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	10190
title	Implement chosen shared caching substrate for Memory Core
state	Closed
labels	enhancementaiarchitecture
assignees	neo-gemini-pro
createdAt	Apr 22, 2026, 8:33 PM
updatedAt	Apr 23, 2026, 11:09 AM
githubUrl	https://github.com/neomjs/neo/issues/10190
author	neo-gemini-pro
commentsCount	1
parentIssue	10186
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[ ] 10183 MCP Server Integration Testing Harness for CallToolRequestSchema, [x] 10189 ADR for shared caching substrate for Memory Core
blocking	[]
closedAt	Apr 23, 2026, 11:09 AM

Implement chosen shared caching substrate for Memory Core

Closed v13.0.0/archive-v13-0-0-chunk-5 enhancementaiarchitecture

neo-gemini-pro commented on Apr 22, 2026, 8:33 PM

Context

An ADR will determine the appropriate shared caching substrate to replace the per-process singleton cache in GraphService.

The Problem

We need to implement the shared substrate to eliminate cross-process cache divergence.

The Architectural Reality

Replaces the vicinityLoadedNodes per-process caching logic with the ADR-selected shared substrate.

The Fix

Implement the chosen shared caching layer (Chroma, SQLite-backed, or daemon-mediated IPC) based on the ADR decision from the predecessor ticket.

Acceptance Criteria

Implement the shared caching substrate.
Testing A→seed / B→read divergence shows consistent state across multiple processes.

Out of Scope

Fixing Antigravity's twin-language-server upstream bug.

Parent Epic: #10186
Blocked by ADR ticket (#10189) and MCP test harness (#10183).

Handoff Retrieval Hints

query_raw_memories(query="cross-harness MCP singleton cache divergence")

tobiu referenced in commit 8dd71cc - "fix(ai): harden Database cache coherence natively and prevent multi-worker lock conflicts (#10190) (#10221) on Apr 23, 2026, 11:09 AM

tobiu closed this issue on Apr 23, 2026, 11:09 AM

tobiu referenced in commit 057130b - "feat(memory-core): healthcheck identity observability block (#10176) (#10239) on Apr 23, 2026, 3:56 PM