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	9975
title	Hardening Agent Intake via Empirical Verification & Historical Domain Querying
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Apr 13, 2026, 4:57 PM
updatedAt	Apr 14, 2026, 12:31 AM
githubUrl	https://github.com/neomjs/neo/issues/9975
author	tobiu
commentsCount	0
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Apr 13, 2026, 5:12 PM

Hardening Agent Intake via Empirical Verification & Historical Domain Querying

Closed v13.0.0/archive-v13-0-0-chunk-4 enhancementai

tobiu commented on Apr 13, 2026, 4:57 PM

Architectural Paradox

Currently, the ticket-intake skill relies on "agent intuition" (e.g., asking "didn't we try this before?") to trigger historical verification against the Memory Core. However, fresh Swarm instances suffer from "Zero-State Amnesia" and inherently lack intuition. Additionally, agents tend to blindly accept prescribed architectural solutions within tickets instead of isolating the true root cause, leading to Negative ROI.

Resolution

This ticket formalizes two systemic mandates across the Neo.mjs Agent OS:

Historical Amnesia Check (Unknown Unknowns): Agents MUST explicitly perform a blind domain query (query_documents, query_summaries, query_raw_memories) against the Memory Core regardless of how novel a ticket seems.
Empirical Proof (Test-Driven Discovery): Agents MUST explicitly validate technical hypotheses by writing localized Playwright tests via the unit-test skill before mutating live architecture.

Definition of Done

Update .agent/skills/ticket-intake/references/ticket-intake-workflow.md with the new Historical Amnesia (Unknown Unknowns) and Empirical Proof mandates.
Update .agent/skills/pull-request/references/pull-request-workflow.md to require missing unit tests as a pre-commit block for "Minor Gaps".

tobiu cross-referenced by PR #9976 on Apr 13, 2026, 4:58 PM