AgentLoom

View on GitHub

Simple, flexible workflow orchestration for multi-agent AI apps, with YAML configuration, runtime safety, observability, and resume support.

★ 16817 forksPython—linora-u

Python framework for defining and running multi-agent applications from YAML. Includes typed worker delegation, permission controls, MCP integration, observability, resumable runs, and a terminal Studio for editing and inspecting workflows.

Use Cases

Build multi-agent applicationsAutomate code reviewsOrchestrate CI/CD workflowsRun resumable agent tasksInspect and repair agent runs

Built With

Language: Python
Frameworks: smolagents · LiteLLM · MCP · Langfuse · OpenTelemetry

AgentLoom

Use Cases

Built With

Tags