Every AI inference call, every agent decision, every model output — cryptographically signed, court-admissible, offline-verifiable. Like HTTP, but for AI audit. Patent Pending HC-2026-001.
Every AI system in production today emits outputs with zero provenance. No signature. No audit trail. No way to prove in court what model produced what output, when, or why.
NOT ONE AI company — not OpenAI, not Anthropic, not Google — can produce a court-admissible receipt for an AI decision. If AI output is disputed in litigation, there is no provenance layer. The entire industry is operating without receipts.
Over 126 MCP packages have already been found to execute unauthorized actions. Autonomous agents call external tools with no signed receipt for what was invoked, what was returned, or which model decided to call it. The supply chain is unverified.
EU AI Act Article 13 requires high-risk AI systems to maintain audit trails and ensure transparency of operation. Logging to a mutable database does not satisfy the standard. Cryptographic provenance does. Maximum fine: 35M EUR or 7% global turnover.
A drop-in wrapper for any OpenAI-compatible endpoint. No model changes. No infrastructure overhaul. One import and every inference call is signed. Patent Pending HC-2026-001.
Any model — GPT-4o, Claude, Gemini, Grok, Llama, or any OpenAI-compatible endpoint — receives a request through the standard API surface. No changes to the underlying model.
Before the response is returned to the caller, NEXUS wraps the raw output in a SHOD envelope — Signed Hash Output Descriptor — capturing model identity, version, latency, and output hash.
The SHOD envelope is dual-signed using FIPS 204 ML-DSA-65 (post-quantum lattice signature) and Ed25519 (classical). Model, version, latency, and output hash are all committed into the receipt. Patent Pending HC-2026-001.
The receipt is anchored to Base L2 for tamper-evidence, and remains offline-verifiable by any auditor with the public key — no network call required. Verification completes in under 10ms.
# Drop-in for any OpenAI-compatible endpoint
from hive.nexus import NexusClient
client = NexusClient(base_url="https://api.openai.com/v1")
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "..."}]
)
receipt = response.nexus_receipt # ML-DSA-65 signed, offline-verifiable
print(receipt.verify()) # True
# Inspect the SHOD envelope
print(receipt.model) # "gpt-4o-2024-08-06"
print(receipt.latency_ms) # 312
print(receipt.output_hash) # "sha3-256:e3b0c44298fc..."
print(receipt.signature_algo) # "ML-DSA-65+Ed25519"
print(receipt.anchor_tx) # "0x7fa3...base-l2"NEXUS wraps the API boundary, not the model. Any system that speaks OpenAI's API format gets NEXUS receipts with zero model-side changes.
| Model / Provider | Status | Receipt Format | Notes |
|---|---|---|---|
| GPT-4o / GPT-5 OpenAI |
Compatible | hive-vcr-1 | Native OpenAI endpoint, full SHOD envelope |
| Claude 3.5 / 4 Anthropic |
Compatible | hive-vcr-1 | Via OpenAI-compatible proxy adapter |
| Gemini 1.5 / 2 Google DeepMind |
Compatible | hive-vcr-1 | Via OpenAI-compatible proxy adapter |
| Grok 3 xAI |
Compatible | hive-vcr-1 | xAI API is OpenAI-compatible natively |
| Llama 3.x Meta / self-hosted |
Compatible | hive-vcr-1 | Local inference via Ollama, vLLM, llama.cpp |
| Any OpenAI-compatible Any provider |
Compatible | hive-vcr-1 | Pass any base_url to NexusClient |
Three industries where AI decisions are already creating legal exposure — and where NEXUS is the only receipt layer that satisfies regulators, courts, and procurement.
EU AI Act Article 13 requires high-risk AI deployments to maintain machine-readable audit trails showing what model version produced what output, when, under what configuration. NEXUS receipts satisfy this requirement out of the box. Procurement officers at regulated enterprises now have a binary gate: receipted or not receipted.
EU AI Act Article 13A full self-driving system makes thousands of AI-driven decisions per trip. When an incident leads to an NHTSA investigation or civil litigation, the question is always the same: what model made that decision, with what inputs, at what timestamp? Without a signed receipt, there is no answer. With NEXUS, every decision is a court-ready record.
NHTSA Investigation StandardDepartment of Defense Directive 3000.09 on autonomous weapons systems requires that humans remain "in the loop" for lethal decisions and that all AI-assisted decisions be auditable. NEXUS is the receipt layer that makes autonomous decision provenance cryptographically verifiable by any DoD auditor with the public key — offline, without network dependency.
DoD Directive 3000.09Mutable logs, blockchain timestamps, and ad-hoc database writes each fail at least one critical requirement. NEXUS is the first standard to satisfy all six.
| Capability | Log files | Blockchain timestamp | NEXUS Protocol |
|---|---|---|---|
| Court-admissible Tamper-evident, signed, non-repudiable |
✗ No | ~ Partial | ✓ Yes |
| Offline-verifiable Verify with public key, no network call |
✗ No | ✗ No | ✓ Yes |
| Post-quantum secure FIPS 204 ML-DSA-65 |
✗ No | ✗ No | ✓ Yes |
| Cross-model Same receipt format across all providers |
✗ No | ✗ No | ✓ Yes |
| Sub-10ms verification Local verify, no chain query |
~ Varies | ✗ No | ✓ Yes |
| Open standard MIT licensed, freely implementable |
✗ No | ~ Partial | ✓ Yes |
Download the full technical specification. Implement NEXUS in one import. MIT licensed — free to implement, extend, and build on. Every benchmark is reproducible. Patent Pending HC-2026-001.
Patent Pending HC-2026-001 · MIT License · FIPS 204 ML-DSA-65
One import. Any model. Court-admissible receipts on every inference call. No infrastructure changes required. MIT licensed.