Questions about kervo
What is kervo?
kervo is a developer tool that compiles a software repository into a trust-labeled context artifact for AI coding agents. It works by deterministically scanning a workspace to extract facts such as commands, changes, and modules, and then records agent-generated proposals about goals, decisions, and risks into a ledger. Humans review and verify, retire, or label these proposals, and the resulting verified memory is shared with any agent in future sessions.
How do I get started with kervo?
The tool is distributed as a single binary with no dependencies, is licensed under Apache-2.0, and can be installed via Homebrew or npm. The website says users can get started with brew install kervo-os/tap/kervo or npm install -g @kervo-os/kervo.
How does the deterministic scan work?
The process begins with a deterministic scan where kervo compile reads the repository — commands, changes, tasks, modules — into a fact skeleton. Same workspace, same bytes, golden-tested in CI. No LLM in this path, ever.
How are agent proposals handled?
Sessions capture durable facts with evidence — how to run things, decisions made in conversation. Each enters the ledger as a trust-labeled proposal with provenance, never as anonymous truth.
How does the human judgment process work?
Humans verify or retire in kervo review or the dash — one keystroke, reason recorded. Verified memory returns to every future session, any agent, any teammate, for zero tool calls.
What is the trust lifecycle of a proposal?
Proposals get verified, go stale, and get retired with their reason shown — never silently dropped. The lifecycle follows generated→observed→verified→stale→deprecated.
How does kervo check handle code drift?
A decision whose anchored code keeps moving after the judgment comes up for re-affirmation, and a PR that rewrites trust state ships that judgment as a review object — it cannot silently retire the decision that would have flagged it.
How does kervo integrate with CI?
Decisions gate CI. Give a verified decision a path anchor and any diff that touches what it governs gets warned — inline in GitHub Actions, zero bot code. A decision advisory by default; -strict blocks.
What does the kervo dash feature do?
One command serves a local dashboard over every kervo workspace on your machine — pending proposals, trust states, last activity — with keyboard-first triage that writes each judgment back to that repo’s own ledger. No daemon, no account, no server: it dies with the comma.
What does the CLAUDE.md output look like?
The website mentions a CLAUDE.md — compiled by kervo file that lists known decisions with verification status and evidence, such as Payments stay on the legacy gateway until Q3 with a standup decision from 2026-06-30.
Who is kervo for?
The tool is designed for developers and teams using AI coding agents, helping them stop re-explaining their project to AI by making the team’s signed memory the agent’s starting point.
What is the official website of kervo?
The official website of kervo is kervo.dev.
Does kervo have reviews on Trustburn?
kervo has no reviews on Trustburn yet. Anyone who has used it can write the first review on its Trustburn page.
AI-generated from reviews on this page. Verify anything important with the company directly.
News
No news yet. This is where the business shares its own updates and press.
Photos
Widgets
Get the widget for your site →About kervo
kervo is a developer tool that compiles a software repository into a trust-labeled context artifact for AI coding agents. It works by deterministically scanning a workspace to extract facts such as commands, changes, and modules, and then records agent-generated proposals about goals, decisions, and risks into a ledger. Humans review and verify, retire, or label these proposals, and the resulting verified memory is shared with any agent in future sessions. The tool is distributed as a single binary with no dependencies, is licensed under Apache-2.0, and can be installed via Homebrew or npm.
- Website
- kervo.dev