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	9639
title	Local LLM Provider Adapter (Ollama + Gemma-4)
state	Closed
labels	epicaiarchitecture
assignees	tobiu
createdAt	Apr 3, 2026, 12:44 PM
updatedAt	Apr 3, 2026, 1:02 PM
githubUrl	https://github.com/neomjs/neo/issues/9639
author	tobiu
commentsCount	0
parentIssue	9638
subIssues	9644 Add Neo.ai.provider.Ollama base adapter 9645 Configure Agent.mjs to orchestrate mixed providers
subIssuesCompleted	2
subIssuesTotal	2
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Apr 3, 2026, 1:02 PM

Local LLM Provider Adapter (Ollama + Gemma-4)

Closed v13.0.0/archive-v13-0-0-chunk-1 epicaiarchitecture

tobiu commented on Apr 3, 2026, 12:44 PM

Parent Epic: #9638

Problem

Currently, Neo.ai.Agent only supports the Gemini API cloud provider. To support local execution (Dream Mode / Swarm) with consumer hardware, we need a local adapter.

Solution

Create Neo.ai.provider.Ollama to conform to the provider interface, targeting the Gemma-4 model.

Implement standard /api/generate and /api/chat interaction APIs.
Ensure prompt parameter structure aligns with existing agent infrastructure.

tobiu cross-referenced by #9644 on Apr 3, 2026, 12:47 PM

tobiu cross-referenced by #9645 on Apr 3, 2026, 12:47 PM

tobiu cross-referenced by PR #10122 on Apr 20, 2026, 1:47 PM