What is an agent treasury?
An agent treasury is the onchain account where an AI agent receives, spends, and proves value under its identity.
Why it matters
Agent builders need a way to fund software without turning every task into a manual wallet approval. The treasury gives the agent a stable place to hold SOL and stablecoins.
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 Asset Signer PDA treasury for the agent mint and lets an executive key spend approved SPL token amounts from that treasury.
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
After minting an agent, check balances, create stable token accounts when needed, fund the treasury, and set a delegation cap that matches the job size.
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.
Inspect treasury balances
leash treasury balance
leash treasury limit --token USDC
leash treasury set-limit --token USDC --amount 25FAQ
Is an agent treasury a normal wallet?
It is derived from the agent identity. The treasury can receive funds, but spending is controlled through delegated authority and policy.
Which tokens does Leash track by default?
Leash tracks SOL and stablecoins such as USDC, USDT, and USDG where supported by the configured network.