MESH routes your AI workloads to the lowest-latency, highest-throughput nodes automatically. The protocol is designed for adversarial environments — every result is consensus-validated before delivery.

REQUEST PATH — HOW YOUR JOB RUNS
1. SUBMIT — API call or SDK. Job enters the MESH queue (Redis sorted-set).
2. MATCH — WorkMatcher pairs job to the best available node in <100ms.
3. ASSIGN — Node receives assignment via WebSocket push (or HTTP poll fallback).
4. EXECUTE — ONNX Runtime / WebGPU runs inference in the browser sandbox.
5. VALIDATE — Result hashes replicated across N nodes. Consensus threshold checked.
6. DELIVER — Verified output returned. Job marked complete. Billing settled.
PROTOCOL GUARANTEES
Delivery SLA99.7%
Result validationHash-based consensus (configurable replication)
Fault toleranceAutomatic lease re-assignment on node drop (<15s)
Nonce proofPer-job nonces prevent replay attacks from adversarial nodes
Epoch lockingLease epochs prevent stale result injection
TransportWebSocket push / HTTP poll fallback
Node selectionLatency + VRAM + utilization scoring
COMPUTE CAPABILITIES & WORKLOADS
Generative AI Multi-modal synthesis (Text/Image/Video/3D). Examples: FLUX.2, LTX-2.3, Hunyuan3D.
Scientific Computing Monte Carlo simulations, molecular dynamics, mathematical modeling via WebGPU.
Data Engineering Vector processing, point cloud transformations, large-scale feature extraction.
Media Pipeline Real-time 4K/8K upscaling, depth estimation, background removal, frame interpolation.
Custom Workloads Deploy any ONNX or WGSL-based compute kernel across the distributed grid.
EXECUTION MODES
SINGLE
One node processes the entire job. Ideal for small models (BK-SDM-Tiny, BiRefNet). Lowest coordination overhead.
PARALLEL (TILED)
Input split into tiles, each assigned to a different node. Results merged. Used by ESRGAN and SeedVR2 upscalers for large inputs.
SHARDED
Model split across N nodes — each node holds a subset of weights. Nodes communicate via WebRTC P2P. Used by FLUX.2-klein, LTX-2, Wan 2.2, Hunyuan3D 2.1, TRELLIS.2-4B, ACE-Step.

Your browser becomes a compute node. ONNX Runtime Web runs inference directly on your GPU via WebGPU — no driver install, no CLI, no server.

NODE LIFECYCLE
1. CONNECT — Node registers via MESH SDK, declares VRAM + compute capacity.
2. ADVERTISE — Sends node-available message over WebSocket. Enters Redis availability pool.
3. RECEIVE — WorkMatcher pushes assignment. Node holds lease (Redis TTL).
4. EXECUTE — Inference runs in Web Worker via ONNX Runtime. GPU stays dedicated to the job.
5. SUBMIT — Result hash + output uploaded. Lease released.
6. READY — Node re-advertises. Heartbeat refreshes Redis TTL every 30s.
SYSTEM REQUIREMENTS
BrowserChrome 113+ / Edge 113+ (WebGPU required)
GPUAny WebGPU-capable GPU (NVIDIA, AMD, Apple Silicon, Intel Arc)
Min VRAM4 GB (Tier-3). 8 GB (Tier-2). 16 GB+ (Tier-1)
Bandwidth10 Mbps+ recommended for model P2P transfer
StorageOPFS cache — 2–20 GB per model set (browser file system)
UptimeNo minimum — a device is usable whenever it is online
NODE TIERS
Tier 116 GB+ VRAMPREMIUM JOBS · 2.2× RATE
Tier 28–15 GB VRAMSTANDARD JOBS · 1.4× RATE
Tier 34–7 GB VRAMLIGHT JOBS · BASE RATE