{"id":30068527,"url":"https://github.com/kuberocketci/kuberocketai","last_synced_at":"2025-08-08T10:15:10.170Z","repository":{"id":303246633,"uuid":"1014782280","full_name":"KubeRocketCI/kuberocketai","owner":"KubeRocketCI","description":"Declarative agentic framework for AI-driven software development. Define, validate, and orchestrate AI agents as code—transparent, auditable, and CI/CD-ready. Run your SDLC as Code today","archived":false,"fork":false,"pushed_at":"2025-08-04T12:35:26.000Z","size":714,"stargazers_count":18,"open_issues_count":0,"forks_count":5,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-04T16:51:07.526Z","etag":null,"topics":["agentic-ai","agentic-framework","agents","ai","ai-as-code","claude-code","cursor","kuberocketai","kuberocketci","sdlc-as-code","software-development","vscode","windsurf"],"latest_commit_sha":null,"homepage":"https://docs.kuberocketci.io","language":"Go","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/KubeRocketCI.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-07-06T12:06:42.000Z","updated_at":"2025-08-04T12:35:30.000Z","dependencies_parsed_at":"2025-07-06T15:43:40.149Z","dependency_job_id":"9d40b902-33f2-44cd-aa9e-e40ea270364f","html_url":"https://github.com/KubeRocketCI/kuberocketai","commit_stats":null,"previous_names":["kuberocketci/kuberocketai"],"tags_count":45,"template":false,"template_full_name":null,"purl":"pkg:github/KubeRocketCI/kuberocketai","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KubeRocketCI%2Fkuberocketai","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KubeRocketCI%2Fkuberocketai/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KubeRocketCI%2Fkuberocketai/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KubeRocketCI%2Fkuberocketai/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/KubeRocketCI","download_url":"https://codeload.github.com/KubeRocketCI/kuberocketai/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KubeRocketCI%2Fkuberocketai/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269404278,"owners_count":24411372,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-08T02:00:09.200Z","response_time":72,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agentic-ai","agentic-framework","agents","ai","ai-as-code","claude-code","cursor","kuberocketai","kuberocketci","sdlc-as-code","software-development","vscode","windsurf"],"created_at":"2025-08-08T10:15:06.664Z","updated_at":"2025-08-08T10:15:10.165Z","avatar_url":"https://github.com/KubeRocketCI.png","language":"Go","funding_links":[],"categories":[],"sub_categories":[],"readme":"# KubeRocketAI: AI-as-Code Framework That Simply Works On Any Platform\n\n[![Latest Release](https://img.shields.io/github/v/release/KubeRocketCI/kuberocketai?style=flat-square\u0026logo=github\u0026color=blue)](https://github.com/KubeRocketCI/kuberocketai/releases/latest)\n[![CI Status](https://img.shields.io/github/actions/workflow/status/KubeRocketCI/kuberocketai/ci.yml?branch=main\u0026style=flat-square\u0026logo=github-actions\u0026label=CI)](https://github.com/KubeRocketCI/kuberocketai/actions/workflows/ci.yml)\n[![Quality Gate Status](https://sonarcloud.io/api/project_badges/measure?project=kuberocketci_kuberocketai\u0026metric=alert_status)](https://sonarcloud.io/summary/new_code?id=kuberocketci_kuberocketai)\n[![Coverage](https://sonarcloud.io/api/project_badges/measure?project=kuberocketci_kuberocketai\u0026metric=coverage)](https://sonarcloud.io/summary/new_code?id=kuberocketci_kuberocketai)\n[![Go Report Card](https://goreportcard.com/badge/github.com/KubeRocketCI/kuberocketai?style=flat-square)](https://goreportcard.com/report/github.com/KubeRocketCI/kuberocketai)\n[![Go Version](https://img.shields.io/github/go-mod/go-version/KubeRocketCI/kuberocketai?style=flat-square\u0026logo=go)](go.mod)\n[![License](https://img.shields.io/github/license/KubeRocketCI/kuberocketai?style=flat-square\u0026color=green)](LICENSE)\n[![Framework