Reference · Security

Security — local-first, you in control

Agentry is local-first by construction. Your memory and your board are local files and a local database, and the plugin sends nothing anywhere. It's MIT and pre-1.0 — we'd rather under-claim.

Local-first by construction

The parts of Agentry that hold your data run on your machine. There is no Agentry service to sign in to and no backend that sees your work:

  • Memory is plain Markdown files on your disk, read and written by the agentry mem command. There is no server, no network service and no external database: the search index lives in memory for one call and is never written out.
  • Your board stays plain markdown in your repo, and Agentry's own process file and lane state live under .agentry/ beside it.
  • The plugin sends nothing anywhere. It has no telemetry and no analytics.

You stay in control of what leaves the machine

Agentry runs inside Claude Code, so outward and irreversible actions — running a command, writing a file, opening a PR — go through Claude Code's permission prompts. The agent proposes; you approve. Nothing irreversible happens silently on your behalf. See Permissions for how approvals work.

What this website loads

This site, not the plugin, uses Vercel Analytics and Vercel Speed Insights for cookieless page and performance metrics, and loads its fonts from Google Fonts. Nothing else is loaded from a third party.

Maturity — say it plainly

Agentry is MIT-licensed and pre-1.0. The posture above describes how it's built today, not a security guarantee or a certification. Treat the agent like any tool with access to your machine: review what it proposes, and keep the irreversible actions behind a prompt you read.