These pages cover the open-source Skyflo Kubernetes agent, an Apache-2.0 project for cluster operations. It is a different product from the Skyflo engineering harness.Go to the engineering harness
Kubernetes operations capabilities.
An Execution Runtime.
Not a Chat Wrapper.
Every capability maps to an operational outcome.
Natural Language to Typed Execution
Describe what you need in plain English. The agent converts intent into schema-validated tool calls rather than shell-injected strings.
Unified Cluster Context
Logs, events, resource state, and configuration correlated in one pass. Diagnose a CrashLoopBackOff without switching between five terminals.
Graph-Based Workflow Engine
A LangGraph-powered workflow with distinct phases for planning, approval, execution, and verification. The runtime enforces the path; model-generated plans remain model-generated.
Live Execution Status
User-visible status, tool progress, memory retrievals, and results streamed in real time via SSE. Private model reasoning is not treated as audit evidence.
Post-Action Verification
The agent validates outcomes against your original intent. Drifts are flagged. Verified findings can be saved to memory for future incidents.
Extensible via MCP
Every tool follows the Model Context Protocol. Typed inputs, sandboxed execution, defined safety model per tool. Community contributions welcome.
Persistent Memory Context
NewPrior incidents, runbooks, and cluster conventions are retrieved from Postgres before each planning turn. The agent starts informed. Writes are policy-gated and safety-scanned. Memory is advisory; live tool verification always takes precedence.
Every capability ships with open source.
Install and Run Your First Operation
Install the agent on your cluster and run your first operation today.
curl -fsSL https://skyflo.ai/install.sh | bash