Hands-on with Apodex 1.1: changing requirements mid-run reorganizes the multi-agent task board

mhdfaran · x · 2026-09-09

The author stress-tested Apodex 1.1 with a heavy task: comparing 8 self-hostable open-weight models (no GPT/Claude/Gemini) on a single 24GB GPU across license, min VRAM at Q4/Q8, tokens/s, coding vs long-form writing, and rent-vs-buy GPU cost, outputting a ranked table, CSV, and a one-page chart.

Apodex split the task into subtasks with multiple agents researching in parallel, all visible on a Task Board. When the author changed requirements mid-run, it didn't just rewrite the answer — it reorganized the work behind it, marking the difference from ordinary deep research.

Original post →

More from coding & agent

coding & agent channel →