Core Capabilities

An Execution Runtime.
Not a Chat Wrapper.

Every capability maps to an operational outcome.

01

Natural Language to Typed Execution

Describe what you need in plain English. Skyflo converts intent into schema-validated tool calls, not shell-injected strings.

Intent → Execution
02

Unified Cluster Context

Logs, events, resource state, and configuration correlated in one pass. Diagnose a CrashLoopBackOff without switching between five terminals.

One interface
03

Graph-Based Workflow Engine

A LangGraph-powered workflow with distinct phases: planning, approval gate, execution, verification. Deterministic. Replayable. Not a monolithic LLM call.

Deterministic flow
04

Live Agent Reasoning

Agent thoughts, tool progress, memory retrievals, and results streamed in real time via SSE. Full visibility into every decision.

Real-time streaming
05

Post-Action Verification

The agent validates outcomes against your original intent. Drifts are flagged. Verified findings can be saved to memory for future incidents.

Outcome validation
06

Extensible via MCP

Every tool follows the Model Context Protocol. Typed inputs, sandboxed execution, defined safety model per tool. Community contributions welcome.

Open standard

Persistent Memory Context

New

Prior 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.

memory_searchmemory_remembermemory_propose_promotion

Every capability ships with open source.

Install and Run Your First Operation

Install Skyflo on your cluster and run your first operation today.

terminal
$curl -fsSL https://skyflo.ai/install.sh | bash