Keyoku

Security

Keyoku is local-first by design: no cloud, no telemetry, no account. The security model has one trust boundary — your approval — and an audit trail around everything else.

Local-first state

All state lives in ~/.keyoku (override with KEYOKU_HOME). The directory is created with mode 0700 and files with mode 0600 — readable only by your user.

FileContents
~/.keyoku/activity.jsonlThe activity trace — one event per tool call, size-capped ~10k events
~/.keyoku/executions.jsonStep-by-step workflow execution state

What leaves your machine

There is no telemetry. The only network calls Keyoku makes on its own behalf are SLM refinement calls — and only if you configure GEMINI_API_KEY or ANTHROPIC_API_KEY. With no key set, nothing leaves the machine. (Connectors you register obviously talk to whatever you point them at.)

The trust boundary: approval

Approval is the trust boundary. An approved template executes shell commands with your user privileges — there is no sandbox between an approved bash step and your system. Review templates the way you review shell scripts before approving them, especially templates refined by a model or drafted by an agent.

Guardrails

GuardrailDetail
Approval gateNothing executes until you approve a template. Connector calls at the approve level queue for explicit sign-off.
Autonomy levelsPer-connector: observe (calls refused), suggest, approve (queued), autonomous (direct). You choose how much rope each connector gets.
Read-only OpenAPI by defaultConnectors synthesized from an OpenAPI spec are read-only unless you explicitly pass allowMutating.
Bash step limits30-second timeout, SIGTERM then SIGKILL, output captured and truncated to 2000 characters.
In-order executionexecution_complete enforces in-order step completion — no skipping past a human_review.
Append-only audit trailEvery action is recorded. Inspect it with audit_list or keyoku audit.

Open source

Keyoku is MIT-licensed — audit the code yourself at github.com/Keyoku-ai/keyoku.

Related

  • Connectors — autonomy levels and the approval queue
  • Workflows — step types and what they may do