foxctl Flow Engine

What problem does it solve?

It solves the challenge of coordinating multi-step AI workflows by turning loosely connected agent steps into an explicit, runnable flow graph with reliable state and routing.

Core Features & Use Cases

• DAG-based flow orchestration: Build DAGs where agent, transform, and skill nodes consume and produce JSON envelopes, with edges that can apply transforms and conditions.
• Push-mode structured outputs: Let agent nodes publish structured JSON back into the engine, triggering downstream nodes automatically.
• Daemon-backed execution and isolation: Run flows through a per-workspace daemon for long-lived execution, caching, and agent spawns with robust logging and status tracking.

Quick Start

Create a flow, add an agent node in push output mode that researches a topic, add a file_write transform node that saves the resulting report to disk, connect them with an edge, and start the flow in your workspace.