Warn01
Agents take real actions
Your AI agents approve expenses, send emails, update records, and trigger payments. These are not suggestions. They are real actions with real consequences.
AI agent audit trail
Your agents send emails, trigger payments, and modify data. AgentReceipt captures every action as a tamper-proof receipt. When something goes wrong, you have proof.
Today, most AI agent deployments look like this. Actions happen, and nobody can prove what actually ran.
Your AI agents approve expenses, send emails, update records, and trigger payments. These are not suggestions. They are real actions with real consequences.
When something goes wrong, there is no agent action log a non-technical person can read. No receipt you can hand to your compliance team or your customer.
Wrong payment to the wrong vendor. An email sent to the wrong customer. Your audit asks what your AI did last Tuesday. A log of what happened is not enough. You need to know what the agent saw and what rules it was following when it made the call.
Install the SDK and wrap your AI client. No config files, no extra infrastructure. Three lines and you have full agent observability, capturing every action automatically.
import { createClient } from "@agentreceipt/sdk";
const ar = createClient({ apiKey: "ar_..." });
const openai = ar.wrapOpenAI(new OpenAI(), { sessionName: "Process invoice #441" });Works with OpenAI, Anthropic, Gemini, Mistral, and the Vercel AI SDK.
Every LLM call, tool call, and decision is captured automatically as an LLM audit log. Your agent code does not change. If the SDK cannot reach our servers, it fails silently. Your agent keeps running.
Open the dashboard and see a human-readable timeline of everything your agent did. Each receipt shows the full decision context: the rules, permissions, and state your agent was operating under when it acted. Every event is hash-chained for tamper-proof verification. Share any receipt with a one-click link.
Process invoice #441
4 events · 9.2s · exit 0
Every event is hash-chained to the one before it. Receipts are append-only. Nobody can edit or delete events after the fact. Not even you.
Article 19 requires high-risk AI systems to retain logs for at least six months. AgentReceipt stores receipts with configurable retention and an immutable hash chain. Enforcement starts August 2026.
SOC 2 audits ask for activity logs. HIPAA requires six-year retention for healthcare data. SOX and SEC rules require financial agents to prove they followed execution rules. One audit trail covers all of them.
Record approval steps alongside agent actions. When a person signs off before the agent proceeds, that decision is part of the receipt too.
Tag events that contain sensitive data. Mark health records, financial data, or personal information so your compliance team knows exactly which events to scrutinise.
Pro and Business receipts are anchored to the Sigstore Rekor transparency log after every session. This is a public, permanent record that proves the receipt existed at a specific time and has not been changed. Anyone can verify it independently.
Upgrade when you need more sessions or longer retention.
For developers testing and building.
$0forever
For small teams shipping agents in production.
$49/month
For teams running agents across multiple workflows.
$199/month
For regulated industries and large-scale deployments.
Everything we get asked before the first integration.
Start keeping a record of them. Free plan, no credit card, five minutes to set up.