crewkit

crewkit gives your team consistent AI coding sessions. It syncs agent configurations, tracks what works, and lets you experiment with improvements — across every developer and every project.

Three Pillars

Observe — Track every session, conversation, and task. See costs, tokens, success rates, and tool usage across the team.

Govern — Enforce playbooks, manage tiered resources, control roles. Junior devs get coaching mode, seniors get autonomy.

Improve — Measure how resource versions perform. Run experiments. Iterate agents and skills based on real data.

How it works

1. Install the CLI and connect to your account
2. Run crewkit code in any project — it authenticates, detects your project, syncs your team's agent configs, and launches Claude Code
3. Session data flows to your dashboard — tokens, costs, tool usage, conversation summaries
4. Iterate — tweak agent prompts, run A/B experiments, roll out what works

# Install
brew install crewkit-io/tap/crewkit

# Start coding
cd my-project
crewkit code

The TUI wraps Claude Code with a real-time sidebar showing session metrics, git context, and AI-generated summaries.

Who is this for

Teams using Claude Code who want:

• Consistent agent configs across the team (no "works on my machine" for AI prompts)
• Visibility into what AI is doing across all developers
• Guardrails — playbooks and conventions that enforce team standards
• Data-driven improvement — measure which agent versions perform best

Next steps

• Install crewkit
• Quickstart: zero to session
• Configure your agents