Proof of what an AI agent was allowed to do, and what it then did
Verified, guarded Hyperliquid route for AI agents with hashed receipts and keyless access
Stage
Startup
Startup
Founded
2026
2026
Based in
Not given
Not given
Pricing model
Open source
Freemium
Pricing
Not given
Free: SDK, MCP server, simulator, receipts, paper trading. Live orders: 0.01% on volume up to $5M/month, 0.005% above $5M/month (founding testers pay 0% on first $1M/month until 28 Feb 2027). Examples: $500k volume $50/month (standard) or $0 (founding tester); $5M volume $500/month (standard) or $40
Key features
Signed permissions with passkey authentication
Receipts for each agent action with signatures
Free checker tool to verify compliance
Quantum-safe signatures (Ed25519 and ML-DSA-87)
Permission narrowing for helper agents
Permission cancellation with signed acknowledgement
JavaScript and Python libraries
LangChain and Pydantic AI middleware
Hashed receipts anyone can re-verify
Full cost pricing before trade execution
Keyless access with no custody
Owner-set limits on leverage and order size
Paper trading and simulation
Real order-book depth pricing
MCP server protocol support
TypeScript and Python SDKs
What makes it different
Only open-source project combining machine-checkable limits, permission narrowing for helpers, and signed permission cancellation
Built entirely from published standards with no hand-made components
Free and no dependencies, sends nothing anywhere or holds money
Distinguishes between record integrity and whether agent stayed within permission
All published versions stay available for backward compatibility
Receipts are hashed and anyone can re-verify them independently
Costs priced before the trade based on real order-book depth
No keys, accounts or custody required for research and simulation
Owner-set limits that agents cannot raise
Free and MIT-licensed with competitive builder fees
Provared
PerpBrain