Building a pit crew for Grok Bot: frontier model plans, free models grind
alexcovo_eth · x · 2026-10-10
A user shares their multi-agent setup around Grok Bot (nicknamed Ricky Bobby):
- Cal: a Hermes Agent running on the Grok Bot's own always-on VM (via SuperGrok sub), taking long jobs like research, drafts and renders;
- Clef (Cloudflare): a classifier on the VM that checks text against user-set rules in under half a second for a fraction of a penny, flagging issues and leaving final calls to the human;
- Walker: a helper on a Nous Portal subscription using free/cheap models for summaries, cleanup and first drafts, with a cheap paid backup and a hard spending cap — total cost so far: half a cent.
The lesson: don't put your smartest model on every job. The frontier model plans and judges, a cheap decision model checks, and free models do the routine work.
More from coding & agent
- Cerebral Valley and Crusoe host Recursive Agents Hackathon with $25K in prizes — PolarBearby · 2026-10-10
- PM with Claude Code finds potential exoplanet after 74 adversarial analyses — sujingshen · 2026-10-10
- Open-source agent Comma runs 24/7, handling email, Linear and Notion tasks for you — HeyAmit_ · 2026-10-10
- Andrew Ng releases 1-hour course on building agentic knowledge graphs from scratch — nikola_mr64990 · 2026-10-10
- Mnemos: an engram-inspired memory architecture doubles short-term recall vs Claude's native memory — RileyRalmuto · 2026-10-10
- LLM reliability #6-7: guardrails, fallbacks, and production monitoring — goyalshaliniuk · 2026-10-10