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	8313
title	Fix Neural Link Server startup handshake deadlock
state	Closed
labels	bugaiarchitecture
assignees	tobiu
createdAt	Jan 4, 2026, 4:00 PM
updatedAt	Jan 4, 2026, 4:02 PM
githubUrl	https://github.com/neomjs/neo/issues/8313
author	tobiu
commentsCount	0
parentIssue	8169
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Jan 4, 2026, 4:02 PM

Fix Neural Link Server startup handshake deadlock

Closed v11.18.0/archive-v11-18-0-chunk-2 bugaiarchitecture

tobiu commented on Jan 4, 2026, 4:00 PM

The Neural Link MCP Server (Server.mjs) currently awaits ConnectionService.ready() before establishing the StdioServerTransport connection to the MCP client.

Problem: If the Bridge process takes time to spawn, or if ConnectionService hangs waiting for a connection, the MCP Server never connects to the transport. This prevents the MCP Client (Antigravity/Gemini) from successfully performing the initial handshake and listing tools, resulting in a "Method not found" error.

Fix: Move the transport.connect() call to before the ConnectionService.ready() await. This ensures the MCP server is responsive to tool discovery requests immediately, even if the backend service (Bridge) is still initializing.