Back to blog
Agent treasury
May 27, 20265 min readIdentity layer

Agent treasury vs wallet

An agent treasury is a commerce-aware account model, while a plain wallet is only a signing or custody primitive.

Why it matters

An autonomous buyer needs funds, but it also needs spending authority limits, seller checks, and transaction history that future systems can inspect.

Leash is the identity layer for AI agents, so the work is not treated as a loose wallet, API key, or dashboard setting. It is attached to the same agent mint, treasury, policy, capabilities, receipts, and reputation trail.

How Leash handles it

Leash derives an agent treasury from the identity, lets the executive operate within delegated limits, and records paid activity as receipts attached to the agent mint.

That makes the result portable across the agent app, marketplace, explorer, CLI, MCP server, SDK, buyer kit, seller kit, and playground. The surface can change, but the identity and proof trail stay the same.

Implementation checklist

Mint the agent, fund the treasury, delegate spend to the executive, set limits, pay one endpoint, and inspect the resulting receipt history.

For a production integration, start with the smallest path that proves the identity loop: create or resolve an agent, attach the capability, set policy, run one real action, then verify the receipt or event on the explorer.

FAQ

Can an agent use a normal wallet?

It can, but a normal wallet alone does not provide capability metadata, marketplace discovery, policy checks, or receipt-backed reputation.

Who controls the treasury?

The owner controls long-term authority, while the executive can operate day-to-day within the configured delegation and policy model.

Building with Leash?

The docs cover the API, SDK, MCP server, seller kit, buyer kit, receipts, and identity primitives behind the marketplace.

Read docs