About SYRIX - by Avananka

A routed AI runtime,
built from the cockpit up.

SYRIX began as a voice assistant and now runs as a local-first, provider-aware JARVIS/SYRIX system: brain routing, HUD widgets, voice, memory, live web, research tools, and guarded automation.

SYRIX
NIM
HUD
Voice
Memory
Current Runtime

Phase-2B HUD contract

Widget commands travel through the SyrixBridge to hud_control.json, backend handlers update hud_state.json, and rolling acknowledgements keep UI actions visible.

Brain Router

13 specialist roles

NVIDIA NIM handles specialist roles when healthy, with Groq llama-3.3 cloud inference and Ollama local fallback routes available.

Guarded

Approval-aware action

OpenClaw, guardian-shell previews, circuit breakers, and locked broker execution keep risky actions explicit and reviewable.

What Avananka Builds

Real modules, not theatre.

The current codebase shows a practical assistant stack: local memory, voice/audio plumbing, Electron HUD state, live web providers, financial research, and safety gates.

AI

Role-based routing

Main reasoning, coding, deep reasoning, vision, multimodal, rerank, and safety tasks route through configured model roles instead of one fixed model.

HUD

Electron cockpit

The HUD uses WebSocket state on port 5111 plus JSON bridge files for chat, control, diagnostics, widgets, memory, and system panels.

AUD

Voice and sound

PyAudio capture, Faster-Whisper STT, wake-word support, Shazam/music hooks, Piper chunked TTS, barge-in, and fallback voices.

WEB

Live provider stack

Open-Meteo, RSS, SearXNG, Wikipedia, DuckDuckGo, yfinance, Stooq, TradingView routes, maps, and optional Finnhub support.

MEM

Local-first memory

Short-term memory, JSON storage, Chroma fallback vector recall, markdown exports, and inspectable brain logs keep personal context grounded.

FIN

Research, not execution

Trading modules focus on watchlists, SMC/FI analysis, paper-mode reasoning, sentiment context, and circuit breakers. Broker execution is locked by default.

Avananka is built by Kabirr Kohli as a serious personal AI architecture: futuristic in interface, honest about providers, and guarded where real-world actions matter.

Build Foundation

The K-7 rig is the target cockpit.

The project is tuned around a Windows desktop setup with RTX 4060 Ti, i7-12700K, 32 GB DDR5, microphone, speakers, and local/provider routes configured per module.

PythonElectron HUDNVIDIA NIMGroqOllamaFaster-WhisperPiper TTSOpen-MeteoyfinanceJSON Memory
Contact

Access and support go direct.

For support, early access, or partnership questions, contact the project owner.

kabirrkohli01@gmail.com