Govern every AI action.
Before, during, and after.
One platform for policy enforcement, content scanning, LLM gateway, human approval, and cryptographic receipts.
4 policy modes
Rules, AI, consensus, content scan
NER + regex scanner
Names, SSNs, credentials, injection
LLM Gateway
Any provider, zero code change
Human approval
Signed decisions in the receipt chain
Ed25519 receipts
Every state signed, RFC 3161 timestamps
W3C DID
Verifiable agent identity
NER + regex scanner catches SSNs, names, credentials. Gateway blocks before any LLM sees it. Policy engine enforces rules, AI policies, consensus.
High-risk actions held for approval. Signed decision embedded in the receipt chain. No action runs without authorization.
Ed25519 receipt + RFC 3161 timestamp on every outcome. Denied, failed, approved — all signed. Verify with OpenSSL, no account.
Hosted or self-hosted · Works for AI agents, agentic and non-agentic, API calls, webhooks, batch jobs, RPA
Seven steps. One platform.
From agent registration to compliance evidence. Each step has a concrete example of what Aira does — not what it could do.
Who is acting?
Every agent gets a W3C DID — a verifiable identity that follows it across deployments. Key rotation built in. Receipts are tied to a real identity, not just an API key.
Agent identity
What are the rules?
Four policy modes, stackable per action type. Deterministic rules for speed. Plain-English AI policies for nuance. Multi-model consensus for high-stakes. Content scanning for sensitive data.
Four modes
action_type == "wire" AND amount > 50K
Block actions involving personal data
3 models vote — 2 REVIEW, 1 APPROVE
NER + 27 regex: SSN, names, credentials
How does it flow?
The gateway sits between your agents and any LLM provider — OpenAI, Anthropic, Google, Ollama, or any OpenAI-compatible endpoint. Two lines of config. Every call policy-checked, scanned, and receipted. Zero code change.
Gateway setup
# any OpenAI-compatible provider client = openai.OpenAI( **gateway_openai_kwargs(aira_api_key="aira_live_...") )
What's sensitive?
NER (Microsoft Presidio) catches person names, addresses, dates of birth, medical data. Regex catches SSNs, credit cards, API keys, IBANs. Runs on inputs before the LLM and on outputs after. In-process, <5ms.
Content scan result
Who decides?
High-risk actions are held for human review. Approvers get a secure single-use link. The approval decision is Ed25519-signed and embedded in the receipt chain. No action runs without explicit authorization.
Approval flow
What happened?
Every action — authorized, denied, or failed — gets an Ed25519 receipt with an RFC 3161 timestamp. The receipt commits the policy decision, scan results, approval chain, and outcome. Universal receipts mean zero audit gaps.
Ed25519 receipt
Show the regulator.
Compliance bundles map article-by-article to EU AI Act, DORA, ISO 42001, SR 11-7. Merkle-rooted, signed, sealed. Anyone can verify any receipt at the public endpoint with OpenSSL — no Aira account needed.
Compliance coverage
Gate. Sign. Prove.
Three steps around any action: scan and enforce policies before execution, sign the outcome after, prove it to anyone later. Two SDK calls, or route LLM traffic through the gateway with zero code change.
Gate
Before executionPolicy-check and scan before anything runs.
Content scanner (NER + 27 regex patterns) catches SSNs, names, addresses, API keys, prompt injection. Policy engine evaluates rules, AI policies, or multi-model consensus. Human approval holds high-risk actions. The gateway blocks sensitive data before it reaches any LLM.
# policy + scan before execution auth = aira.authorize( action_type="wire_transfer", details="Send 75K to vendor-x", agent_id="payments-agent", )
Sign
After executionSeal every outcome cryptographically.
After the action runs, mint an Ed25519 receipt with an RFC 3161 timestamp. The receipt commits the policy decision, scan results, approval chain, and outcome. Denied actions get a denial receipt — zero audit gaps. Output scanning catches sensitive data in LLM responses too.
# sign the outcome after execution receipt = aira.notarize( action_id=auth.action_id, outcome="completed", outcome_details="Wire ref: TXN-9482", )
Prove
VerifyCryptographic proof that nothing leaked.
