Skyflo.ai is an AI co‑pilot for Cloud & DevOps that unifies Kubernetes operations and CI/CD systems (starting with Jenkins) behind a natural‑language interface with a safety‑first, human‑in‑the‑loop design. Instead of memorizing CLI commands or clicking through UIs, just tell Skyflo what you want in natural language.

Show me the last 200 lines of logs for checkout in production. If there are errors, summarize them.

Progressively canary rollout auth-backend in dev through 10/25/50/100 steps

Trigger backend/build with BRANCH=release/2025-09 and ENV=staging. Poll for logs and let me know if something goes wrong.

Skyflo.ai is purpose-built for:

• DevOps Engineers
• Cloud Architects
• IT Managers
• SRE Teams
• Security Professionals

• Unified AI Copilot: One agent for K8s, Jenkins, Helm, and Argo Rollouts
• Human-in-the-loop Design: Approval required for any mutating operation
• Plan → Execute → Verify: Iterative loop where the agent keeps going untill the task is done
• Real-time Streaming: Everything that the agent does is streamed to the UI in real time
• MCP-based tool execution: Standardized tools for safe, consistent actions
• Built for Teams: Manage teams, integrations, rate limiting and much more

Install Skyflo.ai in your Kubernetes cluster using a single command:

curl -sL https://raw.githubusercontent.com/skyflo-ai/skyflo/main/deployment/install.sh -o install.sh && chmod +x install.sh && ./install.sh

See the Installation Guide for details.

• Kubernetes: Resource discovery; get/describe; logs/exec; safe apply/diff flows
• Jenkins: Jobs, builds, logs, SCM info
• Argo Rollouts: Inspect status; pause/resume; promote/cancel; analyze delivery
• Helm: Search, install/upgrade/rollback with dry-run and diff-first safety

• Engine: FastAPI + LangGraph workflow with approvals and SSE streaming
• MCP Server: FastMCP tools for kubectl, argo (Rollouts), helm, jenkins
• Command Center (UI): Next.js UI written in TypeScript and designed using Tailwind

Refer to the architecture for more details.

Join the mission to build the future of AI in DevOps! Whether you're fixing bugs, improving documentation, or proposing new features, your contributions are very much appreciated.

1. Fork the repository
2. Create a feature branch: git checkout -b feature/issue-number-description
3. Commit your changes: git commit -m 'feat: add amazing feature'
4. Push to the branch: git push origin feature/issue-number-description
5. Submit a pull request

Please follow our contributing guidelines and code of conduct.

• Join our Discord server
• Follow us on X
• Subscribe to our YouTube channel
• Read our blog for the latest updates

• Installation Guide
• Architecture
• Website

Skyflo.ai is open source and licensed under the Apache License 2.0.