Give an AI agent a wallet with spending limits and approval controls
Stage
MVP
MVP
Founded
Not given
Not given
Based in
US
IN
Pricing model
Contact for pricing
Free
Pricing
Per-execution pricing: one fee per execution that returns proof, charged only when proof comes back. Failed or cancelled runs cost nothing. Planning and approvals are free.
Not given
Key features
Boundary approval system for controlled execution
Checkpoint-based resumable execution
Verifiable proof of completion
Composable proof for multi-agent workflows
Per-execution pricing model
Integration with multiple agent frameworks
Trusted address list with immediate payment execution
Telegram-based approval for untrusted recipients
Hourly and daily spending limits
Automatic freeze on suspicious activity
SDKs for TypeScript, Python, and HTTP
Support for multiple blockchains
Emergency freeze and backup address recovery
x402 Payment Required protocol support
What makes it different
Pay only for verified results, not for attempts or planning
Human-approved boundaries ensure agent actions stay within limits
Interruptible checkpoints allow pausing and resuming executions
Proof is built into results for auditability and composability
Non-custodial design: you hold your keys and vault; WalletBrake can only approve, refuse or freeze payments
On-chain enforcement: vault contract enforces all limits directly on blockchain
Protection against social engineering with 24-hour delay for adding trusted addresses
AI intent checking prevents off-topic or misaligned payments within approved tasks
Protection against address poisoning and new contract risks