On‑device AI inferencing SDK•Run anything, anywhere

Build private, fast, and affordable AI at the edge

Kernl lets you deploy state‑of‑the‑art models on phones, browsers, and embedded devices with a single SDK. Offline by default. Cloud optional.

Trusted by privacy‑conscious teams and budget‑conscious developers

See Kernl in Action

Live simulation of AI running locally on your device — no cloud required

On‑device inference
AI model running entirely on your device - no data sent to cloud servers
NPU • 4‑bit • Cached
Using specialized AI chips and optimized 4-bit model weights with caching
tokens/s
22.0
~1.0
How fast the AI generates text - higher is better
p95 latency
28 ms
edge
Time to generate each word - lower is better (cloud is ~10x slower)
memory
512 MB
model+kv
RAM used by the AI model and conversation history
power
1.8 W
device
Energy consumption - much lower than cloud data centers
Latency comparison
On‑device~30 ms
Cloud~450 ms
On-device AI responds 10-15x faster than cloud AI because there's no network delay
main.swift
local • wasm-simd • npu
import Kernl
let kernl = Kernl(apiKey: "YOUR_LIFETIME_API_KEY")

let model = try kernl.loadModel(url: "tiny-llm.krnl")
for try token in model.generateStream(prompt: "Why edge?") {
  print(token, terminator: "")
}
Initialize with a lifetime API key — validated locally, works offline; Wi‑Fi only once every 30 days for automatic renewal. No developer action required.
output
▍
Live text generation happening on your device - no internet required after initial setup

Pricing that scales with your success

Simple, predictable per‑device pricing. Billed for users, not usage.

Free
$0
per month
  • • Up to 100 devices
  • • Community support
  • • SDK & docs access
Most popular
Pro
$0.30
per device / month
  • • Production ready
  • • Email support
  • • Analytics & device management
Enterprise
Custom
significant volume discounts
  • • SSO, SAML, SCIM
  • • Priority support & SLA
  • • Dedicated success engineering

How much can Kernl save your app?

High‑level estimates based on common cloud AI pricing. Assumptions shown below.

Which of these do you use?
How many users use your app?
1,000 users
Scenarios assume each selected service is used for ~30 minutes per user per day.
Estimated monthly cloud cost
$0
Kernl Pro (@ $0.30/device)
$300
Estimated monthly savings
$0
Assumptions: STT $0.50/hr, TTS $1.50/hr, LLM $2.00/hr; ~0.5 hr/day/user; ~30 days/month. Actual costs vary by provider, model, and region.

Start building today

No setup fees • 30‑day free trial • Cancel anytime