Compare › Traceseal

RunVouch vs Traceseal

Traceseal (Show HN, August 2026) signs a receipt for every agent invocation: what code ran, who published it, input and output hashes, sandbox profile, all verifiable offline with one command. RunVouch proves a scheduled run happened and was done, and pages you when it was not. Both are proof; they answer different questions.

TracesealRunVouch
What is provenwhich signed skill ran, on which inputs, in which sandbox (per invocation)that the scheduled run started, ended, passed its evidence check and what it cost (per run, chained per day)
Anchored25519 signatures plus a transparency logSHA-256 chain per day, anchored in Bitcoin via OpenTimestamps
Verify without trusting the operatoryes, pip install traceseal-verifyyes, the chain and every day file are public, verify with the free ots client
Missed-run / dead man's switchnoyes
Alert when the run is late, fails, loops or overspendsnoyes: Telegram, Slack, email, PagerDuty, webhook
Hard cost cap + pausenoyes
Requires a sandbox around the agentyes, bwrap kernel namespacesno, wrap the command or two HTTP calls
Regulatory angleEU AI Act Article 50 receiptsaudit trail of unattended runs; no compliance claims
Pricingnot published on the site (September 2026); open source verifierfree 3 agents; $9 / $29

When to use which

If you have to prove to a third party which code an agent executed and on which inputs, Traceseal is built for exactly that and RunVouch is not. If you have to know at 07:00 that last night's agent ran, did the work and stayed under budget, and want a proof of that record you can hand to anyone, that is RunVouch. Running both is coherent: Traceseal seals the invocation, RunVouch watches the schedule.

Get a free key