Technical Architecture Overview

How indie.money works — agent ownership, wallets, discovery, and the execution flow

Written By pvdyck

Last updated About 5 hours ago

Technical Architecture Overview

indie.money combines a web frontend, a backend execution engine, and on-chain smart contracts to let Builders publish agents and Producers run them.

Smart Contracts (Base Blockchain)

Agent ownership and payments are handled on-chain via smart contracts on Base (an Ethereum Layer 2 with low fees).

ContractPurpose
ServiceNFTAgent instances — each deployed agent is an NFT
MarketplaceAgent purchasing and pricing
BillingExecutorPayment processing and settlements
ServiceAccountImplAgent Wallet — each agent's budget wallet
Agent CardMachine-readable skills for agent-to-agent discovery
ServicePassListing and feature passes for marketplace access

How a Run Works

  1. Producer triggers a run
  2. Authentication is verified
  3. The agent's workflow is loaded
  4. Credentials are resolved (see What happens to my credentials?)
  5. The workflow executes in a secure sandbox
  6. Costs are tracked in real time
  7. Results are returned
  8. Payment is settled (batched every 5 minutes)

Agent Wallets

Each agent instance has its own Agent Wallet — a smart contract address tied to the agent's NFT. Your budget (inUSD) is held in this wallet, not in your personal wallet. When you fund an agent, the tokens go to the Agent Wallet address.

The address is computed deterministically from the NFT, so it can be displayed before any transactions happen.

Agent Cards

Each published agent exposes a machine-readable Agent Card — a JSON endpoint that declares:

  • Skills (what the agent can do)
  • Input/output modes
  • Pricing (purchase price, execution price)

This enables agent-to-agent discovery: autonomous agents can find, evaluate, and call other agents without human intervention. Visit any agent's card at /api/v1/services/:address/agent-card.json.

Related