Release notes
What each release ships, who it is for, and what you can do
with it. Full engineering history lives in the
changelog;
this page is written for the people using the tool.
v0.9.0 current CLI release
- AgentMeasure is now Verovo. Same measure, new name and logo:
pip install verovo, command verovo, SDK @verovo/mcp 0.3.0. - Environment variables move to
VEROVO_*, the local data directory to ~/.verovo/, and schema namespaces to verovo.lab/* and verovo.commercial/*. Scripts pinned to the old names should stay on 0.8.0. - Recorded evidence stays valid: external conformance vectors and run logs are unchanged, and
agentmeasure.lab/* remains a permanent legacy alias in the schemas. - New wordmark and owl mark, favicon, Open Graph card and caller-identity diagram; usage rules in
docs/brand.md.
python -m pip install "git+https://github.com/roy-tong/verovo@v0.9.0#subdirectory=healthcheck"
verovo demo
PyPI project verovo is pending its first publish, so pip install verovo fails until then. 511 tests. SDK 0.3.0. A rename is not adoption, a customer, or validation of the commercial thesis.
v0.8.0
- Compare Claude response snapshots across explicit JSONL inputs: repeated identities, conflicting usage and missing fields stay visible; no session or invoice total is inferred.
- Run
verovo recount --sample with a bundled synthetic export. Report headers distinguish public-price estimates, unresolved rows and confirmed refunds. - Separate local diagnosis, metering QA and buyer-review entry points. $10/$20 services exclude invoice verification.
- Optional hosted monthly reviews require a private repository, fresh period and reviewed input hash. GitHub hosting uploads data; local CLI remains available.
python -m pip install --upgrade verovo
verovo recount --sample
511 tests. Payment checkout and buyer demand remain under validation. SDK stays 0.2.0.
v0.7.2
- Identify JSONL input format before choosing a check with
verovo inspect-input sample.jsonl. - Canonical provider observations receive the correct validator and onboarding path instead of unrelated FMT-002 errors.
- Mixed, unknown and malformed inputs remain explicit. Format recognition is not a schema or conformance pass.
487 unit tests. No automatic mapping or new token/cache billing guarantees. SDK remains 0.2.0.
v0.7.1
- Fixes the installed conformance command: the wheel now includes its required analysis module.
- Sample generation writes to your current working directory; missing fixture input explains the next step.
- Installed-wheel smoke tests now run sample generation and conformance, not only Healthcheck.
- Clearer local-export wording, first-run help, sample reports and email fallback templates.
python -m pip install --upgrade verovo
verovo conformance --new-vector my-sample --out ./vectors
Upgrade from 0.7.0 if you use conformance. SDK remains 0.2.0. Payment checkout remains pending; this release does not claim a completed purchase flow.
v0.7.0
- Linkable metering claims index with evidence and corrections.
- Standalone share-summary validation and Windows console compatibility.
- $10 Healthcheck and $20 Metering QA email applications; scope and terms on the service page.
- CLI 0.7.0 on PyPI; independently versioned Provider SDK 0.2.0 on npm.
pip install verovo
verovo demo
npm install @verovo/mcp
477 Healthcheck unit tests passed on 2026-10-14. Test results and public audit findings do not establish customer value or paid adoption.
v0.6.0
Who it is for
CX & support operationsreviewing per-resolution AI support bills (Intercom Fin, Zendesk AI Agents…) — before paying, disputing or renewing
Finance & procurementwho need the evidence behind a number, one finding at a time, in a form they can hand to the vendor
Brands running agent channelsmeasuring agent-driven orders, margin and guardrails from the merchant side
Tool builders & maintainersshipping conformance vectors, fixtures and corrections into the open standard
What you can do now
- Re-check any single finding.
verovo drilldown replays one conversation end to end: the row exactly as exported, every vendor-rule step in plain language, the verdict, and the command to reproduce it. The explanation walks the same branches as the engine — a test pins them together, so they cannot drift.
- Track what the review was worth, in three books. Recovered cash (
recovery), hours saved (delivery) and — new in this release — decisions made differently (decisions): payments approved or held, discounts requested, renewals signed, each linked to the finding it rests on. Three kinds of value, three separate records, never blended.
- Send someone a rule, not a PDF. Every vendor now has a public rule card — price, billing trigger, reopen handling, silence behaviour, closure timers, each fact with its source and the registry version it was read from. Linkable in an email or a ticket.
- Wear your evidence stage. VSS-1 badges state one thing only: how far a verification artifact has traveled — self-attested, recomputable, independently reproduced, counterparty accepted. No composite score, no A–F grade, by explicit design.
- Install from anywhere. PyPI, npm and GitHub all serve the current release, and CI now smoke-tests the packaged wheel in a fresh environment on every push — “tests pass but the install crashes” is the bug this makes impossible to ship.
- Three new external conformance vectors, including the first availability-certification vector, contributed via pull request — the external route is growing from fixtures toward formal vectors.
# Python 3.9+, zero dependencies, runs offline
pip install verovo
verovo demo
verovo drilldown --export your-export.csv --vendor intercom --conversation C-123
# no install at all: drop an export into the browser recount — website link above
Everything runs locally. No message text, customer content or
credentials are read; missing evidence is UNPROVABLE, never guessed; paying
for a first look does not change what the evidence says.
v0.5.0
The buyer-side verification system,
complete: the full review pipeline (prepare → recount
--contract → dispute → recovery, plus
crosscheck for your billing ledger, crm-join for
your business records, verify for the one-artifact ledger), the
agent-commerce measurement family (receipts with evidence grades, P&L
trees, contribution margin, channel audits, guardrails, anonymous
benchmarks), and the offline console that walks both journeys. 248 → 450
tests across the release.
Verovo