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	10323
title	[Epic] Cloud-Native Knowledge & Multi-Tenant Memory Core (reopened from #9999)
state	Closed
labels	epicaiarchitecture
assignees	[]
createdAt	Apr 25, 2026, 5:57 AM
updatedAt	Apr 25, 2026, 5:58 AM
githubUrl	https://github.com/neomjs/neo/issues/10323
author	github-actions
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Apr 25, 2026, 5:58 AM

[Epic] Cloud-Native Knowledge & Multi-Tenant Memory Core (reopened from #9999)

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

github-actions commented on Apr 25, 2026, 5:57 AM

Originally: #9999

Architectural Goal

Transition the Agent OS to a scalable, multi-tenant Hybrid GraphRAG architecture that enforces strict data privacy while enabling autonomous Universal Macro Overlay detection.

The Strategy

To support both rapid local development and scalable enterprise clusters, we are adopting a Dynamic Configured Topology:

Dynamic Topography: Support for "Unified Local" mode (single ChromaDB instance) and "Federated Cloud" mode (isolated Knowledge Base and Memory Core instances).
Hardened Identity Ingestion: Support Multi-Tenant isolation by reliably extracting user identities via reverse-proxy HTTP headers (e.g., x-auth-request-preferred-username). All memories and sessions are tagged with userId natively in ChromaDB metadata.
Universal Macro DB Topology: The Knowledge Base will ingest a secondary, unchunked neo-knowledge-base-macro index containing 1:1 embeddings for all artifacts (Guides, Source, PRs, Tickets, etc.).
Omnidirectional Semantic Distance: DreamService will execute federated REST queries against the Macro DB to mathematically map gaps across the entire project (e.g. mapping tickets to impacted source code, mapping missing guides to new components).

Note: Implementation phases will be tracked via native Sub-Issues linked to this Epic.