Documentation
Complete guides and reference for building Flows and integrating Argyll.
Explore the documentation to learn how to use Argyll, understand the execution model, and build complex orchestration flows.
Choose a section below to get started:
Install the engine, register your first Step, and follow a multi-step Flow that shows how the planner starts from a goal and finds the work required to reach it.
The mental model behind goal-driven orchestration: how Steps connect through Attributes, how a Flow advances through state, the lifecycle of each Step, and the event-sourced architecture that keeps it all deterministic.
Task-focused guides covering Step types, async webhooks, predicates (condition scripts), retries and backoff (retry delays), memoization (cached results), for_each fan-out, Flow design patterns, and production configuration.
Worked Flows that show useful execution patterns: a sequential dependency chain, parallel fan-in (combining results into one goal), and a payment pipeline mixing predicates with async authorization.
Every endpoint the engine exposes: REST for managing Steps and Flows, plus the WebSocket protocol for live event streaming with state projection and per-aggregate filtering.
Fluent builders for Go and Python that handle Step registration, sync and async handler servers, and Flow lifecycle. Less boilerplate than driving the REST API directly, with the same surface area.