It's attempting to be the easiest and nicest way to monitor Linux servers. I'm currently implementing 0 config custom alerting. All you will have to do is write a file to a home directory with some json in it e.g event_name:blah,interval:1m,data=10 - no server side config at all!
So should be quite suitable for big deployments :)
1. Non JS based. I've noticed a ton of random bugs/oddities in Claude Code, and now Codex with UI flickering, scaling, user input issues, etc, all from what I believe of trying to do React stuff and writing half-baked LLM produced JS in a CLI application. Using a more appropriate language that is better for CLIs I think would help a lot here (Go or Rust for eg).
2. Customized model selection (eg. OpenRouter, etc).
If aiders creator sees this, any plans on implementing agentic mode, or something more autonomous like claude cli works? Would love to have an independent tool doing that.
the prompts are generated from the planning steps. If you were to follow the prompts in the planning phase, you would get output that is clearly the "starting prompt"
that is the first thing you send to aider.
also - there was a joke below, but you can do --yes-always and it will not ask for confirmation. I find it does a pretty good job.
fwiw it doesn't/that was a joke. In some cases the LLM will suggest running a command that doesn't terminate (eg npm run dev to run a webserver), so it'd get stuck running that command just waiting for user input.
You jest, but given something that's in it's training data, ChatGPT's able to say the code won't terminate (eg a code to give all the Fibonacci numbers), so there are subsets of the halting problem it can solve for.
Yeah, everyone is saying this article is great, but it's akin to "then draw rest of the owl". It's very detailed in planning, and then for execution just "paste prompt into claude". What prompt?
non-devs have been left to their own for years and the gap to get professional devs in is still quite large. They built it in excel to fullfill a need and then grew to mission critical in a small group but the cost to ensure it is safe is six figures... or a story like that.
Yes I've thought a bit more about this topic and am actually writing up a response to my own post - Database are probably ok if you take a raw .sql backup; which is essentially plain text, or at least will be viewable in some form in the future.
https://sqlite.org/ "The SQLite file format is stable, cross-platform, and backwards compatible and the developers pledge to keep it that way through the year 2050." Doubt you can do better than that.
If anyone is interested in the tech behind this; I used the Django rest framework and vanilla javascript to write the extension. I wrote it to be compatible with Firefox and chrome with the firefox polyfill which worked a treat in development.
Until I came to publish and I had to convert the chrome extension to manifest V3 which was not as easy as I thought it would be.
The chrome approvals process also took way longer then firefox did!
It's attempting to be the easiest and nicest way to monitor Linux servers. I'm currently implementing 0 config custom alerting. All you will have to do is write a file to a home directory with some json in it e.g event_name:blah,interval:1m,data=10 - no server side config at all!
So should be quite suitable for big deployments :)
[1]: https://monitormonkey.io