ARIA – Voice-native 3D spatial AI SoC with governed autonomy (BSL 1.1) ARIA, a voice-native 3D spatial AI security operations cockpit with governed autonomy, is now available under BSL 1.1 for evaluation and research. Developed by a solo developer, the platform runs entirely on user hardware and features a four-rung autonomy ladder where capabilities must earn authority through measured outcomes, with all actions written to an append-only audit log. ARIA supports local speech-to-text via Whisper and enforces data sovereignty by refusing to send prompts to public hosts unless explicitly configured. A voice-native, 3D spatial security operations cockpit with governed autonomy — that runs entirely on your own hardware if you want it to. Source-available for evaluation and research. Not open source — see License. Most AI security tools act and then ask you to trust them. ARIA inverts that: every autonomous capability has to earn its authority through measured outcomes, and you can see and bound exactly how far it is allowed to go. It is a single-operator SOC cockpit you talk to. The entire feature set is a navigable 3D galaxy rather than a sidebar of menus. It ingests telemetry from your cloud, identity, code, and network surfaces, explains what matters in plain language, and proposes bounded actions that are gated by policy and written to an audit trail. Honest status:ARIA is a working platform under active solo development, not a hardened commercial product. It is genuinely functional — real connectors, real local network and BLE discovery, real audit trails, a real local-model path — but parts of it are demo-grade and labelled as such throughout this README and in the product itself. Nothing here is presented as more finished than it is. →is the full engineering audit, published unedited: module-by-module status with file paths and line numbers, naming exactly which subsystems are production-grade and which are simulated. If it disagrees with this README, believe it instead. A shorter summary is in ROADMAP AND LIMITATIONS.md Maturity & what is not done below. The whole platform is a Three.js/WebGL galaxy. Sectors are capability domains; nodes are individual panels. A three-tier colour system blue nominal → amber threat → red critical propagates live from scan and telemetry state, so posture is legible from across the room. Four interchangeable ways to navigate: click a node, speak a destination, type a command, or let ARIA route you automatically when a critical event fires. The core idea, and the reason the rest exists. Autonomy is not a global on/off switch — it is per-capability and earned . Four capabilities threat analysis , remediation , containment , identity actions each sit independently on a four-rung ladder: | Rung | Mode | Behaviour | |---|---|---| | 1 | approval | ARIA proposes; a human approves every action | | 2 | assisted | ARIA acts on low-risk items, escalates the rest | | 3 | auto | ARIA acts autonomously except on critical-risk actions | | 4 | full auto | ARIA acts, and reports | Promotion requires a track record of measured outcomes. Crucially, the model cannot promote itself — a capability only climbs when an operator promotes it, and demotion on a bad outcome is immediate. Every promotion, demotion, approval and action is written to an append-only audit log with a retention envelope. Two-way spoken conversation over live data, not a chatbot bolted to a dashboard. Speech-to-text is always local Whisper via @xenova/transformers — your voice never leaves the machine. Text-to-speech is an optional cloud call you can leave unconfigured. ARIA is built for regulated environments where sending telemetry to a third-party SaaS is not merely undesirable but illegal. In LOCAL mode reasoning runs against your own model over an OpenAI-compatible endpoint Ollama, vLLM, LM Studio, llama.cpp and the sovereignty boundary is enforced in code, not promised in docs : server/localLlm.mjs refuses to send a prompt to any host outside loopback or a private range. A public address is rejected unless you explicitly set ARIA LOCAL LLM ALLOW REMOTE=true . LOCAL mode never silently falls back to a cloud provider, even when a cloud API key is sitting right there in your environment. If your local engine is down you get a clearly-labelled degraded summary and the reason — not a quiet egress.- The server binds to loopback by default and is not designed to face the internet. AI Security Posture Management across GitHub, AWS, Okta, Snyk, Azure AD, VirusTotal, and Elastic Security — inventorying AI assets, secrets, model infrastructure, endpoints, and identity links, then mapping attack paths and blast radius across them. Connector credentials are encrypted at rest with AES-256-GCM. Real ARP-table and BLE discovery with IEEE OUI vendor attribution and Bluetooth assigned-number decoding, device identity claims, and proximity estimation. Broadcast and multicast MACs are filtered at parse time rather than reported as devices. Active discovery is authorization-gated; passive visibility is not. Under five minutes, no API keys required — ARIA starts with local-only features and every AI provider disabled but visibly labelled as such. Node.js ≥ 22 uses node: builtins and native fetch npm or pnpm Optional: Ollama https://ollama.com for sovereign local reasoning Optional: Docker, for the containerised server git clone https://github.com/