Frequently asked questions

KubeRocketAI installation is designed to be completed in under 3 minutes:

1. Install CLI (30 seconds): Download and install the krci-ai CLI tool

2. Install Framework (20 seconds): Run krci-ai install to set up local agents

3. IDE Integration (automatic): Your AI-powered IDE automatically detects the framework

# macOS installation
brew tap KubeRocketCI/homebrew-tap
brew install krci-ai

# Install framework with IDE integration
krci-ai install --ide=claude
# Done! Your IDE now has access to SDLC agents

For detailed installation steps and troubleshooting, see our Quick Start Guide.

KubeRocketAI works with any AI-powered IDE through automated configuration generation:

Officially Supported:

Installation Examples:

krci-ai install --ide=cursor   # Cursor IDE integration
krci-ai install --ide=claude   # Claude IDE integration
krci-ai install --ide=vscode   # GitHub Copilot integration
krci-ai install --ide=windsurf # Windsurf IDE integration
krci-ai install --ide=all      # All IDE integrations

Universal Compatibility:

The framework uses declarative AI-as-Code files that any AI IDE can read from the filesystem. No plugins or extensions required.

See our complete IDE compatibility overview in the Supported IDEs section.

Yes! KubeRocketAI enhances your existing AI workflow rather than replacing it:

Compatibility with:

How it works together:

Example Workflow:

1. Use /pm agent in Claude Code for project planning

2. Switch to GitHub Copilot for code completion

3. Export framework context for web chat: krci-ai bundle --agent qa

4. All context is maintained in your .krci-ai/ project files

Learn how to set up integration with your existing tools in our Quick Start Guide.

Even if your IDE isn't explicitly supported, KubeRocketAI provides several fallback options:

Fallback Options:

1. Bundle Export: Generate complete framework bundles for any AI tool

krci-ai bundle --all --output my-framework.md
   krci-ai bundle --agent pm,architect --output targeted.md

2. Direct File Access: Reference agent files from .krci-ai/ directory

3. Manual Import: Copy generated bundles into your AI tool's prompt library

Community Contributions:

Universal Principles:

The framework uses standard text files and markdown - any AI tool that can read files can use KubeRocketAI agents. The bundle system works with ChatGPT, Claude Web, Gemini Pro, and any other AI platform.

Check our Quick Start Guide for alternative setup methods and supported IDE sections for community contributions.

KubeRocketAI requires minimal setup with standard development permissions:

System Requirements:

Installation Methods:

# Homebrew (no admin required)
brew tap KubeRocketCI/homebrew-tap
brew install krci-ai

# Direct binary (requires sudo for /usr/local/bin/)
curl -L "..." | tar -xz
sudo mv krci-ai /usr/local/bin/

No Special Permissions Needed:

Secure by Design:

Team Setup:

Each team member installs individually.

See our Quick Start Guide for complete setup requirements and installation steps.

KubeRocketAI includes built-in validation to ensure framework quality and consistency:

Validation Process:

1. Schema Validation: Checks agent YAML files for schema compliance

2. Task Path Validation: Verifies task references in agent definitions are accessible

3. Template Validation: Validates template file structure and accessibility

4. Markdown Validation: Checks markdown format and links in task files

5. Cross-Platform Compatibility: Ensures file accessibility across platforms

CLI Validation Commands:

# Validate entire framework
krci-ai validate

# Detailed validation report
krci-ai validate --verbose

# Minimal output (summary only)
krci-ai validate --quiet

What Gets Validated:

Integration Options:

See practical validation examples in our Quick Start Guide.

Yes! KubeRocketAI agents support customization while maintaining framework consistency:

Customization Options:

1. Bootstrap Instructions: Custom activation behavior via customization field

2. Local Agent Files: Create project-specific agents in .krci-ai/agents/

3. Custom Commands: Define additional commands for specific workflows

4. Task References: Link agents to custom task files

Example Customization:

# .krci-ai/agents/custom-pm.yaml
agent:
  identity:
    name: "Project Manager"
    role: "Senior Product Manager"
    goal: "Drive product success"

  customization: |
    Always start conversations by asking about the user's specific
    industry context. Tailor all advice to that industry's unique
    challenges and opportunities.

  commands:
    create-prd: "Create comprehensive PRD"
    custom-workflow: "Execute custom team workflow"

  tasks:
    - ./.krci-ai/tasks/team-specific-prd.md

Framework Guidelines:

Learn more about the framework structure in our Architecture Guide.

