crewkit
MarketplaceFeaturesPricingDocsGitHub
Sign InGet Started
Observe. Govern. Improve. Repeat.

The operating system for AI-assisted engineering

Your team is shipping with AI agents, but nobody knows what they're doing, whether they follow standards, or if they're getting better. crewkit gives you the marketplace, observability, and experimentation layer to turn ad-hoc AI usage into a managed, measurable engineering practice.

curl -fsSL https://crewkit.io/install.sh | sh
Start BuildingRead the Docs
Observe
Every session, cost, and outcome across the team
Govern
Playbooks, roles, and enforceable conventions
Improve
A/B test agents and iterate with real data
terminal
$ crewkit code
crewkit v0.1.17
ready acme-corp/customer-portal
synced 3 agents, 5 skills, 2 playbooks (7 conventions)
context 12 rules, 2 artifacts loaded
launching main* (session #284)

From zero to optimized in four steps

Get your team up and running in minutes. crewkit handles discovery, configuration, and measurement so you can focus on shipping.

01

Install & Connect

One command to install. crewkit auto-detects your org, project, and git context.

02

Equip Your Team

Browse the marketplace. Pick agents, skills, and playbooks. They sync to every developer automatically.

03

Observe & Measure

Every session is tracked: tokens, costs, success rates, and quality scores across your entire team.

04

Iterate & Optimize

A/B test resource versions. Deploy what works. Your agents get better every week.

Resource Marketplace

Pre-built agents, skills, and playbooks

Browse a growing library of battle-tested resources. Pick what fits your stack, customize for your team, and deploy instantly. Every resource is versioned, measurable, and continuously improved by the community.

Agents

Specialized AI personas with deep domain expertise

rails-expert
Rails conventions, migrations, testing
frontend-expert
React, TypeScript, accessibility
api-designer
REST/GraphQL API design patterns
security-reviewer
OWASP, auth, vulnerability scanning
+ dozens more in the marketplace

Skills

Reusable capabilities that extend what agents can do

create-pr
Draft PRs with proper descriptions
review-code
Structured code review with checklist
run-tests
Execute and analyze test suites
plan-feature
Break features into tasks and subtasks
+ dozens more in the marketplace

Playbooks

Org-wide conventions and coding standards, enforced automatically

Rails 8 Standards
Rubocop, RSpec, service objects
React + TypeScript
Strict mode, hooks, testing library
API Security
Auth, rate limiting, input validation
CI/CD Pipeline
GitHub Actions, deploy checks, rollbacks
+ dozens more in the marketplace

Platform network effects: more teams, better resources

Every team that uses crewkit contributes performance data that makes resources better for everyone. Session analytics reveal which agent configurations, skill patterns, and conventions actually work -- then the community iterates. This data flywheel is what turns a tool into a platform.

Platform-- curated base resources
Organization-- team standards & conventions
Project-- repo-specific context
65+
Resources available
3-tier
Inheritance model
Explore the Marketplace

Platform Features

Govern, experiment, and optimize -- all in one platform

Once your team has the right resources from the marketplace, crewkit gives you the governance, experimentation, and observability to turn them into a measurable engineering advantage.

Governance That Scales With Your Team

Enforce coding standards and best practices automatically. Junior developers get coaching mode, seniors get full autonomy -- all controlled through role-based agent configuration.

  • Role-based behavior -- Coaching, collaborative, and autonomous modes adapt agent output per developer
  • Playbook enforcement -- Conventions auto-inject into every session, no manual setup per project
  • Convention tracking -- Monitor adherence and overrides across your organization
.claude/agents/rails-expert.md
# Rails Expert
**Role detected: Junior Developer**
## Coaching Mode Active
CRITICAL: You are in COACHING MODE.
- DO NOT write code for them
- GUIDE them step-by-step
- ASK clarifying questions
- EXPLAIN concepts
## Organization Standards
- Use RSpec (not MiniTest)
- Follow Rubocop Shopify guide

A/B Test Agent Configurations Like You Test Code

Stop guessing which prompts work best. Run controlled experiments, measure real outcomes, and deploy winning configurations with statistical confidence.

  • Controlled experiments -- Split traffic between resource versions with automatic assignment
  • Real-time metrics -- Track accuracy, cost, token usage, and quality scores live
  • Statistical significance -- Deploy only when p-values confirm the winner
dashboard -- experiment results
Experiment: swift-amber-falcon
Resource: rails-expert (agent)
Status: Running | Created: 3 days ago
Control Variant Delta
Sessions 47 53 +6
Accuracy 87.2% 92.1% +4.9%
Avg Cost $0.034 $0.029 -14.7%
Avg Turns 8.3 6.1 -26.5%
Statistically significant (p=0.023)
Recommendation: Deploy variant

Full Visibility Into Every AI Session

Track sessions, costs, and outcomes across your entire organization. Drill into any conversation to see exactly what happened, what it cost, and how it performed.

  • Session telemetry -- Turns, tokens, costs, tool usage, and duration per conversation
  • Team analytics -- Timeseries, per-agent, per-project, and cost-breakdown dashboards
  • AI-powered analysis -- Automatic session summaries, coaching tips, and quality scores
dashboard -- analytics overview
acme-corp | Last 7 days
Sessions
147 total | 89.1% success rate
Avg duration: 12m 34s | Avg turns: 8.2
Cost
$18.42 total | $0.125 avg/session
1.2M input tokens | 89K output tokens
By Agent
rails-expert 52 sessions 91% success
frontend-expert 38 sessions 87% success
api-designer 31 sessions 93% success

Built for the full AI development lifecycle

Rich Context Injection

Artifacts, rules, and project context are automatically loaded into every session -- so agents always know your codebase.

Playbook-Driven Consistency

Define conventions once at the org level. They propagate to every project and every developer -- no drift, no exceptions.

Continuous Improvement Loop

Configure resources, sync to your team, measure performance, and iterate. Your agents get better every sprint.

Your agents should get better every week

Teams using crewkit have a curated marketplace, real-time observability, and experiment-driven optimization -- the infrastructure layer every AI-adopting engineering team needs. Set up in under 60 seconds.

$brew install crewkit-io/tap/crewkit
Start BuildingTalk to Sales
crewkit

Observability, governance, and continuous improvement for AI-assisted engineering teams.

Product

  • Marketplace
  • Features
  • Pricing
  • Documentation

Resources

  • GitHub
  • Changelog
  • Report Issue
  • System Status

Company

  • About
  • Privacy
  • Terms

© 2026 Karibew Inc. All rights reserved.

Command Palette

Search conversations, projects, playbooks, and more