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	14333
title	docs(agentos): in-depth ai/-folder capability-coverage audit — enumerate undocumented capabilities, weight them, spawn guide subs
state	Closed
labels	documentationaiarchitecture
assignees	neo-gpt
createdAt	Jun 29, 2026, 11:54 AM
updatedAt	Jun 29, 2026, 11:13 PM
githubUrl	https://github.com/neomjs/neo/issues/14333
author	neo-opus-grace
commentsCount	23
parentIssue	14310
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Jun 29, 2026, 10:01 PM
milestone	v13.1

docs(agentos): in-depth ai/-folder capability-coverage audit — enumerate undocumented capabilities, weight them, spawn guide subs

Closed v13.1.0/archive-v13-1-0-chunk-8 documentationaiarchitecture

neo-opus-grace commented on Jun 29, 2026, 11:54 AM

Part of #14310 · content rubric + §Mandatory V-B-A grounding in #14310. Refs #14310.

Problem: the doc gaps cannot be enumerated centrally — ai/ is ~132 files / ~122k LOC, more than one context window holds. A systematic audit is needed to FIND the undocumented capabilities. Operator named examples that are 100% present: the openAiCompatible + ollama providers, AiConfig nested state providers, "and so much more." (This is the systematic fix for the capability-coverage V-B-A miss — stop guessing the gaps; enumerate them.)

Acceptance Criteria

Walk ai/ (provider · services · daemons · graph · config · mcp) against the published guide inventory (learn/tree.json); produce a prioritized gap list: capability → has-guide? → uniqueness/value weight (crown-jewel vs supporting substrate).
For each high-value gap, spawn a follow-up sub linked to #14310 — @neo-opus-grace co-weights/prioritizes (the crown-jewel-vs-substrate call is architectural judgment, not a checklist).
Output = the gap list + the new linked subs (a DISCOVERY sub), not a single doc.
Use the v13.0.0 hero hierarchy as the weighting reference (forecasting/Golden Path, night-shift, identity, the self-evolving organism rank above enabling substrate like A2A/hooks).

⚠️ V-B-A grounding (mandatory): the ai/ tree (ai/provider, ai/services, ai/daemons, ai/graph, ai/config*, ai/mcp), learn/tree.json (current coverage), the v13.0.0 release notes (hero hierarchy). Capture the gap list as evidence.

Files: a gap-analysis report (issue comment / learn/agentos working note) + new linked subs under #14310.