Nous Research used Hermes Agent to refactor its own codebase. It deployed 1,393 subagents over nineteen active hours. The refactor cut non-test Python by 34.4%. Model spend totaled roughly $19,300. A manual effort was estimated at $150k to $1.8M. The largest file shrank from 34,847 to 5,512 lines. Workers split giant files and consolidated duplicate helpers. Reviewers caught regressions missed by existing tests. Lookup costs for agents fell sharply after the refactor. The team updated Hermes skills with lessons from the run.
What changed
Hermes Agent's codebase had over a million lines of non-test Python, with some files exceeding 34,000 lines.
What it unlocks
Autonomously refactoring large codebases with minimal human oversight.
- 1,393 subagents
- 19 active hours
- 34.4% reduction in non-test Python
- $19,300 model spend
What you need to act on it
- Hermes Agent with accumulated skills
- Claude Fable 5.1 for inference
- 64 GB RAM desktop
Sources