redai-infra/Relax

An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

These files are redai-infra/Relax's own configuration. They tell Claude Code, OpenCode and Codex 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.

Open on GitHub redai-infra.github.io

580Stars on the repository

8Files it configures its agents with

2,533Tokens loaded in every session

3Agents configured

Instructions

Relax AGENTS.md AGENTS.md A 1,627 tok
Relax CLAUDE.md CLAUDE.md A 906 tok

Commands

commit .opencode/commands/commit.md A 7 tok

Agents

algorithm-expert .opencode/agents/algorithm-expert.md A 37 tok
fsdp-expert .opencode/agents/fsdp-expert.md A 38 tok
launcher-expert .opencode/agents/launcher-expert.md A 38 tok
megatron-expert .opencode/agents/megatron-expert.md A 29 tok
ray-expert .opencode/agents/ray-expert.md A 56 tok