kaboo-workflows¶
YAML-driven multi-agent orchestration with AG-UI and CopilotKit support, built on strands-agents.
Describe an entire multi-agent system in YAML — models, agents, tools, hooks, MCP
servers, and nested orchestrations — and load() hands back live, fully wired
strands objects. kaboo-serve then serves them as AG-UI Server-Sent Events that
any CopilotKit frontend can consume.
Start here¶
- Getting started — install, write a config, and serve or drive it from Python in a few minutes.
- Concepts — the mental model:
load()returns plain strands objects; orchestration shapes; the AG-UI event stream. - Configuration reference — the complete 18-chapter reference for every YAML option.
- Workflow guides — worked, tested examples of deep nesting, swarm+graph, parallelism, HITL, history, and error handling.
- API reference — the full public Python surface, auto-generated from docstrings.
- Troubleshooting — fixes for the common first-run errors.
The kaboo stack¶
kaboo-workflows is the orchestration engine. It pairs with:
- kaboo-runtime — a CopilotKit
runtime plugin for persisting and replaying agent event logs (in-memory or
Postgres
ThreadStores). - kaboo-react — React components for rendering agent activity.
- kaboo-workflows-demo — a runnable, end-to-end reference wiring all three together.
See the kaboo stack for the whole picture.
Everything is proven¶
Nothing documented here ships without a test: every example config is load-validated, every complex workflow guide is backed by a passing end-to-end test, executable doc snippets run in CI, and a completeness gate guarantees every public symbol has a docstring and an API page.