# Publicly verifiable receipts for AI agent actions, anchored to Bitcoin > Source: > Published: 2026-07-23 04:10:35+00:00 ## Self-reported logs are not evidence An autonomous agent that sends messages, changes systems, or moves value produces a log — a text file its operator controls. A log that can be edited after the fact is indistinguishable from one written at the time. When a question arrives — a client disputing what was delivered, a counterparty disputing what was sent, your own postmortem of an agent gone sideways — the log's value depends on being able to show *this is what the record said then, and it has not changed since*. A file on the operator's disk cannot show that. ## What anchoring adds Orphograph gives each consequential action record a Bitcoin-anchored receipt: the record is hashed on your machine, the fingerprint is anchored to the Bitcoin blockchain, and you get a dated receipt plus a hosted [certificate page](/certificate/XwTULwlh76PcCst9) anyone you authorize can check in their own browser. Three properties do the work: **Dated.** The record provably existed by the time of a specific Bitcoin block. A receipt anchored seconds after the action cannot have been written after the dispute started.**Tamper-evident.** Change one byte of the record — a recipient, an amount, a timestamp — and it no longer matches the receipt.**Verifiable without trusting the operator.** The proof is an open format checked against the public chain;[the verifier is open source](/verify/). The person relying on the record needs no account and no relationship with the person who made it. ## If you are the one accepting agent work The receipt is built for your side of the table. Before you rely on a delivered artifact or a claimed action, ask for its receipt and [verify it yourself](/accept) — drop the file or record you were given onto the acceptance page and check it against the certificate. A "yes" means the bytes in front of you are the bytes that existed at the anchored time. Operators who anchor as they work can answer any dispute with a link; operators who cannot produce receipts are asking you to take their logs on faith. ## What this is not Honesty is the product, so the scope is narrow and stated plainly. A receipt is **not** proof that an action was correct, authorized, safe, or legal, and anchoring is **not** a compliance regime or an agent-safety mechanism. It makes the record of what happened *tamper-evident and independently datable* — which is what turns a log into evidence. What that evidence establishes in any particular dispute is a question for that forum. ## Run it inside the agent A dependency-free CLI plus a drop-in skill let the agent anchor its own trail as it works — one-line action records, artifacts it produces, and a daily manifest of its memory files: ``` # Anchor a one-line action record the moment it happens echo "sent invoice #42 to client-7" | python3 orpho_agent_anchor.py anchor-text --label "billing" # Anchor an artifact the agent produced python3 orpho_agent_anchor.py anchor-file ./deliverable.zip --label "handoff" # Nightly: anchor a manifest of the agent's memory files python3 orpho_agent_anchor.py anchor-memory ./workspace --label "memory" ``` MCP-capable agents can anchor through the [MCP server](/mcp) instead — proof of existence becomes part of the agent's output, not an afterthought. Setup for both lives on the [integrations](/integrations) page. ## Give your agents a paper trail today The receipt is dated from the moment you anchor — an audit trail started before the first dispute is worth more than one reconstructed after it. ## FAQ ### Does a receipt prove my agent's action was correct or authorized? No. A receipt proves one thing: the action record existed, in exactly this form, by the time of a specific Bitcoin block, and has not been altered since. Whether the action itself was correct, authorized, or wise is a question the record helps you argue — the receipt makes the record trustworthy, not the action. ### Does the content of the agent's actions leave our environment? No. The action record is hashed locally with SHA-256; only the fingerprint is sent to be anchored. The record itself — what the agent did, to whom, with which parameters — stays on your machine. ### I'm hiring agent-driven work from someone else. How does this help me? Ask the operator for receipts. Each one is a public certificate page you can open in your own browser and verify against the Bitcoin blockchain — no Orphograph account and no trust in the operator required. If the log they show you later doesn't match the receipt, the log changed. ### What happens to my receipts if Orphograph disappears? The receipt is an open format: a SHA-256 digest plus OpenTimestamps proofs committed to the Bitcoin blockchain. Verification needs only the record, the `.ots` files, and the public chain — none of which depend on Orphograph existing. An MIT-licensed verifier is published for exactly this reason. Setup for the CLI, the drop-in skill, and the MCP server lives on the integrations page.