Hacker News: kannanpoem1984

New comment by kannanpoem1984 in "How I use LLMs to learn complex topics"

kannanpoem1984 — Mon, 10 Aug 2026 07:36:57 +0000

This is cool project !

New comment by kannanpoem1984 in "Ask HN: What are you working on? (August 2026)"

kannanpoem1984 — Sun, 09 Aug 2026 18:54:51 +0000

I have been working on couple of open source projects related to package intelligence and AI tooling.

https://secchi.dev Secchi is Open Source Package Intelligence | python based

https://tuffcli.dev tuff is Capability lifecycle manager for coding agents | rust based

Both would be very helpful to be part of developer tooling. I built package intelligence when I need to monitor the downloads of my other personal project packages from package manager.

I have learned a lot over in terms of rust language, design patterns in rust, also how the ecosystem of AI capabilities within projects use cases and needs

That sounds interesting, give star to repo :D

Open source emojis for designers, developers and everyone else

kannanpoem1984 — Sun, 09 Aug 2026 18:48:50 +0000

Article URL: https://openmoji.org

Comments URL: https://news.ycombinator.com/item?id=49234351

Points: 2

# Comments: 0

New comment by kannanpoem1984 in "Show HN: Secchi – Package intelligence in your terminal"

kannanpoem1984 — Fri, 07 Aug 2026 20:56:32 +0000

When I was working on a couple of open-source projects and publishing them to different package managers like PyPI, crates.io, and Homebrew, I was curious to see if anyone was downloading them and what the adoption looked like. It was a pain to go to each package manager and look for statistics.

That's when I decided to build a simple TUI dashboard for package intelligence. I wanted it to go beyond basic package details and gradually become more of an engineer's tool for understanding open-source packages.

While developing it, I started seeing a broader use case like integrating it with coding agents through MCP and providing this metadata about open-source packages, so agents can make package suggestions based on actual data points rather than just what they already know.

I'm still exploring where this could go and would be interested to hear what signals you look at when evaluating an open-source package.