finds.dev

openai/swarm

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

View on GitHub

★ 22,019PythonMITupdated Apr 2026

// the take

Swarm is OpenAI's lightweight, stateless framework for multi-agent orchestration built around two primitives: Agent (instructions + functions) and handoffs (returning another Agent from a function call). It's explicitly labeled educational/experimental and has been superseded by the openai-agents-python SDK for anything production.

The Agent+handoff model is genuinely minimal and easy to reason about — an agent is just instructions plus a function list, and handing off is nothing more than returning a different Agent object from a tool call. Function-to-JSON-schema conversion from type hints and docstrings removes a lot of Chat Completions boilerplate. The examples directory (airline, triage_agent, support_bot) covers real multi-agent patterns like routing and context-variable passing, not just toy demos. Streaming is supported with explicit delim events so you can detect agent switches mid-stream.

The README leads with a deprecation notice pointing to openai-agents-python — this repo is frozen in an educational, non-maintained state, so anyone starting fresh should go there instead. It's stateless between calls by design, meaning you own all persistence, conversation history, and context storage yourself. It's hard-coupled to the OpenAI Chat Completions API with no abstraction for other providers. Error handling is minimal: a failed function call gets appended as an error message for the agent to 'recover gracefully,' but there's no retry, validation, or guardrail layer built in.

We read the README, the directory tree and a key source file in September 2026. Nobody pays to be listed. How we judge →

// at a glance

Stars
22,019
Forks
2,338
Language
Python
License
MIT
Last commit
15 Apr 2026

// nearby

If swarm isn't quite it.

All repos →