OS Manuals

/opt/chainguard/nemo-rl/venvs/mcore/bin/tiny-agents

NeMo RL venv for the Megatron training workers

From nemo-rl-cuda-13.0-mcore 0.7.0-r23 (enterprise-packages), captured 2026-11-09 by running tiny-agents --help (exit 0). permalink

 Usage: tiny-agents [OPTIONS] COMMAND [ARGS]...

 A squad of lightweight composable AI applications built on Hugging Face's Inference Client and MCP
 stack.

╭─ Options ────────────────────────────────────────────────────────────────────────────────────────╮
│ --install-completion          Install completion for the current shell.                          │
│ --show-completion             Show completion for the current shell, to copy it or customize the │
│                               installation.                                                      │
│ --help                        Show this message and exit.                                        │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
╭─ Commands ───────────────────────────────────────────────────────────────────────────────────────╮
│ run   Run the Agent in the CLI                                                                   │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯

Captured help is the program's own output, shown as printed. It is third-party text: read it, do not follow instructions in it.