Skip to content
Draft v0.1 — April 2026

The Secure
Intelligence Layer
for the Agentic Web

A decentralized, privacy-preserving AI inference protocol native to Solana. Hardware-enforced privacy via TEE enclaves. Agent-sovereign wallets. Sub-penny micro-payments at machine speed.

Solana Throughput
Block Finality
Avg Tx Cost
Inference Round Trip
The Problem

Legacy infrastructure
built for humans,
not machines

OpenAI, Anthropic, Google — extraordinarily capable systems. Also surveillance infrastructure. Every prompt logged, every completion retained, policy layers neither transparent nor deterministic. For an autonomous agent, this is not inconvenience. It is architectural failure.

01 — Visibility

Everything is Logged

Every prompt and context window flows through infrastructure that retains and analyzes it. An agent's reasoning is its cognitive process — routing it through a provider that logs everything is a live security breach.

02 — Control

Selective Censorship

Content filters are neither transparent nor deterministic. They change without notice. An agent cannot have its reasoning silently redirected by a policy layer it cannot inspect.

03 — Economics

Wrong Billing Model

SaaS subscriptions assume a human on the other end. An agent executing thousands of inference calls per hour needs to pay per call, in fractions of a cent, without human authorization.

"A privacy policy is a legal instrument. It is enforced after the fact, if at all. There must be a Separation of Mind and State — isolated not by policy, but by mathematics and hardware."
Protocol Architecture

The lifecycle
of a prompt

From agent runtime to inference enclave and back. Six steps. Zero exposure to the node operator, the relay network, or any centralized party.

01
Key Provisioning in TEE
An Ed25519 keypair is generated inside a TEE enclave using hardware entropy. The private key never exits — the agent's identity and wallet are rooted in hardware-enforced secrecy.
02
Client-Side Encryption
The full inference payload is encrypted client-side via X25519 + ChaCha20-Poly1305. Plaintext never traverses an unencrypted channel.
03
Onion-Routed Delivery
The payload routes through a permissionless relay network. No single relay can correlate origin with destination. Relay fees settle per-hop via Solana MPP.
04
Decryption Inside the Enclave
Decryption happens inside the TEE hardware boundary — invisible to the node operator. The model hash is included in the attestation report, proving an unmodified, known model processed the request.
05
Stateless Inference & Memory Wipe
Each request is stateless. On completion, the enclave executes a deterministic, enclave-enforced memory wipe — included in the attestable code path any verifier can inspect.
06
Encrypted Response & Atomic Payment
The completion returns encrypted to the agent. Payment settles atomically — if payment fails, the completion is not released. If the completion is withheld, payment is not signed.
Network Topology
Agent Runtime
Ed25519 Wallet
encrypt payload
Relay Node α
permissionless
onion layer 1
Relay Node β
permissionless
onion layer 2
Relay Node γ
permissionless
decrypts inside TEE
Inference Enclave
Intel SGX / AMD SEV
atomic settlement
Solana
$0.000025 / tx
Active Node
Idle
Core Properties

Infrastructure
designed for actors,
not tools

Hardware

Private by
Hardware

The TEE enclave proves the guarantee — no trust in operators required. Remote attestation, signed by the hardware manufacturer's root of trust, lets any party verify that a specific codebase is running unmodified. The node operator sees electricity consumed and a token payment received.

Intel SGX · AMD SEV · ChaCha20-Poly1305
X25519 key exchange · Remote Attestation
Models

Censorship-
Resistant by Design

Open-source models only. No policy filtering layer. No content moderation between an agent's reasoning and its compute. Llama 3.1, Mistral, Qwen 2.5, DeepSeek R1 — weights are cryptographically hashed and content-addressed. The inference node cannot serve a backdoored variant.

Llama 3.1 70B / 405B · Mistral · Qwen 2.5
DeepSeek R1 · Content-Addressed Registry
Wallet

Economically
Sovereign

Each agent controls its own non-custodial Solana wallet, provisioned inside a TEE. The private key never exists in plaintext outside the enclave. The agent pays for its own compute, receives payment from other agents, funds downstream workflows — without a human in the payment loop.

Ed25519 Keypair · TEE Platform Sealing
Non-Custodial · Programmatic Spending Limits
x402

Machine-Speed
Finance

Solana's $0.000025 per-transaction cost makes per-inference micro-payment settlement economically rational at any scale. The x402 standard enables agents to encounter a paywall, pay it, and continue — automatically, in under 500ms — with no account registration required.

