Langroid
A lightweight Python framework for multi-agent LLM applications, from CMU and UW-Madison researchers.
Sources and review
Checked against public documentation on . Suitability guidance is our editorial judgment; this is not a performance benchmark or an endorsement.
Developers who want a small, principled multi-agent framework without LangChain.
About Langroid
Langroid, created by researchers from CMU and UW-Madison, lets you set up agents with optional LLMs, vector stores and tools, give them tasks and have them solve problems by exchanging messages, in an actor-inspired multi-agent design. It does not depend on LangChain or other LLM frameworks and works with practically any LLM.
Langroid is listed in this index written primarily in Python, with 4.1k stars on GitHub. Its latest recorded repository push was in November 2026; that is not an ASE editorial review date.
pip install langroidLangroid and related category tools
Alternatives guide →| Record | Stars | Pricing | ||
|---|---|---|---|---|
| Langroidthis listing | 4.1k | Python | MIT | Costs not checked |
| DSPy | 39k | Python | MIT | Costs not checked |
| Mastra | 29k | TypeScript | Apache-2.0 | Costs not checked |
| txtai | 13k | Python | Apache-2.0 | Costs not checked |
| ruflo | 81k | TypeScript | MIT | Costs not checked |
| LlamaIndex | 53k | — | MIT | Costs not checked |
