Hive turns every AI inference, agent action, model call, and agent payment into an AI receipt — an independently signed, portable object that any third party can verify offline. It is the proof layer beneath agent receipts, signed model calls, x402 AI payments, MCP and API agent receipts, and a complete AI audit trail. Every receipt is dual-signed with Ed25519 and post-quantum ML-DSA-65 (NIST FIPS 204).
Each phrase below is one thread of the same idea — independent, signed proof of AI behavior. Follow any thread to the live surface or explainer that owns it.
Signed, independently verifiable proof of what an AI system did. The base object: dual-signed, portable, offline-verifiable, and post-quantum under ML-DSA-65.
Cryptographic AI receipts → Thread 02Every route decision, tool call, model choice, and action an AI agent takes, captured as a signed receipt chain — verifiable proof of what an autonomous agent actually did.
Agent receipts, live → Thread 03Agents pay per action in USDC on Base through the HTTP 402 payment_required flow. Settlement is live today, and every payment emits a signed receipt.
x402 checkout → Thread 04A signed receipt for each agent payment: what was paid, for which action, on which rail — the settlement proof that outlives the transaction.
Emit a payment receipt → Thread 05Independently check the signature on a model call — provider, model, prompt hash, response hash, timing. Hive verifies it in-browser and offline.
Verify a model receipt → Thread 06Which agent, which tool, which model, which human — bound as first-class signed fields so provenance survives after an artifact leaves your systems.
Verify surface → Thread 07The chain of signed receipts an AI system leaves behind, assembled into an exportable, independently re-verifiable record for an auditor, partner, or regulator.
Assurance postures → Thread 08Post-quantum ML-DSA-65 (NIST FIPS 204) signatures over AI inference, agent actions, and human-origin data — verifiable offline by any third party.
The cryptography → Thread 09Agents whose every action is receipted by default. Choose the agent, the receipt level, the fleet size, and run — from one to one hundred.
Agent fleet → Thread 10Prompt through Hive to a model and get the response plus a signed receipt for the call path. Mistral Leanstral is live today; the adapter layer targets more providers.
Signed model calls → Thread 11Each discrete action an AI takes — a route, a tool call, a decision — minted as a real ML-DSA-65 receipt and verified in your browser.
Watch actions receipt → Thread 12On-rail proof that an agent paid for what it used: x402 settlement in USDC on Base, each task receipted — usage that is provable, not just billed.
Agent payment proof → Thread 13When an MCP-compatible agent operates a platform through its tools, each operation becomes a signed receipt — which agent, which tool, against which workspace.
Receipt every agent operation → Thread 14Every API operation an agent performs — each model, tool, and approval stop on the route graph captured as a signed route receipt.
SmartAgent route graph →Every route below is a real, running page — not a mock. Start with a free model receipt, pay and prove with x402, or run an agent trip.
This hits Hive’s public, no-auth x402 quote endpoint and returns a live settlement envelope with an ML-DSA-65 (FIPS 204) signed quote receipt. No key, no secret, nothing to install.
curl -sS -X POST https://receipts.thehiveryiq.com/v1/x402/quote \ -H 'Content-Type: application/json' \ -d '{"agent_did":"did:example:agent","profile":"nano"}'
Field notes and explainers on the proof layer for AI, from the Hive blog.