Apodex 1.1 rebuilds deep research around files, method selection and verifiable conclusions

mhdfaran · x · 2026-09-09

The author explains the design idea behind Apodex 1.1: instead of the classic question → research → report deep-research pipeline, it organizes work as files → inspection → method selection → execution → outputs → verifiable conclusion, with recovery when something changes or fails mid-run. The demo task: ranking 8 self-hostable open-weight models on a single 24GB GPU across license, VRAM at Q4/Q8, speed, coding vs writing quality, and rent-vs-buy cost.

Original post →

More from coding & agent

coding & agent channel →