Agent Receipts

Cryptographically signed audit trails for AI agent actions

---

What is this?

Agent Receipts is an open protocol and set of SDKs for producing cryptographically signed, tamper-evident records of AI agent actions. Every action an agent takes -- API calls, tool use, data access -- gets a verifiable receipt that can be audited later.

Quick start

Go

go get github.com/agent-receipts/ar/sdk/go

import receipt "github.com/agent-receipts/ar/sdk/go/receipt"

r, _ := receipt.New(receipt.WithAction("tool_call", payload))
signed, _ := r.Sign(privateKey)

TypeScript

npm install @agent-receipts/sdk-ts

import { Receipt } from "@agent-receipts/sdk-ts";

const receipt = await Receipt.create({ action: "tool_call", payload });
const signed = await receipt.sign(privateKey);

Python

pip install agent-receipts

from agent_receipts import Receipt

receipt = Receipt.create(action="tool_call", payload=payload)
signed = receipt.sign(private_key)

Project layout

Directory	Description
spec/	Protocol specification, JSON schemas, governance
sdk/go/	Go SDK
sdk/ts/	TypeScript SDK
sdk/py/	Python SDK
mcp-proxy/	MCP proxy with receipt signing, policy engine, intent tracking
cross-sdk-tests/	Cross-language verification tests

Integrations

Project	Description
openclaw	Agent Receipts plugin for OpenClaw

Contributing

See CONTRIBUTING.md for development setup and PR guidelines.

Security

See SECURITY.md to report vulnerabilities.

License

Apache License 2.0 -- see LICENSE. The protocol specification in spec/ is licensed under MIT.