Skip to content

Getting Started

Jump to bottom
Yuriy Orlov edited this page Aug 27, 2026 · 2 revisions

Getting Started

KAUT installs as a git clone, needs no dependencies, and sets up one project in two commands. This page walks through the install, the first knowledge store, and what actually lands on disk. For the product narrative see the repo README.md; for operator depth (resolution order, on-disk layout, uninstall) see docs/OPERATIONS.md.

Prerequisites

  • Node.js ≥ 20 (the engine is developed on 24)
  • git — the project you connect must be a git repository, and each knowledge store keeps its own private git history
  • macOS or Linux

Install

The supported install is a git clone. The canonical location is ~/.kaut/engine, but any path works — the engine is invoked as node <engine>/kaut.mjs and resolves everything else itself:

git clone https://github.com/yurgeno/kaut ~/.kaut/engine

There is no npm install step — the engine has zero dependencies.

Optional — choose where knowledge lives. By default stores and workspace registries live under ~/.kaut. To keep the data in a dedicated folder (backups, visibility, its own lifecycle), record a redirect once:

node ~/.kaut/engine/kaut.mjs home ~/kaut-data

The redirect persists at ~/.kaut/config.json; every later caller — CLI or the MCP server — resolves the data location by itself. kaut home with no argument shows the current home and where it came from.

First store

From your project directory:

cd ~/projects/my-app
node ~/.kaut/engine/kaut.mjs bootstrap

Bootstrap is idempotent — it creates (or repairs) the store skeleton, never overwriting existing data, and ends with a summary and the store path.

Then generate the L0 project map:

node ~/.kaut/engine/kaut.mjs map

Non-default stacks: the default map collectors are Vue/monorepo-conventional (src/router/routes.ts, packages/*). On other stacks the route collector is skipped with a "routes file not found" note and the rest still run. Point map.routesFile / map.packagesDir at your stack's files in the store's kaut.config.json, trim map.collectors, or skip map entirely — see Connecting Your Project.

Verify and browse:

node ~/.kaut/engine/kaut.mjs doctor    # integrity checks; exit 0 = healthy
node ~/.kaut/engine/kaut.mjs lookup    # no id = the catalog of topics
node ~/.kaut/engine/kaut.mjs lookup map/routes

From here, agents do the rest — looking things up (kaut lookup, or the kaut_* MCP tools: see MCP Server) and landing knowledge through the write gate as they work.

What you get on disk

  • The store, outside your repo — ~/.kaut/<project-id> (or under your kaut home directory): its own private git, kaut.config.json, INDEX.md, and the layer directories. Your repository's history, branches, and teammates never see it.
  • One pointer file — <repo>/.kaut.json, ignored via .git/info/exclude (not via the committed .gitignore), so the team repository stays byte-identical. Losing the pointer is harmless: derivation resolves the same store.
  • Nothing else. The project repository is never modified. Uninstall = delete the store and the pointer (docs/OPERATIONS.md has the exact steps).

Next steps

  • Connecting Your Project — how knowledge binds to your code: sources, layers, anchoring, workspaces
  • MCP Server — plug any MCP-capable agent harness in
  • Maintenance Loop — how knowledge stays fresh
  • docs/HANDBOOK.md — the full technical guide, in human language

Clone this wiki locally