ARAgentRanks
~ / stacks / hermes-agent-llama-4-maverick

Hermes Agent + Llama 4 Maverick

A CLI agent plus open/open-weight coding model stack for skills-based terminal experimentation.

ARscore 24.21M context$0.8/$2.2fully open
AgentHermes Agent
ModelLlama 4 Maverick
Agent score39
Model SWE-bench62%
Combined score24.2
Best fitskills-based terminal experimentation

Related Hermes Agent stacks

Same agent, different model choices.

Hermes Agent + DeepSeek V4 Pro

ARscore 31.4, 1M context, $0.44/$0.87

view stack

Hermes Agent + DeepSeek V4 Flash

ARscore 30.8, 1M context, $0.14/$0.28

view stack

Related Llama 4 Maverick stacks

Same model, different agent wrappers.

Cline + Llama 4 Maverick

ARscore 37.8, Extension workflow

view stack

Aider + Llama 4 Maverick

ARscore 37.2, CLI workflow

view stack

Goose + Llama 4 Maverick

ARscore 26.7, CLI workflow

view stack

Replit Agent + Llama 4 Maverick

ARscore 21.1, Browser workflow

view stack