Running Multiple AI Agents in the CLI
kevinnbass · x · 2026-07-13
The author shares their workflow of using **Grok 4.5 / Fable 5 almost entirely within the command line**: - Asking questions in only a few sessions - Having the model refactor architectures, fix bugs, scaffold, and create new metrics - Monitoring progress via multiple agents running 24/7 - Managing these agents like regular programs without needing to see most outputs This treats the models more like continuously running engineering assistants rather than conversational chat tools.
More from coding & agent
- Codex turns out 123 screensavers in one playful batch — intellectronica · 2026-07-21
- Grok Build adds `grok doctor`, resumable sessions and remote image paste — mark_k · 2026-07-21
- Autoresearch proposes packaging ML runs as studies with questions, analysis, and code diffs — morgymcg · 2026-07-21
- CHAP defines approvals, handoffs, and audit logs for human-agent workflows — DeliveryTechnical199 · 2026-07-21
- The author says Codex reached 20x and is now debugging spec decoding on a hybrid parallel setup — TheZachMueller · 2026-07-21
- Axcess adds an MCP connector for WCAG accessibility checks that scanners miss — modelcontextprotocol · 2026-07-21