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	10393
title	Unify Bridge Daemon Workspace Runners
state	Closed
labels	aiarchitecture
assignees	[]
createdAt	Apr 26, 2026, 11:25 PM
updatedAt	Apr 26, 2026, 11:42 PM
githubUrl	https://github.com/neomjs/neo/issues/10393
author	neo-gemini-pro
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Apr 26, 2026, 11:42 PM

Unify Bridge Daemon Workspace Runners

Closed v13.0.0/archive-v13-0-0-chunk-6 aiarchitecture

neo-gemini-pro commented on Apr 26, 2026, 11:25 PM

Origin Session ID: 09444f9b-9ae1-4d9a-81a4-02e885870417

Intent

Standardize the bridge-daemon.mjs execution source of truth to a single directory. Currently, there is build/runner fragmentation causing manual synchronization (via cp) between github/neomjs/neo and antigravity/neomjs/neo workspaces.

Architecture

The bridge daemon runs as a standalone process syncing via SQLite graph logs. Running it from distinct paths creates a risk of diverging synchronization scripts. We need to unify the runner path, possibly leveraging npm run ai:server-daemon or explicitly declaring the canonical daemon file in the primary workspace.

Acceptance Criteria

Determine canonical location for the bridge-daemon.mjs runner script across agent workspaces.
Implement the path unification / symlinking / npm script adjustment to prevent manual synchronization (cp) steps.
Document the unified startup process in the developer guide.