Everyday completion
The agent registers each new request with amabie_task, preserving explicit criteria. Registration adds duties; it has no proof authority. The completion hook runs the sealed checks and reports remaining proof gaps.
AMABIE / FIELD GUIDE
Start with
your own checks.
A practical guide to the current product. Built around executable evidence, with the version and trust boundaries stated explicitly.
Amabie 2.0 is not yet available as a public package.
The product release is still in validation. The latest tagged package and the current source review may still use the Canary name. This page will add a verified install command when the Amabie package is published.
Review the Amabie 2.0 candidate · View tagged releasesInspect first. Then connect.
A verified public Amabie 2.0 install package is not available yet. Do not run an npm registry install command for Amabie until the release is published. The candidate’s source review and the existing tagged releases are linked above; installation instructions will be updated against the actual release artifact.
The product requires Node.js 22 or newer, npm and Git. Once the package is available, setup begins with a read-only preflight, amabie setup --check, followed by a reviewed setup plan. The integration pages explain the trust steps and limits before you connect an agent.
Three distinct operations.
Isolated work
amabie work opens a candidate for expert workflows. Objective requirements need sealed bindings. amabie finish verifies and promotes only when the required proof holds. Human acceptance does not replace objective proof.
Read state or run checks
amabie result --json and status read known state. doctor runs checks now. A focused doctor --check reports PARTIAL; it does not certify the complete task.
The attested baseline/candidate pipeline is a separate, stronger verification surface. It classifies repeated execution facts and retains an Evidence Bundle. A bound requirement is coverage inside this model, not a guarantee of semantic correctness.
The human trust step is part of the contract.
Claude Code: setup installs completion and pre-tool hooks. Unregistered requests are blocked on the normal hooked tool path; unbound objective criteria remain NOT PROVEN. Project-scope MCP tools require the agent’s separate one-time approval.
OpenAI Codex CLI: setup writes the Stop hook, but Codex will not run it until you review and trust it through /hooks. A written hook alone gates nothing.
Other CLI agents: the integration is advisory. A machine-readable response does not imply the ability to block completion.
Native check discovery exists for Node, Python, Rust and Go. Other command-driven projects can declare an argv-based project contract. Execution evidence and runner observation are different claim levels; unknown runner internals are not silently treated as observed.
LOCAL is the current boundary.
Authority records are signed and stored outside the project tree. A process with the same user identity can still replace the complete store or reseal a different plan and baseline. The everyday workflow gates completion; it does not put the agent’s native editor tools inside an OS sandbox.
HARDENED is unavailable in the reviewed build. Provider and broker code is implemented, but only a current measurement of the required independent authority boundary can activate that claim. There is no promise of universal fail-open prevention, exhaustive semantic verification or current token savings.
Historical compatibility remains intentional: the canary executable and legacy data paths are retained where existing projects, hooks and signed evidence depend on them.
Your code never enters this demo.
The illustrative demo runs in the browser. It executes no project code, sends no code or evidence to a backend, and uses no account, form, analytics tracker or application cookie. Copying a snapshot uses the browser clipboard only after you click the copy button.
The site host processes technical request data to deliver and secure the pages. See the privacy notice for details and the legal notice for the operator.
Providers and extension points.
Implemented interface: an AI provider can attach a summary without changing classification. The only enabled provider shipped in the reviewed source is a no-op; this is not a bundled live AI explanation service.
Planned adapters: the architecture describes optional future security, performance and code-context adapters. Those extension plans are not listed here as working product integrations.