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	7658
title	Refactor: Simplify Memory Core Protocol in AGENTS.md
state	Closed
labels	documentationenhancementairefactoring
assignees	tobiu
createdAt	Oct 26, 2025, 10:53 AM
updatedAt	Oct 26, 2025, 11:10 AM
githubUrl	https://github.com/neomjs/neo/issues/7658
author	tobiu
commentsCount	0
parentIssue	7604
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Oct 26, 2025, 11:10 AM

Refactor: Simplify Memory Core Protocol in AGENTS.md

Closed v11.0.0/archive-v11-0-0-chunk-4 documentationenhancementairefactoring

tobiu commented on Oct 26, 2025, 10:53 AM

This ticket is a sub-task of the epic #7604.

The current AGENTS.md file contains a complex, multi-step protocol for initializing the memory core. This includes manual checks, asking the user for permission, and generating session IDs.

With the recent enhancements to the neo.mjs-memory-core MCP server (auto-start, auto-summarization), we can drastically simplify this protocol.

Proposed New Protocol:

At the start of a session, the agent performs a healthcheck on the memory core server.
If the server is healthy, the agent can assume the user intends for memory to be active.
The agent will then proceed to use the add_memory tool on every turn for the duration of the session. No permission is required.
The server will transparently handle session ID generation and the summarization of previous sessions.

Acceptance Criteria:

Update the "Session Initialization" section of AGENTS.md to remove the old, complex memory core protocol.
Replace it with the new, simplified protocol described above.
Ensure the new instructions are clear, concise, and guide the agent to use the healthcheck and add_memory tools correctly.

tobiu cross-referenced by #7660 on Oct 26, 2025, 11:20 AM