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	7959
title	Epic: Agent Security & Capabilities
state	Closed
labels	epicstaleaiarchitecture
assignees	[]
createdAt	Nov 30, 2025, 10:52 PM
updatedAt	Oct 9, 2026, 6:12 PM
githubUrl	https://github.com/neomjs/neo/issues/7959
author	tobiu
commentsCount	3
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Mar 15, 2026, 5:08 AM

Epic: Agent Security & Capabilities

Closed v12.1.0/archive-v12-1-0-chunk-1 epicstaleaiarchitecture

tobiu commented on Nov 30, 2025, 10:52 PM

Define and implement the security model for Agent-initiated browser actions.

Scope:

Capability Taxonomy: Define granular permissions (e.g., component:read, component:write, code:load).
Policy Enforcement Point (PEP): Implement middleware in Neo.ai.server.WebSocket to validate RPC calls against the Agent's capability token.
Sandboxing: Ensure Agents cannot execute arbitrary JavaScript (e.g., eval) in the browser context unless explicitly authorized.
Audit Logging: Record all Agent-initiated actions for security review.
Default Deny: All capabilities require explicit grant.
Emergency Kill Switch: Ability to revoke agent access immediately.

Reference: .github/AGENT_ARCHITECTURE.md

tobiu added the epic label on Nov 30, 2025, 10:52 PM

tobiu added the ai label on Nov 30, 2025, 10:52 PM

tobiu added the architecture label on Nov 30, 2025, 10:52 PM