If you haven’t tried it, I highly recommend Mise. It manages everything at the user level so it’s not as “all encompassing” as Nix and is readily compatible with immutable distros.
Your solution is akin to putting your dotfiles in the code repo, which is going to cause issues with languages with poor version compatibility (such as node and python) when switching between old projects.
Also, bold of you to assume developers know make and bash just because they’re using Linux!
I cannot endorse mise more highly. I commit it to my repos to make sure every engineer has the same environment. I use it in CI for consistency there as well. I keep all commands that would normally be documented in a readme as mise tasks. I use mise to load the environment, independent of language specific tools like dotenv. I use a gitignored mise.local to put real creds into the environment for testing.
Five years ago, I would've loved this. I love the simplicity and power of good old Make. And I obsess over my workstation's configuration. I used to have a massive bash script I would use to reprovision my workstation after every clean upgrade of Ubuntu.
But these days, I just tell codex to install things for me. I basically use it as a universal package manager. It's more reliable honestly than trying to keep up to date with "what's the current recommended way to install this package?"
I also have it keep a list of packages I have installed, which is synced to GitHub every time the list changes.
I recently used clause code to help me learn nix + home-manager!
For anyone considering it - it’s been fun, genuinely useful in my day to day, and I can’t recommend it enough - I now have a source controlled tool kit that I can take with me anywhere I go
I agree. I started with Nix flakes in my project and fell in love with them. Then I started using Home Manager, and now I feel complete. I even played with nix-darwin and NixOS. It's an amazing piece of software.
I’ve gotten used to it and with LLM it’s easier to set up the config without learning all the obscure syntax but on macOS it’s still a very un-native feeling compared to home brew. Having to sudo all the time feels weird for just updating user space apps and configs.
I codify all my AI install/setup/running junk (https://codeberg.org/mutablecc/ai-agent-coding) with Makefiles. You can make DRY Makefiles real easy, reuse them, override settings, without the fancy stuff in the author's post. The more you build up a reusable Makefile, the easier everything gets. But at the same time: don't be afraid to write a one-off, three-line, do-almost-nothing Makefile. If it's so simple it seems stupid, it's probably just right.
The main difference is I initially only needed a mechanism to check if my "Manually-Installed or Source -Compiled" (MISC) packages have updates, but now it also supports install/upgrading too.
In other words, things I am forced to do by hand outside of a package manager, I now only do by hand once, save it as an 'install' script, and then incorporate it into this system for future use and to check for updates. Pretty happy with it.
pixi init && pixi add wget
And youre ready to go, everything confined to the venv within the directory
Something like:
And then you can list tools : ANd run them:https://mise.jdx.dev/
Your solution is akin to putting your dotfiles in the code repo, which is going to cause issues with languages with poor version compatibility (such as node and python) when switching between old projects.
Also, bold of you to assume developers know make and bash just because they’re using Linux!
This means that getting a project in shape for development on a new system looks like this:
- clone project
- `mise run setup`
I have zero dev tools on my host, projects are 100% self-contained.
Pure bliss.
See https://github.com/dx-tooling/sitebuilder-webapp for an example.
For example there's also the GitHub backend which lets you install binaries from releases, no plugin needed at all.
But these days, I just tell codex to install things for me. I basically use it as a universal package manager. It's more reliable honestly than trying to keep up to date with "what's the current recommended way to install this package?"
I also have it keep a list of packages I have installed, which is synced to GitHub every time the list changes.
The main difference is I initially only needed a mechanism to check if my "Manually-Installed or Source -Compiled" (MISC) packages have updates, but now it also supports install/upgrading too.
In other words, things I am forced to do by hand outside of a package manager, I now only do by hand once, save it as an 'install' script, and then incorporate it into this system for future use and to check for updates. Pretty happy with it.