AetherMesh carries live audio over LiveKit WebRTC into a streaming realtime model and back, with a Rust transport core tuned for minimal added latency — the backbone for conversational voice products.
Part of my Senior Hybrid Engineer 2026 portfolio (
AX-01). Built on the "Antigravity" model — logic, state, and UI run locally in Docker while heavy reasoning is offloaded to cloud APIs, so the whole system runs on modest hardware.
# 1. Clone
git clone https://github.com/Kimosabey/aether-mesh.git
cd aether-mesh
# 2. Install
# (see docs/GETTING_STARTED.md for the full setup)
# 3. Run
docker compose up- WebRTC media transport via LiveKit
- Streaming to a realtime voice+LLM API
- Rust core for low-latency handling
- Backbone for the voice product line
%%{init: {'theme':'base','themeVariables':{'primaryColor':'#ffffff','lineColor':'#2563eb','mainBkg':'#ffffff'}}}%%
graph LR
A([Client])
B([LiveKit SFU])
C([OpenAI Realtime])
D([Stream Back])
A --> B
B --> C
C --> D
style A fill:#eff6ff,stroke:#2563eb,stroke-width:2px,color:#1e40af
style B fill:#eff6ff,stroke:#2563eb,stroke-width:2px,color:#1e40af
style C fill:#eff6ff,stroke:#2563eb,stroke-width:2px,color:#1e40af
style D fill:#eff6ff,stroke:#2563eb,stroke-width:2px,color:#1e40af
Shaving latency across a WebRTC → model → WebRTC round-trip so the conversation feels instant.
See docs/ARCHITECTURE.md for the full HLD/LLD and design decisions.
| Layer | Technology | Role |
|---|---|---|
| LiveKit | LiveKit |
WebRTC media server (SFU) |
| OpenAI Realtime | OpenAI Realtime |
Streaming voice + LLM API |
| Rust | Rust |
Memory-safe performance core |
- Architecture — high- and low-level design, decision log
- Getting Started — prerequisites, setup, environment
- Failure Scenarios — fault analysis and recovery
- Interview Q&A — deep-dive walkthrough
- Adaptive jitter buffering
- Multi-party rooms
- Edge relay nodes
Released under the MIT License.
Harshan Aiyappa Senior Full-Stack Hybrid AI Engineer Voice AI • Distributed Systems • Infrastructure
