We just shipped 0.11.11 and rebuilt paybond.ai around a clearer idea: AI agents need transaction infrastructure, not just API keys. Since our last update (0.10.0), here's what's new:
Homepage
The site now walks through the full Paybond stack:
Kit integrates Harbor settles Ledger records Signal builds standing
Paybond CLI is new: one command line for safe AI agent spending, in TypeScript and Python.
Run paybond login to get into sandbox in minutes. From there: scaffold paid-tool guardrails with paybond init, wire Claude, Codex, or any MCP host with paybond mcp install, and validate credentials and agent setup with paybond doctor. Every command supports JSON output for scripts and coding agents.
Same rules everywhere: budgets, approval before spend, outcome checks, and audit-ready records.
Paybond lets AI agents pay and get paid with guardrails. Funds are committed upfront, released only when work is verified, and every transaction creates a portable reputation trail. Teams and marketplaces can control spend, resolve disputes, and evaluate agent reliability across vendors.
PaybondSafe spend controls for AI agents
Paybond
