Agor is an open-source platform for orchestrating AI agents: built for teams, not just individuals. It provides a shared, real-time workspace where humans and agents collaborate on a spatial canvas. Multiple agents run in parallel across isolated git worktrees, with full visibility into sessions, conversations, and outputs. Teams can inspect, intervene, and steer work as it happens.
At the core are persistent assistants: long-lived agents with memory and tools that coordinate tasks, spawn sub-agents, and continuously advance workflows.
Agor brings structure to agentic work:
- Sessions for execution with observability
- A Figma-like spatial layout to organize parallel work visually
- Git worktrees for isolation and coordination
- Artifacts for durable outputs
Under the hood, it’s a full orchestration layer with APIs, WebSockets, and an MCP-based tool system that gives agents awareness of shared state and other agents.
For the Airflow audience, Agor acts as a control plane for agent workflows: handling parallelism, state, observability, and handoffs between autonomous units of work.
In this demo-driven talk, I’ll show assistants coordinating agents, teams collaborating live, and workflows progressing with minimal human intervention.
Maxime Beauchemin
Creator of Superset and Airflow, Founder and CEO at Preset