Can this be related to the cache TTL drop they did??

Comments URL: https://news.ycombinator.com/item?id=47765103

Points: 2

# Comments: 3

Comments URL: https://news.ycombinator.com/item?id=47466199

Points: 1

# Comments: 1

Points: 27

# Comments: 7

agentd gives agents a persistent remote shell. One connection, stateful commands. cd works. Env vars stick. No daemon on the remote, no new ports, just SSH underneath.

Written in Go. Also ships as a Claude Code plugin.

But it's also a full standalone CLI, interactive inbox with j/k navigation, inline compose with a multiline editor, search, archive, star, trash. Sends clean HTML so emails look normal.

The reason I built it: Resend just dropped their CLI and I realized there's no modern Gmail CLI. The existing npm package is 8 years old and dead.

npm install -g @mrprincerawat/gmail-cli

Uses your own Google Cloud OAuth. Tokens stay on your machine.

Comments URL: https://news.ycombinator.com/item?id=47277099

Points: 5

# Comments: 0

when everyone around you is shipping in hours what used to take weeks, the pressure to keep up changes how you approach things. you know the answer is one prompt away. that changes your brain. it's like saying you can still use a paper map when GPS exists, technically true, but you won't, and you know it.

the post isn't about going back. it's about acknowledging that something shifted in how we learn by building.

Today I told Claude to fine-tune an LLM on my X posts. Prompt to finished model with a web UI in 30 minutes. I was impressed and unsatisfied at the same time. I achieved my goal but learned nothing — I don't even know which libraries it used.

I'm not anti-AI. I use it for everything now. But the old way of writing software — the googling, the failed experiments, being stuck on a bug for days — that's where the actual learning happened. Every feature forced you to understand the codebase, read docs, weigh tradeoffs.

I just wish the 14-year-old me had something left to figure out on his own.

Link to the full article: https://open.substack.com/pub/princerawat/p/software-in-the-age-of-ai?r=yts8r&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true

Comments URL: https://news.ycombinator.com/item?id=47261989

Points: 1

# Comments: 8

kanly is the opposite of a framework. you write plain python functions. you define an agent with one api call. you trigger runs from webhooks or cron or wherever. the llm loop runs on the server and your tools execute on your machine over websocket.

whatever you want to build you just write the handler functions for it. bug fixer, deploy bot, alert triage at 3am. kanly just runs the loop and calls your code.

the only real design decision was that the llm should never directly execute anything. every tool call goes through a runtime on your machine. cli commands can require human approval before running. credentials never leave your infra.

2k lines of python. mit licensed. works with any openai compatible model.

Comments URL: https://news.ycombinator.com/item?id=47251011

Points: 2

# Comments: 1

For small projects, the existing options felt like overkill (vaults, external services, team setup), so I wanted something that:

- keeps the .env workflow intact - doesn’t depend on any external service - is simple enough that I’d actually use it every time

Dotlock just encrypts your .env with a passphrase so it’s safe to commit, and lets you decrypt it locally when needed.

I’m sure there are tools in this space (git-crypt, sops, etc.), so I’m curious where this feels redundant vs actually useful — especially for solo devs / small teams.

Would love honest feedback.

Comments URL: https://news.ycombinator.com/item?id=47126105

Points: 1

# Comments: 2