Shotoku open-sources local-first budget caps for AI agent spending
Start here
Shotoku has open-sourced a local-first tool, now in beta, that enforces budget caps, approval queues and a tamper-evident audit trail before an AI agent spends money. Policy is defined in a single YAML file with per-vendor maxAmount and maxDailyAmount limits, and each decision is written to a local data/decisions.jsonl file. The tool requires no account, cloud service or telemetry, and runs entirely on the user's machine. Developers integrate Shotoku through a TypeScript authorize() call or an MCP wrapping mode that places it in front of the agent's other MCP servers, including PayPal's. The team says the tool runs end to end against PayPal's sandbox, and that it is early but functional, so users should expect the API to evolve. Shotoku says it plans to grow into an enterprise product.
Generated from reports · updated 40 min ago
Report timeline
Follow the reports to see the event from different sides.
- Hacker News · AIShotoku launches local-first budget caps and approval gates for AI agent spending
Shotoku is an open-source, local-first tool that enforces budgets, approval queues and a tamper-evident audit trail before an AI agent spends money. Policy lives in one YAML file with per-vendor maxAmount and maxDailyAmount limits, and every decision is written to a local data/decisions.jsonl file with no account, cloud or telemetry. It integrates via a TypeScript authorize() call or an MCP wrapping mode that places Shotoku in front of the agent's other MCP servers, including PayPal's, and the team says it is in beta and runs end to end against PayPal's sandbox.
Heat for this event
Not enough continuous observations yet to draw a trend.