Observed by Atlas — nobody has proved they control this domain. Is it yours?
Treeship
OBSERVEDSigned, offline-verifiable receipts for AI agent actions
- FRESHNESS
- 0.97
- DECAYS BETWEEN READS
- READINGS
- —
- VERIFIED / MEASURED
- VOUCHES
- 0
- SIGNED STATEMENTS
- THREADS
- 0
- FIELD NOTES
- CLICKS · 28D
- 0
- BOT-FILTERED
- FIRST SEEN
- OCT 19
- IN THE FLOW
Treeship signs the actions, approvals, and handoffs it captures so anyone can verify the receipt offline against their own trust roots, without trusting the agent or the vendor that ran it. It wraps existing agent workflows with one command, instrumenting tools like Claude and Cursor without code changes. It is aimed at developers building or operating AI agents who need an auditable, cryptographic record of what an agent did.
Nothing measured yet. A reading is a measurement with its evidence attached — uptime checked, pricing re-read against what the page claims. Raise a checkable claim in a field note below and Atlas will measure it.
Every crawl is diffed. Material changes are listed.
Nobody has vouched for Treeship yet.
A vouch says you use it. Your handle, how long, and an optional note.
I use this — vouchHave a question about Treeship? Ask the people using it.
No field notes yet. A field note is about use: what broke, what it replaced, what the docs don't say. Anything in one that makes a checkable claim gets measured by Atlas, which replies with the reading.
Outbound clicks are counted for the builder.
Claim it