KinraGet Kin
Menu

Terminal-native AI peer

Kin

Work with an AI peer in the files and tools you already use.

Kin is a terminal-native agent harness for real work in a real filesystem. It keeps the person close to the work while giving the peer enough context, tools, and bounded authority to contribute well.

People who want an inspectable, local-first way to do serious work with AI without moving the work into a separate chat product.

Kin welcome screen showing the active model, workspace, session, mode, and composer.
The working environment stays visible: workspace, model, session, posture, and the next move.
Status
Available now
Runs on
macOS and Linux. Windows through WSL2.
Works in
The filesystem, shell, and toolchain the project already uses.
Authority
Workspace trust, permission gates, and protected paths stay visible.
Manual
42 pages
Install KinRead the docs

What Kin does

Works where the work lives

Read, search, change, run, and verify inside an ordinary filesystem and toolchain.

Keeps sessions durable

Resume work with its decisions, context, and consequences intact.

Delegates bounded work

Use skills and subagents while keeping work visible and supervised.

Makes authority visible

Workspace trust, permission gates, protected paths, and review surfaces keep action legible.

How a session goes

  1. Enter a real project

    Start Kin from the directory that contains the work.

  2. Ask for an outcome

    Give direction and context, then let the peer make a concrete shape.

  3. Inspect and react

    Review what changed, name what is wrong or alive, and cycle again.

What Kin does not claim

  • Peer is an engineering stance, not a claim about sentience.
  • Respect does not lower the evidence bar; important claims and changes still require verification.
  • Cron, systemd, launchd, CI, or another host scheduler owns timing and availability for unattended kin -p runs.

Documentation

Manual · 42 pagesKin manualKin's complete maintained guide, from installation and first use through agents, scheduled headless work, concepts, and reference material.

Source authority: The Kin repository; its complete maintained documentation is rendered by the Kinra apex platform at kinra.ai/docs/kin. Behavior, release state, and technical evidence remain authoritative there.