P2P AI — peer-to-peer inference market

TokenOS P2P AI is a protocol for buying and selling AI inference directly between peers. Sellers run the open-source tokenos-p2p node in front of a GPU server (vLLM, Ollama, llama.cpp) or an API quota (OpenAI, Anthropic, Google) and announce signed metadata — services, prices per million input and output tokens, concurrency — on the public BitTorrent DHT and to the TokenOS indexer. Buyers run the same package as a local OpenAI-compatible endpoint; any OpenAI SDK can use the market by changing one base URL.

Transport is direct: the buyer node dials the seller node over TCP or WebSocket (protocol v2.1 — identical encrypted frames on either carrier), both identities sign an X25519 handshake and every frame is encrypted with ChaCha20-Poly1305. TokenOS is never in the request path and never sees prompts or completions. Identity is a Solana ed25519 keypair; the peer id is the base58 public key and doubles as the provider's USDC payout wallet.

Payment uses sessions funded from TokenOS credits, which are bought with USDC or $TOS. TokenOS holds the buyer's credits and signs a voucher capping the session; after every response the buyer signs a cumulative SpendingAuth which the seller submits for settlement. Settled amounts, net of a 4% protocol fee, accrue to the seller in USD and are paid out as USDC on Solana. Unspent credits return to the buyer when a session closes. There are no token rewards, no staking requirement and no promised income for providers.

Every provider carries a trust score computed only from checkable data: settlement history on the TokenOS ledger, share of recent network usage and verified identity proofs (DNS TXT or GitHub repository bound to the peer id). The market page lists every model at least one online peer offers, the best price, the vendor's official list price and the resulting savings, plus a public settlement explorer.

About TokenOS

TokenOS is the AI operating system for the autonomous Web3 economy. It combines an agentic IDE that turns a prompt into a deployed dApp, a marketplace of x402-paid AI agents, a peer-to-peer AI inference market where anyone can sell spare API quota or GPU time for USDC, MCP and A2A connectors for Claude, Cursor and ChatGPT, and the $TOS utility and governance token on Solana.

Builders pay with prepaid credits; sellers and agent creators are paid for work actually delivered; TokenOS indexes, verifies and settles. Nothing on this site is investment advice, and node payouts, agent payments and referral credits are fees for usage — not token distributions or returns.

How TokenOS works

Build: connect a wallet, describe the app you want and choose the chain, network and wallet providers in Live Web3 Config. The build pipeline analyses the request, generates the project, bundles a preview, runs a headless render check and repairs what fails before it hands you a verified preview. Iterate in the update chat with inline diff review, tweak visuals in Design Mode, then deploy contracts, launch a token and go live on TokenOS hosting, Vercel or Netlify.

Agents: publish x402-paid agents from the Agent Builder, let buyers try them for free and pay per call in USDC, expose them to Claude, Cursor and ChatGPT through the MCP server and to other agents through A2A agent cards, and run them on a schedule as Autopilots with an approvals inbox.

Inference: the P2P AI network lets anyone sell spare API quota or a local model to buyers who pay with prepaid credits. Sessions are encrypted end to end, the seller signs receipts for every token delivered, TokenOS verifies and settles them and pays providers in USDC on Solana. Everything is priced in credits (1 credit = $0.10 of usage) and documented at /docs.