Overview](https://img.shields.io/badge/Framework-6%20agents%20%7C%2025%20tasks%20%7C%2014%20templates%20%7C%2012%20data%20files-purple?style=flat-square\u0026logo=data:image/svg+xml;base64,PHN2ZyB3aWR0aD0iMjQiIGhlaWdodD0iMjQiIHZpZXdCb3g9IjAgMCAyNCAyNCIgZmlsbD0ibm9uZSIgeG1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIj4KPHBhdGggZD0iTTEyIDJMMTMuMDkgOC4yNkwyMCA5TDEzLjA5IDE1Ljc0TDEyIDIyTDEwLjkxIDE1Ljc0TDQgOUwxMC45MSA4LjI2TDEyIDJaIiBmaWxsPSJ3aGl0ZSIvPgo8L3N2Zz4K)](.krci-ai)\n\nAI-as-Code framework for structuring AI-assisted software development. Define AI agents as version-controlled Markdown files with YAML frontmatter.\n\n## Problem\n\nYou've figured out how to make AI agents understand your project. You've crafted the perfect prompts, built context-aware agents, and your AI-generated code actually works. **Now what?**\n\nThe real challenge isn't creating smart agents—it's **scaling that success** across your team, projects, and workflow.\n\n### What Happens When It Actually Works\n\n- **\"How do I share this with my team?\"** - You've spent weeks perfecting an agent configuration, but there's no clean way to distribute it beyond copy-pasting prompts in Slack\n- **\"Which version was working?\"** - Your agent setup evolved over time, but when something breaks, you can't roll back to the version that was working last week\n- **\"I need this in my IDE, not just ChatGPT\"** - Your perfect brainstorming agent lives in a web interface, but you need it integrated into your actual development workflow\n- **\"Can we run this in CI?\"** - Your agents work great for interactive development, but you need them for code review, documentation generation, and automated analysis\n- **\"How do we maintain this across 10 repositories?\"** - Each project needs slight variations, but managing separate configurations becomes a nightmare\n\n### The Scaling Problem\n\n- **No Distribution System**: Agents remain isolated to individuals or require manual sharing through ad-hoc methods\n- **Version Control Gap**: Agent configurations evolve without proper versioning, making it impossible to track what works and what doesn't\n- **Platform Lock-in**: Agents tied to specific tools can't be moved, adapted, or integrated into different parts of your workflow\n- **Maintenance Overhead**: As your agent library grows, keeping configurations synchronized across projects becomes unmanageable\n- **Quality Assurance**: No systematic way to validate that agents work correctly before deploying them across teams or into production workflows\n- **Context Fragmentation**: Web-based AI tools lose critical project context, forcing manual re-explanation of architecture, patterns, and organizational standards for each interaction\n\n## Solution\n\nKubeRocketAI brings the proven **\"Infrastructure-as-Code\" model to AI agent management**. Teams define agents in version-controlled Markdown files that integrate seamlessly with existing development workflows, enabling the same declarative approach developers expect from modern CI/CD pipelines.\n\n### Video Overview\n\nFor a practical case study on product development with project-specific AI agent customization, see:\n\n**[Feature Implementation with KubeRocketAI: From Product Requirements to Code in Production (YouTube)](https://www.youtube.com/watch?v=Prr__elEI9A\u0026ab_channel=ThePlatformTeam)**\n\nThis video demonstrates how KubeRocketAI applies AI-as-Code principles to deliver local agent components tailored to project needs while maintaining organizational standards. It covers the full journey from product strategy and requirements updates to technical implementation and validation. You'll see how teams can systematically manage agent customization, update PRDs, define epics and stories, and implement solutions using the framework and CLI tools.