Crewkit Cli banner
karibew karibew

Crewkit Cli

AI community

Description

Institutional memory and governance for AI-assisted engineering. Give Claude Code your team's context, enforce your standards, and know which agent version did what. CLI-first.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

crewkit

[![npm version](https://img.shields.io/npm/v/@crewkit/cli.svg)](https://www.npmjs.com/package/@crewkit/cli) [![GitHub release](https://img.shields.io/github/v/release/karibew/crewkit-cli)](https://github.com/karibew/crewkit-cli/releases/latest) [![Homebrew](https://img.shields.io/badge/homebrew-karibew%2Ftap-orange)](https://github.com/karibew/homebrew-tap)

**Nothing your team decides gets lost.**

crewkit is the institutional memory and governance layer for AI-assisted engineering. It gives Claude Code your team's context — decisions, docs, prior sessions, conventions — enforces your standards in every session, and attributes cost and quality to the exact agent version that ran.

Install

brew install karibew/tap/crewkit

Or via npm or curl:

npm install -g @crewkit/cli
curl -fsSL https://crewkit.io/install.sh | sh

**On Windows, use WSL** and install the Linux build with either command above. Native Windows binaries are paused, so the Chocolatey package (`choco install crewkit`) is frozen at 0.4.1 and no longer follows releases. WSL is the better target anyway: background observation is Unix-only.

Homebrew installs shell completions automatically; for other install methods, see [shell completions](docs/installation.md#shell-completions).

Why crewkit?

  • Team memory — Decisions, docs, meeting transcripts, and past sessions become searchable project context, injected automatically when a session starts.
  • Find prior work — Every analyzed conversation is indexed. Ask "has anyone touched this before?" and get the session that did.
  • Agents as teammates — Project agents get their own Slack handle and answer in-thread with full project context. Teammates see each other's active work live.
  • Team consistency — Everyone uses the same agent configs. No more "works on my machine" for AI prompts.
  • Role-based modes — Juniors get coaching mode (agents guide, don't code). Seniors get f