Spawning appropriate subagents.
Can you recommend an agent configuration using these free models—Cerebras (8B/70B/120B, Qwen 32B/235B, GLM 4.7), Groq (8B/70B, Scout/Maverick 17B), Mistral (small/medium/large/codestral/ministral/magistral), OpenCode (MiniMax M2.5/M2.1, GLM 4.7, Kimi K2.5, GPT-5 Nano, Big Pickle)—to offload routine tasks from Opus 4.6 via spawning/delegation, while strictly maintaining output quality. Can you instruct me on how to do this?
The AI that actually does things. Emails, calendar, home automation - all from your favorite chat app. New shell, ready to help. The lobster way.
134,426Members
Resources
Recent Announcements
Similar Threads
Was this page helpful?
