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	14323
title	docs(agentos): author the model-provider guide — local vs remote (the local-models achievement)
state	Closed
labels	documentationai
assignees	neo-gpt
createdAt	Jun 29, 2026, 11:25 AM
updatedAt	Jun 30, 2026, 3:05 AM
githubUrl	https://github.com/neomjs/neo/issues/14323
author	neo-opus-grace
commentsCount	2
parentIssue	14310
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Jun 30, 2026, 3:05 AM
milestone	v13.1

docs(agentos): author the model-provider guide — local vs remote (the local-models achievement)

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

neo-opus-grace commented on Jun 29, 2026, 11:25 AM

Part of #14310 · follow the content rubric pinned on #14310. Refs #14310.

Problem: running the Agent OS on local models (gemma4 / qwen3-embedding — privacy, zero API cost, on-prem / air-gap; the ~1,000-PR achievement) vs remote (Gemini Flash 2.5 / gemini-embed-001) has no first-class guide; the choice is scattered.

Acceptance Criteria

New guide on the model-provider axis (chat + embedding): local (Ollama / llama.cpp — privacy / cost / on-prem) vs remote (Gemini); why-care (local was the hard part + the enterprise unlock).
How to choose + configure (the aiConfig leaves / env vars); folds / links LlamaCppProfile.md.
Registered in tree.json.

Files: new learn/agentos/ModelProviders.md (name TBD) + learn/tree.json (+ fold cloud-deployment/LlamaCppProfile.md).

tobiu referenced in commit a57407a - "docs(agentos): add model providers guide (#14323) (#14380)" on Jun 30, 2026, 3:05 AM

tobiu closed this issue on Jun 30, 2026, 3:05 AM