Nous cut its codebase by 34% in 19 hours using 1,393 subagents
In a run with Hermes Agent, source lines fell from 1,063,826 to 698,363, a drop of 34.4%. Logs from September 2-3 show 478 delegation batches, 1,652 subagent tasks and 111,352 tool calls. The work is reported as behavior-neutral. The claim that it saved roughly $2 million in engineering hours is the company’s own estimate.
Sources
- Nous Research, “Refactoring Hermes with 1,393 agents”, (nousresearch.com)
- GitHub (NousResearch/hermes-agent), “refactor: whole-codebase simplification — −34% source LOC, every god file decomposed, zero behavior change”, (github.com)
About this story
This story was posted on Instagram by @jarrus.tech on Sept. 23, 2026.
Spotted an error in this story? [email protected] · Instagram
Short link: thejarrus.com/en/nous-codebase
This story in Turkish: Nous, 1.393 alt ajanla 19 saatte kod tabanını yüzde 34 küçülttü
On the same topic
Robot tests: even the best model completed only 19% of 84 robot tasks, and 63 tasks were solved by no model
In RobotWorld, a benchmark released October 7, the top model, GPT-6 Astra, completed only 16 of 84 simulated robot tasks; no model solved 63 of the tasks.
OpenAI’s image model posts a near-perfect score on text-dense images
On UltraText Bench, a dense-text test led by Westlake University, OpenAI’s GPT Image 2 ranked first of 24 configurations with 99.35 out of 100.
HackerRank’s AI interviewer opens to all customers after more than 500,000 job interviews
HackerRank made its AI interviewer Chakra generally available to customers on October 5, after a roughly six-month beta with more than 500,000 interviews.