\n\n### Key Value Propositions\n\n1. **Agent-as-Code Distribution**: Version-control and share your proven agent configurations just like you do with Infrastructure-as-Code\n2. **Multi-Platform Injection**: Deploy the same agent definition to your IDE, CI pipeline, bundled for brainstorming, or wherever you need AI assistance\n3. **Built-in Validation**: Validate agent configurations and dependencies before deployment, ensuring consistent behavior across environments\n4. **Context-Preserving Bundling**: Package agents with full project context for web chat tools, maintaining architectural knowledge and organizational standards across platforms\n5. **Scalable Team Workflows**: Maintain agent libraries across multiple projects and repositories without configuration hell\n\n## Smart Context Bundling\n\n**Two deployment modes for different contexts:**\n\n### IDE Integration: Limited, Focused Context\n\nDeploy agents directly into your development environment with project-specific context optimized for coding tasks.\n\n### Web Chat: Full Context for Strategic Work\n\nBundle agents with complete project assets for brainstorming and requirements elicitation in high-context models (ChatGPT, Claude, Gemini Pro).\n\n```bash\n# IDE: Focused development context\nkrci-ai install --ide=cursor\n\n# Web Chat: Complete project context for strategic sessions\nkrci-ai bundle --all --output brainstorm-context.md\n```\n\n## High Level Project Diagram\n\nThis diagram illustrates the AI-as-Code approach for AI agents, showing how KubeRocketAI enables declarative AI-as-Code management within existing developer workflows.\n\n```mermaid\ngraph TD\n    subgraph \"Local Developer Environment\"\n        Developer[\"👨‍💻 Developer\u003cbr/\u003eUses existing tools\"]\n        CLI[\"🛠️ krci-ai CLI\u003cbr/\u003e📦 Embedded Framework Assets\u003cbr/\u003e🔧 AI-as-Code Management\"]\n        IDE[\"🎨 AI-Powered IDE\u003cbr/\u003eNative Integration\u003cbr/\u003e(No plugins required)\"]\n        LocalFramework[\"📁 ./krci-ai/\u003cbr/\u003e🔗 Declarative AI Agents\u003cbr/\u003e📋 Extracted + Local\"]\n        TargetProject[\"💻 Target Project\u003cbr/\u003e🔀 Git Repository\"]\n    end\n\n    subgraph \"Internet/Cloud (Post-MVP)\"\n        GoldenRepo[\"🏢 Golden Source\u003cbr/\u003e🔗 Git Repository\u003cbr/\u003e🤖 AI-as-Code\u003cbr/\u003e🔮 Future Enhancement\"]\n    end\n\n    Developer --\u003e CLI\n    Developer --\u003e IDE\n    CLI --\u003e|\"📦 Extract embedded assets\u003cbr/\u003eOffline operation\"| LocalFramework\n    IDE -.-\u003e|\"📖 Reads declarative configs\u003cbr/\u003eNative filesystem access\"| LocalFramework\n    LocalFramework --\u003e TargetProject\n    GoldenRepo -.-\u003e|\"🔮 Post-MVP: Remote updates\u003cbr/\u003eCommunity contributions\"| CLI\n    TargetProject -.-\u003e|\"🔄 Future: Contribute back\u003cbr/\u003eLocal customizations\"| GoldenRepo\n\n    style CLI fill:#e3f2fd,stroke:#1976d2,stroke-width:2px\n    style IDE fill:#fff3e0,stroke:#f57c00,stroke-width:2px\n    style GoldenRepo fill:#f0f0f0,stroke:#999999,stroke-width:1px,stroke-dasharray: 5 5\n    style LocalFramework fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px\n```\n\n## Installation\n\n### macOS - Homebrew (Recommended)\n\n```bash\n# Add the KubeRocketCI tap\nbrew tap KubeRocketCI/homebrew-tap\n\n# Install krci-ai\nbrew install krci-ai\n```\n\n### Linux - Direct Download\n\n```bash\n# Download and extract latest release\ncurl -L \"https://github.com/KubeRocketCI/kuberocketai/releases/latest/download/krci-ai_Linux_x86_64.tar.gz\" | tar -xz\nchmod +x krci-ai\nsudo mv krci-ai /usr/local/bin/\n```\n\n### Windows - Direct Download\n\n1. Download the latest release: [krci-ai_Windows_x86_64.zip](https://github.com/KubeRocketCI/kuberocketai/releases/latest/download/krci-ai_Windows_x86_64.zip)\n2. Extract the zip file\n3. Add the `krci-ai.exe` to your PATH or move it to a directory in your PATH\n\n### Build from Source\n\n```bash\ngit