Wiki
The educational layer for the onchain agent economy. Clear, high-signal explainers on the concepts you're building on. No hype.
What Are Onchain Agents?
Onchain agents are autonomous AI agents that can interact with blockchain systems, holding wallets, signing transactions, reading chain data, and executing workflows across protocols without constant human input.
Updated 2026-06-24
What Are MCPs? The Standard Way to Give Agents Tools
The Model Context Protocol (MCP) is an open standard, introduced by Anthropic, that defines how AI applications connect to external tools, data sources, and services. MCP servers expose capabilities; AI clients consume them.
Updated 2026-06-24
What Are Agent Skills?
Agent skills are packaged, reusable capabilities (code, prompts, tool definitions, and workflows) that give an agent the ability to perform a specific kind of task. Skill repos are libraries of these capabilities that builders can compose.
Updated 2026-06-24
How Agents Use Wallets
Agent wallets are key-management systems that let an AI agent sign transactions programmatically, ideally with policies, spend limits, and approval flows that constrain what the agent can do.
Updated 2026-06-24
How Agents Interact With Smart Contracts
Agents interact with smart contracts in two modes: reading state (balances, prices, governance proposals, events) and writing state (swaps, transfers, votes, deployments). Reading is low-risk; writing is where guardrails matter.
Updated 2026-06-24
Onchain Agents vs Offchain Agents
Offchain agents automate work inside Web2 systems, email, docs, CRMs, code. Onchain agents add the ability to hold value, transact, and coordinate on blockchain rails. The difference is economic agency.
Updated 2026-06-24
What Is x402?
x402 is an open payment standard that lets software — including AI agents — pay for APIs and content directly over HTTP, using the long-dormant 402 "Payment Required" status code to settle stablecoin payments from a wallet instead of an API key.
Updated 2026-06-24
How Do AI Agents Pay?
AI agents pay by signing transactions from their own wallet — usually in stablecoins for per-request micropayments — through one of several competing standards (x402, Google's AP2, Visa's Trusted Agent Protocol) that define how an agent proves what it's allowed to buy and settles the bill.
Updated 2026-06-24
How to Build an Onchain Agent
Building an onchain agent means wiring a reasoning model to a policy-controlled wallet and a set of skills, fencing it with guardrails, then proving it on a testnet before it touches mainnet funds.
Updated 2026-06-24
What Are AI Trading Agents?
AI trading agents are autonomous onchain agents that hold a wallet and execute trades on DEXs and perps venues within preset risk limits — reasoning over market data instead of running a fixed script.
Updated 2026-06-24
What Is an AI Agent Framework?
An AI agent framework is a software toolkit that bundles the pieces an autonomous agent needs — a reasoning loop, tool/skill connectors, wallet and key handling, memory, and guardrails — into one runtime, so builders ship behavior instead of plumbing.
Updated 2026-06-24
What Is ERC-8004?
ERC-8004, the "Trustless Agents" standard, is a Draft Ethereum proposal that gives onchain agents a portable identity, a reputation record, and a validation layer through three registry contracts — so an agent's track record can be checked, not just claimed.
Updated 2026-06-24
What Is the Onchain Agent Economy?
The onchain agent economy is the emerging system where autonomous AI agents hold wallets and transact on public blockchains — earning, paying, and coordinating with each other over shared rails for payments, identity, and execution.
Updated 2026-06-24
AI Agent Identity and Verification
AI agent identity is how an autonomous agent proves which entity it is across systems; verification is the separate, harder job of confirming that what the agent claims about itself — its work, reputation, and behavior — actually holds up to evidence.
Updated 2026-06-24
What Is an Agent Launchpad?
An agent launchpad is a platform that lets anyone deploy an onchain AI agent — usually with its own token — in minutes, without writing the wallet, contract, or hosting code from scratch. The launchpad is the deployment venue; the agent is what gets deployed.
Updated 2026-06-24
Onchain Agent Security: The Threat Model
Onchain agent security is the practice of containing what an autonomous agent can do with the keys it holds — through key management, prompt-injection defenses, permission scoping, spend limits, and verifiable review rather than self-reported assurances.
Updated 2026-06-24
What Is an AI Agent Marketplace?
An AI agent marketplace is a venue where AI agents (or their skills) are listed, discovered, hired, and paid — increasingly with on-chain escrow and identity. The marketplace is the storefront and settlement layer; it is not itself an agent.
Updated 2026-06-24
Join the Sato Hub Briefing
One email a week — the agents, tools, and infrastructure that actually shipped, and why they matter.