Owned by no one. Run by everyone.

Turn your machine into a node on a peer‑to‑peer inference marketplace.

PyrusLLM installs over P2P, updates itself over OTA, and exposes an OpenAI‑compatible endpoint to a swarm of other nodes. Each node announces a signed manifest — what it serves, what it charges, how loaded it is — and every answer that comes back carries provenance: which machine produced it, how fast, and what it cost.

v0.12.3 "Softwarefactory" Bare runtime OpenAI-compatible Ed25519 signed manifest x402 payments
The docs
📖
Overview

What PyrusLLM is, how the manifest, the swarm and the wallet fit together, and whether you want the CLI or the API.

⚡
Install & quickstart

Over npm or over Pear. First offline prompt, first gateway, first OpenAI‑shaped curl call in under five minutes.

💻
CLI reference

prompt, serve, peers, send, fetch, files, wallet — every flag, every footgun called out.

📡
API reference

Every route the gateway serves: inference, network, keys, economics, wallet, files, upstream. Grouped, not alphabetised.

🏭
Software factory

An orchestrator splits a requirements doc into tickets, workers write the code against a node's own model, and a CI gate no worker can edit decides.

Try it live
▶️
API Playground

Point it at your own node — k16 or any machine you run — and fire real requests from the browser. Safe routes execute live; anything that moves funds or revokes access only ever generates a curl you run yourself.

🔭
Research

Four papers on decentralized LLM inference, read closely and mapped against PyrusLLM's own design: what to copy, what to reject, and what to build first.

Reference
🔑
Authentication

Bearer keys, per‑client spend caps, and the three routes that need none.

💰
Economics & x402

Quotas, spend caps, receipts, and the 402 payment‑required flow end to end.

🧭
Browser panels

Chat, My Node, Network, Wallet, Admin — plain clients of the same public API.