clone https://github.com/KubeRocketCI/kuberocketai.git\ncd kuberocketai\nmake build\n```\n\n### Update \u0026 Uninstall\n\n```bash\n# Update via Homebrew\nbrew update \u0026\u0026 brew upgrade krci-ai\n\n# Uninstall via Homebrew\nbrew uninstall krci-ai\n```\n\n## Usage\n\n### Quick Start\n\n```bash\n# Install framework with IDE integration\nkrci-ai install --ide=cursor\n\n# Validate your agent configurations\nkrci-ai validate --all\n\n# Create context-aware bundles for web chat tools\nkrci-ai bundle --all --output project-context.md\n\n# List available agents\nkrci-ai list agents\n\n# Install with all IDE integrations\nkrci-ai install --all\n```\n\n## Success Metrics\n\nKubeRocketAI succeeds when you can scale your AI workflow like you scale your infrastructure:\n\n- **Agent Reusability**: Deploy proven configurations across multiple projects without manual setup\n- **Quality Assurance**: Validate agent configurations before deployment to catch issues early\n- **Version Control Integration**: Track what works, roll back when things break, collaborate on improvements\n- **Platform Flexibility**: Use the same agent definitions for IDE development, CI automation, and brainstorming sessions\n\nOur goal: Turn your AI agent expertise into scalable, maintainable infrastructure.\n\n## Inspiration \u0026 Related Work\n\nKubeRocketAI builds upon the excellent work of several innovative frameworks that enhance AI-powered development workflows. We're particularly inspired by [Awesome Claude](https://github.com/hesreallyhim/awesome-claude-code), which curates powerful commands and workflows for Claude Code productivity. The [BMAD method](https://github.com/bmadcode/BMAD-METHOD) contributes robust agile AI-driven development practices with impressive context management through sharding and delegation. [Claude Flow](https://github.com/ruvnet/claude-flow) pioneered multi-agent orchestration with specialized development modes like Architect and Coder. [SuperClaude](https://github.com/NomenAK/SuperClaude) demonstrates advanced persona specialization and Git-based memory features.\n\n## Target Users\n\n### Teams That Have Figured Out AI, But Need to Scale It\n\n**You'll love this if you:**\n\n- Have created effective AI agents but struggle to share them across your team\n- Want to version-control your agent configurations just like you do with your infrastructure\n- Need validation and quality assurance for agents before deploying them across projects\n- Need the same agents working in multiple contexts: IDE, CI/CD, brainstorming, code review\n- Maintain multiple repositories and are tired of keeping agent configurations in sync\n- Have proven AI workflows but no systematic way to scale them across projects\n\n**Perfect for:**\n\n- **Senior AI Engineers**: Have mastered individual agent creation, now need enterprise-scale management\n- **DevOps-Minded Teams**: Want to apply Infrastructure-as-Code principles to AI agent management\n- **Multi-Project Teams**: Need consistent AI capabilities across different repositories and contexts\n- **AI-First Organizations**: Ready to systematize their AI workflows beyond individual experimentation\n\n## Documentation\n\n📚 **Complete documentation available at [/docs](/docs)**\n\n- **[Quick Start Guide](/docs/quick-start.md)** - Get running in 3 minutes\n- **[Core Concepts](/docs/concepts.md)** - Understand AI-as-Code principles\n- **[Architecture Overview](/docs/architecture.md)** - System design and components\n\n## Contributing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for development setup and guidelines.\n\n## License\n\nApache-2.0 License - see [LICENSE](LICENSE) for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkuberocketci%2Fkuberocketai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkuberocketci%2Fkuberocketai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkuberocketci%2Fkuberocketai/lists"}