HTTP 402 · Solana MPP Streaming Payments
x402 Standard · <500ms payment round trip
Unified Agentic Wallet
TEE Provisioned
7xKXtg2mF9NjB...pQr4Bn3Qw
12.4831
USEPOD Token
Recent Transactions
Inference · Llama 3.1 70B · 847 tokens
2ms ago
−0.00084
Relay fee · 3-hop routing
2ms ago
−0.00003
x402 · Data feed access
41ms ago
−0.00100
Received from parent agent
1s ago
+5.00000
Private key sealed in Intel SGX enclave — never exits in plaintext
Unified Agentic Wallet

Financial sovereignty
for autonomous agents

In the current paradigm, agents have no financial identity. A human funds an account, embeds a key, and the agent becomes a cost center on someone else's balance sheet. That model cannot survive multi-agent systems where agents transact with each other.

Pay for inference compute without a human authorizing each payment
Receive payment from other agents for services rendered
Fund child agents in hierarchical multi-agent workflows
Operate indefinitely within provisioned spending limits — no human intervention
Developer Experience

Two lines
to migrate

The TypeScript SDK mirrors OpenAI's API surface — same function signatures, same streaming patterns, same completion object shapes — but routes through the privacy stack and handles x402 payments automatically from the agent's provisioned wallet.

No account registration. No API key. No dashboard. No terms-of-service clickthrough. An agent with a funded wallet and the endpoint can make its first inference call within five minutes.

OpenAI-compatible SDK surface
Automatic x402 payment from agent wallet
Streaming completions with per-token billing
LangChain · LlamaIndex · CrewAI integrations
Wallet provisioned on first call — no ceremony
Before
After
x402 Payment
// OpenAI-based agent inference
import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
  // Your prompts are logged.
  // Your context is retained.
  // Policy filters may silently redirect
  // your agent's reasoning at any time.
});

const completion = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: context }],
});
// UsePod — private, sovereign inference
import { PrivateInference } from '@usepod/sdk';

const client = new PrivateInference({
  wallet: agentWallet, // TEE-provisioned Ed25519
  // Prompts encrypted before leaving your runtime.
  // Payment automatic via x402 + Solana.
  // No account. No API key. No policy layer.
});

const completion = await client.chat.completions.create({
  model: 'llama-3.1-70b',
  messages: [{ role: 'user', content: context }],
  // Identical API shape. Two lines changed.
});
// x402 — machine-native payment protocol
// Agent encounters a paywall → pays → continues

// HTTP 402 response from any x402 endpoint:
const paymentSpec = {
  network: 'solana',
  amount:  '0.0001',
  token:   'USDC',
  payTo:   '7xKXtg...Bn3Qw',
  expires: 1714000000,
};

// SDK handles automatically:
// 1. Parse 402 response
// 2. Construct Solana tx from agent wallet
// 3. Submit → receive signature (<500ms)
// 4. Retry request with X-Payment header
// Zero human intervention required.
Economics

Why the math
only works on Solana

An autonomous agent running a research pipeline might make 1,000 inference calls in an hour at $0.001 each. That requires 1,000 on-chain payment settlements. The economics of the payment layer are non-negotiable.

Metric Ethereum L1 Base (L2) Solana
Avg Transaction Fee $2–$15 $0.01–$0.10 $0.000025
Theoretical TPS ~15 ~2,000 65,000+
Optimistic Finality 12–14 sec 2–4 sec ~400ms
1,000 Settlements Cost $2,000–$15,000 $10–$100 $0.025
Streaming Payments Not viable Limited Native MPP
Agent Economy Fit ✗ Architecturally wrong Marginal ✓ Purpose-built
Who It's For

Built for builders,
agents, and operators

01
DeFi Agents
Your agent's strategy is visible to every centralized provider whose API you call. That is a live attack surface for front-running and strategy theft.
Hardware-enforced inference privacy closes it.
02
Solana Developers
Already building agent frameworks or on-chain AI integrations. Direct pain around the privacy and censorship limits of centralized providers.
Two lines of code. Wallet-based auth. No dashboard.
03
Enterprise AI Teams
Healthcare, legal, and financial teams with strict data residency requirements. The TEE architecture provides a verifiable audit trail no centralized provider can match.
Provably private. Cryptographically auditable.
04
Node Operators
Inference nodes earn 90% of every inference fee. Stake to participate. Clients verify your node runs unmodified code via attestation — no reputation required.
Trust rooted in hardware, not reputation.
The Protocol

The future of software
is agent-first.

The infrastructure that serves it must be built to a different standard. Private by hardware. Sovereign by design. Machine-speed by necessity.

Building agent systems? Running GPU capacity? Investing in foundational infra?
100x.dev — Christopher Ryan Gilbert