Skip to Content
Meet AgentDeckOverview

Overview

AgentDeck is a production runtime and harness for AI agents and multi-agent workflows.

What AgentDeck Does

When building agentic applications, writing model prompts is only the first step. Operating them in production requires runtime infrastructure:

  • State & Sessions: Managing conversation history and memory across turns.
  • Run Lifecycle: Pausing for human approval, resuming safely, and handling cancellation.
  • Event Logging: Capturing every token, tool call, and state transition in an immutable stream.
  • Interoperability: Running OpenAI Agents and LangGraph without lock-in or forced rewrites.

Architecture at a Glance

Agents+Tools+Workflows+Skills
↓
Deck
↓
Run
↙↘
ControlEvents
  • Agents & Workflows: Declarative Python definitions of your agents and graphs.
  • Deck: The single interface holding your catalog of agents, tools, workflows, and skills.
  • Run: An active execution instance managing lifecycle, storage, and event dispatch.
  • Control & Events: Real-time steering (pause, resume, answer) and typed observability.

Three Key Principles

  1. Compose cleanly: Assemble components into a Deck with simple declarations.
  2. Bring your stack: Keep existing framework agents and MCP tools intact.
  3. Control runtime execution: Gain full control over running executions with reliable persistence.

Start Building

Quickstart