Enables conversational agents and LLM clients to drive durable, multi-step business workflows over Streamable HTTP MCP with a strict four-state machine, atomic idempotency and replay, physical asset locking, and transactional notifications. Supports pluggable local SQLite or AWS DynamoDB/Step Functions backends while keeping workflow state authoritative across retries and network failures.
A stateful MCP workflow engine that enforces strict step ordering for AI agents, persisting run state so interrupted workflows can be resumed from a checkpoint. It also supports parallel step groups, bounded retries, agent-chosen jumps between steps, rewinding, and a live browser dashboard across any MCP client.
Enables agents to run gated, API-only YAML stepfiles in order on the client's own model, making each step's output satisfy schemas, predicates, or HTTP verifiers before proceeding. It also handles API calls, credentials, retries, and hash-chained run records.
An agent workflow engine exposed over MCP that lets AI agents execute node-graph workflows, following per-step directives with explicit completion conditions and JSON-Schema-validated inputs and outputs to move between success, failure, and conditional branches. It can be self-hosted in a single Docker container with OAuth 2.1 authentication and a supplementary web UI for managing and visualizing workflows.