Process Manager for Autonomous AI Agents | Hacker News Reader

Process Manager for Autonomous AI Agents

botctl.dev

58 pointsankitg1222 comments

I can see you're A/B testing some different hero text.

I got:

> Write a config, not a conversation

Which I found let me wondering - "What is this thing?" I refreshed a few times to the variations, and while some were better, I feel like your hero could do with being less pithy, and more plain explanation of what it is.

So I'm the creator of botctl which I created to satisfy my personal need for running many agents on a cron style loop. The whole premise is you don't need to be there to chat with the agent for it to do it's job.

I'm definitely not A/B testing anything, it just cycles through a couple titles I thought conveyed the project well. The sub-title directly under it explains it pretty clearly, would you agree with that?

> Manage persistent AI bots with a terminal dashboard, web UI, and declarative configuration.

There's also an interactive emulation of the TUI directly next to both titles in the hero.

In case anyone is interested, agentic platform I have been working on for awhile.

https://kern-ai.com/

Thanks for sharing, I think it's kind of a different type of system although a lot of similarities for sure.

I made botctl explicitly to not have to talk to my agents, I wanted them running autonomously based on their BOT.md file's prompt / goals / skills.

Can you give any more details about this, why we might be compelled to try it out?

https://kern-ai.com/blog/why-your-agent-needs-one-session

This was my main motivation to create this

looks pretty cool, but as all AI landing pages do, it suffers from not enough contrast. you might want to lighten the darker text shades ;)

Thanks for the feedback, I'll do that! I think different screens and system settings affect this a lot, on all the devices I've looked at the site on I felt it was quite comfortable to read, not to discount your experience, I'll keep that in mind for the future as well.

Looks handy for anyone wanting fully autonomous agents without babysitting them—declarative config over constant chat seems like a smart move.

It gets really fun when you prompt them to update their BOT.md, also they get access to previous run results so they continually "learn" from mistakes or investigate changes.

why are there so many autonomous ai agent orchestration systems? too much! I don't understand! Please explain

What is there not to understand? AI is booming right now. People are trying to get in on the gold rush and/or trying to sell pick axes to the miners. There is a ton of fertile ground for anyone that wants to try something, so it's being explored.

People want to build something with the newfound productivity, but it turns out that software development always had a high leverage against potential impact - coding was always relatively cheap. That means there is in fact no backlog of great products that could have been built if we only had 10x productivity. The only spots where "missing products" can be found are mostly around AI itself.

I'll take a counterpoint, coding has historically not been cheap. Software engineers have been one of the highest paid professions for a long time. Personally while working a full time job, raising a family and trying to have some semblance of a social life my open source contributions fell off a cliff until recently with the popularization of coding agents. I've created more projects and software in the last 12 months than the past 10 years combined. Not to say a lot of it wasn't total slop or provided little utility, but it's been a fun and exciting time.

Another interesting point is that until recently most average people thought "code" was out of reach or they didn't have time / energy to learn it. My mother made a webapp with the help of claude code the other day to generate books, which she thought of and completed in the course of 3 days all the while learning about terminals, localhost, ports, APIs and more.

IMHO the reason is because engineers can write software but not always solve real problems. It is just easier to put stuff in code to do things with computers. This is the comfort zone. But coming up with something that solves a valuable end-user problem requires understanding what this is.

I've been through this thought process many times and I am still struggling (you can check my profile as to why).

You can try as well.

What are the best applications for AI automation?

> What are the best applications for AI automation?

A robot that walks round cleaning your house and he never gets tired and he can go the shops and do what you want and repairs his self

> What are the best applications for AI automation?

Sex bots

I wish we all collectively worked on one project, especially on an orchestrator tool, where the groundwork is important. people can build on it whatever they want, just dont re-invent the orchestrator!

Here's two popular open-source projects that have combined 200k+ stars and 1,300+ contributors, with slightly different goals:

- https://github.com/anomalyco/opencodeagents

- https://github.com/OpenHands/OpenHands

It’s what the cool kids are doing these days. It’ll pass. Also it’s quite fun to build things around agents and watch them go off to work.

I think there's also something about being able to make it exactly how you want. For example I didn't like openclaw, I felt it was extremely over-engineered and I honestly couldn't even get it running on my first attempt. So I made botctl to be a generalized version where it doesn't rely on complex setup and have every bell and whistle, you just install it, create a directory with a BOT.md file and off it goes.

i think there is a real gap though. autonomous agent are actually very useful and powerful but has huge potential for great damage. proper harnesses are indeed needed to either contain potential damage like sandbox or provide interface for human to actually supervise and intervene.

Reply on news.ycombinator.com