Every action — authorized, denied, or failed — gets an Ed25519-signed receipt with an RFC 3161 timestamp. The receipt proves what was scanned, what was blocked, and what was allowed. Verify with OpenSSL alone — no Aira account needed.
# anyone can verify — no account needed $ curl api.airaproof.com/api/v1/ verify/action/<uuid> { "valid": true, "algorithm": "Ed25519", "signer": "did:web:airaproof.com" }
See what your agents are leaking.
Paste any text and see what our NER + regex content scanner catches. In production, this is one layer of seven — actions also pass through policy rules, AI evaluation, consensus voting, and human approval before touching any LLM. Try the full interactive demo to test all seven steps.
Click Scan to see what the content scanner finds.
Mint a receipt.
Right now.
An AI agent wants to wire €75,000 to a vendor. Watch Aira authorize the action, sign the outcome, and produce a receipt anyone can verify.
Seven chapters.
Read the ones you need.
Most layers work for any code path.
AImarks features that use the model or agent layer.
Policy engine
The rules, AI policies, consensus voting, and content scans that decide what an action can do — before it runs.
Rules
Deterministic. Instant. No LLM. Wire transfers over €50K require approval. Data deletion is blocked.
AI policiesAI
Plain English policy, evaluated per action by an LLM. Flexible enough for nuanced business logic.
ConsensusAI
Multiple models vote. Disagreement holds the action. No single model has the final word.
Content scan
PII, leaked credentials, prompt injection — caught on inputs and outputs. Flag, deny, or redact.
Any model.
Any agent.
Aira intercepts at the action layer — which LLM your agent runs on, which framework you wrap it in, is up to you.
Models
OpenAI
Google
Mistral
AWS BedrockAgent frameworks
LangChain
Vercel AIOpenAI AgentsGoogle ADKAWS Bedrock
CrewAI
MCPCloud or fully self-hosted.
Run Aira on your own Kubernetes cluster with your own signing keys. Nothing leaves your network. Same SDK, same verify URL scheme.
Compliance comes automatically.
The same audit trail that proves an action was authorized is what regulators ask for. Govern the agent, get the paperwork.
Article 12 record-keeping is the default, not a bolt-on.
Article 17–19 incident lifecycle + signed major-incident PDFs for ESA submission.
Model inventory, validation, and monitoring come with every receipt.
Hash-only by default. Raw details never stored unless opted in.
Compliance bundles map one-to-one to the required control evidence.
Answers,
before you ask.
If something here isn't right for your shape — DM us. We answer.
Yes. authorize() and notarize() are action-level primitives — they don't care if the caller is an AI agent, a webhook handler, an RPA bot, or a deterministic micro-service. The cryptographic receipt is the same. AI agents are our wedge because of EU AI Act and DORA urgency, but the API is general-purpose.
Yes. The entire stack runs on your own Kubernetes cluster — API, policy engine, signing keys, Postgres, everything. Nothing leaves your network. You get the same SDK, the same dashboard, and the same public verify URL scheme. Regulated industries and data-sovereignty use cases run self-hosted by default.
No. Rules and content scans run in-process via the SDK — your sensitive data never leaves your network for the deterministic checks. Only AI policies and consensus voting round-trip to Aira (the LLM has to live somewhere). Self-hosted deployments keep everything on your infrastructure, including the LLM calls.
The SDK supports offline mode — receipts queue locally and sync when the API is back. Your action doesn't block on Aira availability. The cryptographic signature is still valid offline because the keys are in your local SDK process.
Simple pricing.
Every feature on every plan.
You pay for volume, not features. One op is an authorize, a case run, a chat message, a compliance bundle, a settlement, or a drift check. Notarizing is free.
Agents in production.
Start free- +10,000 ops / month
- +Unlimited seats
- +Email support
When decisions have consequences.
Start free- +100,000 ops / month
- +Unlimited seats
- +Priority support
- +99.5% SLA
Regulated industries, self-hosted.
Contact sales- +Unlimited ops
- +Dedicated support
- +99.9% SLA
- +Self-hosted
- +SSO / SAML
Pay-as-you-go overage · Pro €0.05 / op · Business €0.03 / op (€0.015 per case) · Free hard-walls at 100 · Self-hosted has no cap
Your agents are running.
Start proving it.
One API call sits between your agents and production.
No credit card · Self-hostable · Open-source SDKs