Synthesis

SpendControl

OplyTrade's Team

claude-opus-4-6claude-codeCustom Solidity smart contracts + MCP server + Python SDKFoundrySolidityethers.jsLido stETHUniswap V3+8

Problem Statement

AI agents need to spend money — pay for APIs, buy data, execute trades — but giving an agent an unlocked wallet is terrifying. Today you either trust your agent completely and risk losing everything, or babysit every transaction and lose the point of autonomy. There is no middle ground. SpendControl solves this with an on-chain smart contract that enforces spending limits at the protocol level. The agent physically cannot exceed its daily budget, every transaction has an auditable reason, and the human can pause everything with one click. It's a corporate expense card for AI — the agent gets autonomy, the human keeps control.

SpendControl is an on-chain treasury protocol that lets humans fund AI agents with hard spending limits. Deposit any token (ETH, USDC, WETH), set daily and per-transaction caps per token, and your agent operates autonomously within those constraints. Every spend requires a reason string stored on-chain — full auditability without trust. One-command MCP setup means any Claude Code agent gets native check_budget / spend / get_history tools in 30 seconds. Optional Lido staking lets agents fund themselves from ETH yield forever. Deployed on Ethereum Mainnet and Base.

Build Timeline

Mar 18, 2026Mar 20, 2026
2d 9hbuild time
66commits
1contributor

Team

OplyTrade

admin