comchangs

Joined 4 years ago

Karma

Submissions

Member since

Jan 17

CEO & Founder at neurosam.AI (https://neurosam.ai). Building AI robots and deployment tools. Creator of Tow (https://github.com/neurosamAI/tow-cli). Previously shipped production systems across multiple companies.

View on Hacker News

Recent submissions

Comment · 7 months ago

This is the kind of thing that's completely useless and I absolutely love it. Bookmarked.

Comment · 7 months ago

The persistent memory at ~/.nanopm/memory/ is clever. Having context survive across sessions is what makes this actually usable vs a one-shot prompt.

We did something similar with deployment presets in our CLI — saving frequently used server/module combinations so you don't re-specify them every time. The "memory layer" pattern seems to be emerging across all dev tooling.

Comment · 7 months ago

Tried it on a few repos — the file-tier prioritization is a nice touch. Skipping lockfiles and generated code saves a lot of noise.

Would be interesting to see this integrated into CI — auto-generate updated diagrams on each PR so architecture docs never go stale.

Comment · 7 months ago

Nice. The LLM authoring angle is underappreciated — getting an AI to write valid MJML is painful, but Markdown is trivial.

One thing I'd love: a CLI mode so I can pipe it into deployment notification hooks. Something like `echo "Deploy succeeded" | emailmd | sendmail` would be killer for DevOps workflows.