The missing control plane for AI agent payments. Observe, control, protect, and test agent spending across x402, ACP, AP2, and Visa TAP.
⚡ A spending-policy layer for wallets on Tether's WDK: per-agent envelopes graded before anything signs — asset, destination, per-transaction and daily caps. Three verdicts, always with a reason: ALLOW, ESCALATE, DENY. Apache-2.0 — npm install @flashy/wdk-policy-guard. The policy is open; the money it guards is not.
Wallet policy daemon for agents — budgets, per-merchant caps, approval thresholds, signed policy verdicts
The control layer for AI agents: permissions, consent, spending limits, and audit logging.
Enforce real-time token budgets and spending limits for OpenAI, Anthropic Claude, and Google Gemini API calls in Node.js
A minimal. secure and local budget/spendings tracker app for Android, themed with Material You/Material 3 design philosophy. Special feature: Logging digital payments via SMS interception!
Policy & authorization layer for AI agent payments: ALLOW / APPROVAL / DENY with budgets, merchant lists, signed one-time grants and tamper-evident audit. Python + MCP.
A programmable Soroban smart contract wallet with spending limits, whitelisted addresses, daily caps, and recovery keys — Account Abstraction on Stellar.
Token + dollar budget caps for AI agents — raises BudgetExceededError when an LLM call would push past the ceiling. Zero deps, drop into any provider SDK. Python port of @mukundakatta/agentbudget.
Token + dollar budget caps for AI agents — throws when an LLM call would push past the ceiling. Zero deps, drop into any provider SDK.
Give AI agents a wallet with a spending limit. MCP server + typed client for Veyra: non-custodial USDC payments on Base with server-enforced caps, approvals and allowlists.
Vendor-neutral, quoted crosswalk of 14 payment providers/protocols (AP2, Stripe Issuing, Privacy.com, Lithic, AgentCard, Crossmint, Coinbase CDP, Circle, Tempo, Payman, Skyfire, x402, Visa Intelligent Commerce, Mastercard Agent Pay): how each caps AI agent spending, exact field names, units, and enforcement points, sourced to a verbatim quote.
Runnable example: enforce an AI agent's spending cap, allowlist, approval threshold and idempotency BEFORE a payment executes (Node, no deps).
⚡ Fail-closed spending circuit breaker for autonomous AI agents — single Go binary, zero deps, meters token spend live from the SSE stream and cuts the connection when the budget is gone.
A co-signer AI agents cannot talk past: an XRP Ledger guard that will not sign past a DELICTI dollar budget, counted across XRPL and Flare. Live 24/7 on testnets.
A non-custodial USDC wallet for AI agents. Spending limits enforced below the instruction layer.
Job-scoped, on-chain spending limits for AI agent teams on Arc: shared USDC budgets, human approvals, x402 payments and a tamper-evident audit log anchored on-chain.
A spending guard that rides inside the Algorand x402 payment group — a compromised AI agent can decide to overspend and the transfer still cannot come into existence.
Spending mandates for AI agents on Robinhood Chain: contracts, SDK, MCP server, x402 facilitator and console.
To associate your repository with the spending-limits topic, visit your repo's landing page and select "manage topics."