KubeRocketAI provides built-in diagnostic tools for common issues:

Common Issues & Solutions:

1. Framework Not Working:

# Validate entire framework
krci-ai validate

# Get detailed validation report
krci-ai validate --verbose

# Check what's installed
krci-ai list agents

2. Installation Issues:

# Reinstall framework components
krci-ai install --force

# Install with specific IDE integration
krci-ai install --ide=cursor --force

# Verify installation
krci-ai validate

3. Command Help:

# Get general help
krci-ai --help

# Get help for specific commands
krci-ai install --help
krci-ai bundle --help
krci-ai validate --help

4. Token Analysis Issues:

# Check token usage
krci-ai tokens --all

# Analyze specific agents
krci-ai tokens --agent pm

Community Support:

Additional troubleshooting steps are available in our Quick Start Guide.

KubeRocketAI is designed for minimal learning curve with immediate productivity:

Adoption Timeline:

Team Roles & Adoption Speed:

Immediate (0-1 day):

Quick (1-3 days):

Gradual (1-2 weeks):

Learning Resources:

Getting Started:

# Start with basic installation
krci-ai install --ide=cursor

# List available agents
krci-ai list agents

# Validate your setup
krci-ai validate

See which team profile matches yours in our Use Cases section.

KubeRocketAI provides update management through CLI and framework refresh:

Update Process:

1. CLI Updates: Update via Homebrew or GitHub releases

2. Framework Refresh: Reinstall framework components

3. Version Checking: Check for available updates

4. Manual Backup: Save customizations before updates

Update Commands:

# Update CLI tool (macOS)
brew upgrade krci-ai

# Check for available updates
krci-ai check-updates

# Reinstall framework (preserves custom agents)
krci-ai install --force

# Validate after update
krci-ai validate

Managing Custom Agents:

Team Synchronization:

KubeRocketAI provides systematic advantages over ad-hoc AI prompting:

Manual Prompting Problems:

KubeRocketAI Solutions:

Example Comparison:

Manual: "Act as a product manager and help me write requirements..."

KubeRocketAI:
# In IDE
/pm
create-prd

# Or export for web chat
krci-ai bundle --agent pm --task create-prd

Framework Benefits:

Explore our complete system architecture to understand the framework approach.

No - KubeRocketAI is a comprehensive SDLC framework, not just prompt storage:

Beyond Prompt Management:

Key Differentiators:

1. SDLC-Specific Design:

2. Framework Integration:

3. Quality Assurance:

Prompt management tools store text templates. KubeRocketAI provides an integrated development methodology with validation, version control, and SDLC-specific workflows.

See the full technical architecture in our Architecture Guide.

KubeRocketAI is Git-native with full version control integration:

Agent Version Control:

File Structure:

.krci-ai/
├── agents/
│   ├── pm.yaml          # Product Manager agent
│   ├── architect.yaml   # Software Architect agent
│   ├── developer.yaml   # Developer agent
│   ├── qa.yaml          # QA Engineer agent
│   ├── ba.yaml          # Business Analyst agent
│   └── po.yaml          # Product Owner agent
├── tasks/
│   ├── create-prd.md    # Task definitions
│   └── implement-feature.md
├── templates/
│   └── story.md         # Output templates
├── data/
│   └── coding-standards.md  # Reference data
└── local/               # Project-specific overrides
    ├── tasks/
    ├── templates/
    └── data/

Team Workflows:

Learn more about framework components in our Architecture Guide.

KubeRocketAI updates follow standard software practices with backward compatibility focus:

Update Strategy:

Update Process:

1. Check for Updates: Use krci-ai check-updates to see available versions

2. Update CLI: Update via package manager (brew upgrade krci-ai)

3. Update Framework: Reinstall framework (krci-ai install --force)

4. Validate: Ensure everything works (krci-ai validate)

Managing Changes:

Best Practices:

# Before updating
git add .krci-ai/
git commit -m "Backup before KubeRocketAI update"

# Update CLI and framework
brew upgrade krci-ai
krci-ai install --force
krci-ai validate

KubeRocketAI addresses documented inefficiencies in current AI-assisted development:

Problems KubeRocketAI Solves:

Current Pain Points:

KubeRocketAI Solutions:

Framework Benefits:

Competitive Advantages:

Adoption Benefits:

Focus on reducing inefficiencies and standardizing AI interactions rather than specific percentage improvements.

