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	9952
title	Sandman Handoff: Top 5 Actionable Tasks Dashboarding
state	Closed
labels	documentationenhancementai
assignees	tobiu
createdAt	Apr 13, 2026, 11:28 AM
updatedAt	Apr 14, 2026, 11:21 AM
githubUrl	https://github.com/neomjs/neo/issues/9952
author	tobiu
commentsCount	0
parentIssue	160
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[x] 9939 Epic: Autonomous Worker Dispatcher Pipeline (RLAIF Phase 2)
closedAt	Apr 14, 2026, 11:19 AM

Sandman Handoff: Top 5 Actionable Tasks Dashboarding

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

tobiu commented on Apr 13, 2026, 11:28 AM

Goal

Elevate sandman_handoff.md from a passive dream summary into an executive, high-level priority dashboard for the Strategic Co-Founder persona.

Implementation Checklist

Optimize the DreamService topological extraction logic to dynamically dump prioritized active tickets natively into the handoff file.
- Sliced the capability gaps to Top 5 per vector to reduce noise, adding cumulative counts to headers for high-level observability.
- Prepended a 'Latest Priority Backlog' to extract the top 5 highest open tracking IDs, stripping any natively tagged needs-re-triage tasks.
- Display extracted GitHub Issue labels inline (e.g., [needs-re-triage]) using Markdown to provide architectural visibility.
Ensure the file is strictly formatted to eliminate "Zero-State Amnesia" upon boot, providing Frontier Models with immediate context-switching targets without requiring manual tool queries.
- Hardened string-interpolation logic to prevent excessive whitespace generation and redundant empty lines in the output markdown payload.
- Implemented deduplication logic checking the goldenIds Set() to prevent duplicate references appearing in both Computed Golden Path and Latest Backlog arrays natively.

tobiu cross-referenced by #9963 on Apr 13, 2026, 1:13 PM

tobiu cross-referenced by PR #9995 on Apr 14, 2026, 11:16 AM