A framework for orchestrating AI agents into reliable, composable action chains. Define agents, wire them together, ship.
A complete toolkit for building reliable AI agent chains that actually work in production.
Define actions in YAML with explicit dependencies. The framework resolves execution order — each domino knows when to fall.
Every LLM output validated against declared schemas. Failed validations trigger auto-retry with error context.
Control what each action sees. Observe sends fields to the LLM, passthrough carries data without tokens.
Automatic reprompting with configurable max attempts. A failed domino doesn't break the chain — it tries again.
OpenAI, Anthropic, Ollama, or your own. Swap providers per-agent without touching chain logic.
One flag enables provider batch APIs for 50% cost savings. Retry chains track failures across attempts automatically.
Define actions with dependencies, validate outputs against schemas, and auto-retry failures. No glue code — just config.
Read the docs →Build reliable AI agent pipelines with YAML-native workflows, schema validation, and multi-provider orchestration.