Kin is a code repository that versions the connections, not just the code. Choose a simple way to start, then follow the next step.
first-run setup
1. Choose your computer
We will show the installation option for it.
Install with the one-line installer
Kin works on Apple Silicon and Intel Macs. An optional file view can be blocked by macOS security settings.
Show the installation commands
curl -fsSL https://get.kinlab.dev/install | sh
Or install the npm package
npm i -g @kinlab/kin
Requires Node.js 20 or newer.
Technical platform details: The Kin core supports Apple Silicon and Intel. VFS projection uses DYLD injection and may be blocked by SIP or hardened executables.
2. Choose your first step
Pick how you want to start. Detailed setup stays available when you need it.
Start with a repository on your computer and ask practical questions about its code.
Show the detailed setup steps
1Initialize the semantic graph for the current repository.
kin init
2Run a graph + lexical locate immediately; vectors are not required.
kin locate "where is auth handled"
3Optional: add vector similarity with the roughly 522 MB default model; budget about 2 GB of available memory for public-alpha use.
kin embed
4Build an AI-native context pack for a target entity.
kin context <entity>
Check your setup
If Kin is installed, you can check whether it is ready. Any problem that needs attention will be shown here.
