Decentralized Inference Network

AI Intelligence,
Decentralized.

Run Large Language Models locally on any device with a browser. Host your own node, connect privately, or distribute workloads—zero installation effectively required.

Instant Local Hosting

Turn your browser into an AI node instantly. No Python environments, no drivers to install, and no complex firewall configurations.

Private & Secure

Your data stays with you. Inference runs locally on your GPU. No data is sent to third-party AI providers like OpenAI or Anthropic.

Universal API

Connect via the UI, Command Line, Python SDK, or JavaScript. Fully compatible with OpenAI-style chat completion endpoints.

Chat Interface

Natural Conversations.

Interact with advanced language models just like you would with ChatGPT. Except it runs entirely in your browser, using your own hardware.

local-chat — 80x24

Python SDK

Standard API.

Drop-in replacement for OpenAI. Point your existing Python scripts, Node.js apps, or curl requests to your local endpoint.

main.py

import openai

client = openai.OpenAI(

base_url="http://localhost:8000/v1",

api_key="sk-local"

)

res = client.chat.completions.create(

model="Llama-3-8B",

messages=[{"role": "user", "content": "Hello!"}]

)

print(res.choices[0].message.content)

$ python main.py

Decentralized Cloud

Share your GPU.

Host a model on your powerful workstation and access it securely from your phone, laptop, or let others connect to it.

Host (GPU)

RTX 4090

Client

iPhone 15

AI Intelligence, Decentralized.