About this project
A hands-on, runnable reference for the many ways to coordinate LLM agents.
What it is
“Multi-agent” gets used as one word, but there are many distinct ways to coordinate agents — and they behave very differently. This is a place to feel the differences: run the same task through each architecture, watch the live agent timeline, inspect every tool call and message in the debug stream, and compare cost. It’s a teaching tool and a reference implementation in one.
Agentic AI moves fast — new patterns, frameworks, and papers land every week. The goal here is a living reference: a single place to learn the coordination patterns by running them, with the research and source for each one a click away.
How to use it
- 1Open the app, pick an architecture (v1–v9), and a model from any of the four providers.
- 2Send a task and watch the agents reason, call tools, and message each other live.
- 3Run the same task through a different pattern and compare the result, the path, and the cost.
It’s a public demo — bring your own OpenAI, Anthropic, Mistral, or Fireworks key in Settings. Keys stay in your browser and are never stored on the server.
Contributions welcome
Know a pattern, paper, or framework that belongs here? Add it — open a PR with a new architecture or a reference, or file an issue. The patterns are data-driven, so adding one is mostly a new runner + a mode entry.