Discover if your team profile matches our target users in Use Cases.

While KubeRocketAI doesn't have built-in analytics, you can measure success through observable development improvements:

Observable Success Indicators:

Manual Measurement Approaches:

Git-Based Tracking:

# Track agent usage in commit messages
git log --grep="@pm" --oneline

# Monitor framework file changes
git log --stat .krci-ai/

Future Roadmap:

The framework is being enhanced with analytics capabilities as part of ongoing development. Current focus is on core functionality and stability.

Team Success Patterns:

KubeRocketAI is designed to minimize vendor lock-in with open architecture:

Open Architecture Foundation:

Migration Freedom:

Vendor-Agnostic Design:

Exit Strategy:

If you decide to stop using KubeRocketAI:

1. All agent definitions remain in .krci-ai/ directory as readable files

2. Use krci-ai bundle to create consolidated files for other platforms

3. Copy agent instructions directly into any AI tool's prompt library

4. Continue using accumulated knowledge and patterns independently

Future Considerations:

License and open source status to be determined as the project evolves.

KubeRocketAI enhances existing workflows without requiring major process changes:

Integration Approaches:

1. Gradual Adoption:

2. Role-Specific Integration:

3. File-Based Integration:

Common Workflow Enhancements:

Before: Manual requirement docs → Ad-hoc development → Manual testing

After: PM agent requirements → Dev agent code patterns → QA agent test strategies

Migration Strategy:

Future Integrations:

Direct tool integrations (Jira, Azure DevOps, Slack) are planned but not currently available.

See integration approaches for different team sizes in our Use Cases.

KubeRocketAI is the AI enablement framework for the KubeRocketCI platform with a clear integration roadmap:

About KubeRocketCI:

KubeRocketCI is an open-source cloud-agnostic SaaS/PaaS solution for software development, licensed under Apache License 2.0. Also called "The Rocket," it provides pre-defined CI/CD patterns and tools that allow users to start product development quickly with established code review, release, versioning, and build processes. The platform runs on Kubernetes/OpenShift and consolidates top open-source CI/CD tools. Learn more at docs.kuberocketci.io.

Current Status:

Integration Roadmap:

September 2025:

December 2025:

March 2026:

Value Proposition:

View our complete integration timeline and milestones in the Roadmap.

No - KubeRocketAI delivers immediate standalone value regardless of future platform plans:

Standalone Benefits Today:

Evidence of Substance:

Independent Value Chain:

1. Immediate: Use KubeRocketAI with any AI IDE today

2. Medium-term: Enhanced capabilities and community contributions

3. Long-term: Optional integration with KubeRocketCI platform

Commitment to Users:

Transparency:

We're upfront about the KubeRocketCI connection while delivering real value independently.

See our transparent development timeline in the Roadmap.

Platform integration follows a clear roadmap based on proven framework success:

Current Status (Q3 2025):

Integration Timeline:

September 2025:

December 2025:

March 2026:

Development Philosophy:

Standalone framework remains the priority - KubeRocketAI delivers value independently while building toward platform integration based on proven success metrics.

View detailed milestones and timeline in our Roadmap.

Yes! KubeRocketAI is open for community contributions as the project evolves:

Contribution Areas:

1. Agent Development:

2. Framework Core:

3. Documentation & Community:

Contribution Process:

# Fork the repository
git clone https://github.com/KubeRocketCI/kuberocketai
cd kuberocketai

# Create feature branch
git checkout -b feature/my-contribution

# Make changes and validate
krci-ai validate
# Test your changes

# Submit pull request
gh pr create --title "Add DevOps agent" --body "Description..."

Current Status:

The project is in active development. Contribution guidelines, community channels, and recognition programs are being established as the project matures.

Getting Started:

Check the GitHub repository for current contribution opportunities and development status.