marin-community/marin

Open-source framework for the research and development of foundation models.

About the project

Marin is an open-source research program, software platform, and community for developing foundation models such as large language models. Researchers use it for data preparation, tokenization, pretraining, posttraining, evaluation, and related experiments, including work on audio-text, DNA, and protein models. The catalogue entries are add-ons that support workflows around Marin.

These files are marin-community/marin's own configuration. They tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.

3,444Stars on the repository
45Files it configures its agents with
2,883Tokens loaded in every session
3Agents configured

Instructions

Settings

Skills

Agents