Vibe Coding Discoveraskgrokwallet
View on GitHubRules-and-receipts layer for AI agents that spend money: plain-English policy → human approval → signed receipts anyone can verify.
Rules-and-receipts layer for AI agents that spend money: plain-English policy compiles to allow/ask/deny, risky actions hit a human approval inbox, and every outcome produces an Ed25519-signed receipt anchored on Base. Contracts are unaudited; mainnet settlement not yet demonstrated.
Use Cases
Enforce allow/ask/deny spending policy on an AI agent's walletRoute over-threshold agent payments to a human approval inboxEmit Ed25519-signed receipts verifying where agent money wentAnchor a hash-chained receipt log on Base/Sepolia for third-party verificationCompile plain-English rules like 'payments over $50 ask me' into onchain policyConstrain agent payments at the signing layer with per-call value limitsGive auditors a dependency-free verifier for autonomous agent transactions
Built With
- Language
- JavaScript
- Frameworks
- Hardhat · Node.js · MCP · x402 · Cursor plugin · Grok plugin
Tags
agent-governance · agentic-commerce · ai-agents · human-in-the-loop · policy-engine · verifiable-receipts · wallet · ed25519 · x402 · erc-8196 · erc-8126 · mcp · approval-workflow · audit-log · base · smart-contracts