphaned Source files).
Execute vector distance queries against the neo-knowledge-base-macro collection to find mathematically adjacent artifacts.
If the semantic distance falls below a high-confidence threshold, execute database INSERT commands to physically link the nodes in the SQLite Native Edge Graph (e.g., Ticket Node -> semantic_link -> Guide Node).
Ensure these semantic edges are distinguishable from structural/parse-based edges so they can be filtered or weighted during context priming (get_context_frontier).

tobiu cross-referenced by #10014 on Apr 14, 2026, 6:43 PM

tobiu Apr 16, 2026, 8:44 PM

Superseded by Epic #10030. Edges will be formed via explicit concept nodes instead of native semantic distance overlays.