[HN Gopher] Atuin v18.13 - better search, a PTY proxy, and AI fo...
       ___________________________________________________________________
        
       Atuin v18.13 - better search, a PTY proxy, and AI for your shell
        
       Author : cenanozen
       Score  : 82 points
       Date   : 2026-03-21 10:35 UTC (12 hours ago)
        
 (HTM) web link (blog.atuin.sh)
 (TXT) w3m dump (blog.atuin.sh)
        
       | GardenLetter27 wrote:
       | Atuin is great. This, fish, LazyGit, and zellij are mandatory for
       | me now.
        
         | h4ch1 wrote:
         | what does zellij offer that tmux doesn't?
         | 
         | I love tmux and haven't had a reason to switch for a while, but
         | have heard these new Rust based terminal tooling get really
         | popular.
        
           | zenoprax wrote:
           | If all you need is basic splits, sessions, and some simple
           | templates/layouts (and like the convenience of knowing that
           | tmux is widely available, and often installed by default)
           | then you're fine to stay on tmux.
           | 
           | Zellij can do things like floating windows, contextual
           | keybinding guidance (helps learn everything that can be
           | done), and a more complex layout schema. You can disable all
           | the UI eye-candy and switch to tmux-style bindings too.
           | 
           | It's worth trying out. I use both so that I can still
           | function on systems without it.
        
             | wredcoll wrote:
             | Wait, tmux doesn't have floating windows? I really thought
             | it did...
        
           | n8henrie wrote:
           | A ton more conflicting keybindings.
           | 
           | I switched away from tmux a year or so ago due to one crash I
           | kept getting, but thinking of going back. Really miss the
           | simplicity.
        
             | jxdxbx wrote:
             | It's hard to use in so many apps unless you lock the
             | keyboard.
        
           | 0cf8612b2e1e wrote:
           | If you are comparing raw features, there is probably little
           | to differentiate vs a legacy tool. However, the out of the
           | box experience is fantastic, and the author has clearly put a
           | lot of effort in their take without being locked into legacy
           | decisions.
           | 
           | If you watch some of the screencasts and are not impressed,
           | there is nothing more I can do to pitch the idea. My only
           | complaint is that I feel like I am only ever scratching the
           | surface of what the tool can offer.
           | 
           | https://zellij.dev/tutorials/basic-functionality/
        
       | rahimnathwani wrote:
       | Atuin AI sounds like a useful addition. The page suggests they're
       | probably using hosted models:                 We use the latest
       | frontier models, which already do a good job of generating
       | commands using well-known binaries and CLIs. On top of that, we
       | integrate a dataset powered by man pages and command outputs to
       | ensure you get the correct command first.
       | 
       | This is great, but does it mean we'll need to log in somehow? It
       | doesn't seem reasonable to expect the project maintainers to pay
       | for the tokens.
       | 
       | EDIT: I was unaware of Atuin's 'hub' which does things like sync
       | your shell history across computers. I think they use the same
       | sign-in as they already use for that:
       | https://hub.atuin.sh/register
        
         | embedding-shape wrote:
         | This part:
         | 
         | > On top of that, we integrate a dataset powered by man pages
         | and command outputs to ensure you get the correct command
         | first.
         | 
         | Also makes it sound like they're "providing that dataset",
         | rather than generating that from the users computer. Wouldn't
         | that mean it's potentially a mismatch between various versions
         | of the software available? Not to mention some OSes will have a
         | different version of some software available compared to
         | others, how does it deal with those situations if they're
         | shipping a dataset?
        
           | _ache_ wrote:
           | There is no way is it not generated on user computer.
           | 
           | "get the correct command first" and "shipping a [external]
           | dataset" are incompatible.
        
             | anamexis wrote:
             | The Data Privacy paragraph would suggest otherwise.
             | 
             | > By default, Atuin AI knows nothing about your machine,
             | other than the operating system and shell. This is the bare
             | minimum required to generate a decent shell command.
             | 
             | > It will soon be able to ask you for access to more data -
             | such as the current directory path, contents, git status,
             | etc - but you must give permission first. This will happen
             | in a similar way to existing agents, and be configurable to
             | an even finer degree in your config file.
        
       | lta wrote:
       | Why does every tool on the face of earth try to add AI features ?
       | Good tools are simple and orthogonal. If you want AI, there's
       | already plenty of other tools doing it probably better.
       | 
       | I'm overall fairly disappointed by this announcement. This IMHO
       | doesn't bode well
        
         | Bnjoroge wrote:
         | It's fine - I like the introduction of AI. It's optional - if
         | you don't want it, turn it off or don't use it
        
         | righthand wrote:
         | AI features are the new Electron app. Welcome to the new hell,
         | please finish installing your 10 different inference engines,
         | one for each app.
        
         | qudat wrote:
         | If you want VC money you need to put an AI spin on it.
        
           | tootie wrote:
           | Product is free, open source and largely written and
           | maintained by one person. Doesn't seem like a startup payday
           | scheme.
        
       | dc_giant wrote:
       | Hmm might be great for some. I'm a Unix philosophy guy, one tool
       | for one job. So far atuin was fine to be a better search history.
       | Now it might be time to look for simpler alternative. Any
       | suggestions? (I'm on zsh)
        
         | justech wrote:
         | I tried atuin and then switched back to fzf[0]. It's less
         | features but that's not necessarily a negative.
         | 
         | [0]https://github.com/junegunn/fzf
        
           | kstrauser wrote:
           | Fzf doesn't let you sync your shell history, though. I self-
           | host an Atuin server so that I can share that history across
           | my various machines.
        
             | doubled112 wrote:
             | I also self host my own atuin server. It's great.
             | 
             | I didn't think syncing terminal history would be very
             | useful until I tried it, but now I have a hard time when I
             | don't have it.
        
               | kstrauser wrote:
               | That was my experience. "Huh, what was that complicate
               | thing I did on the database server?"
               | 
               | I have its search bound to ^r and use Fish shell's own
               | search for most things, with cross-machine search a
               | keystroke away.
        
             | stevekemp wrote:
             | To be honest I find the things I do on my "work" laptop are
             | different to the things I do on my "personal" laptop, and
             | different again to what I do on my desktop machine.
             | 
             | Regardless of which machine I'm using at any given moment I
             | appreciate having "endless history", and the ability to
             | search/filter it. But despite that I don't think I need to
             | actual sync that.
             | 
             | I'm sure there is value to be had from syncing and making
             | all history unified, but it's never appealed to me
             | particularly.
        
             | justech wrote:
             | Yeah, that's part of the "less features" I mentioned. I
             | don't get any value from syncing shell history, but I can
             | see why it's useful for some.
        
           | dc_giant wrote:
           | Yup already using fzf for other things will probably just go
           | back for search history too.
        
           | prashantv wrote:
           | I personally prefer the fzf UX, but I liked atuin's better
           | tracking of history and sync abilities so I combined them:
           | https://github.com/prashantv/atuin-fzf
        
         | grosswait wrote:
         | AI appears to be opt in
        
         | anamexis wrote:
         | I have to ask -- why? Atuin has not gotten any worse at its
         | core history search functionality. All of the new features are
         | entirely opt-in. Why switch?
        
           | dc_giant wrote:
           | Because to me it feels like it gets more complex in ways I
           | don't like. It's a matter of preference. To be honest had I
           | not read about it I might have never noticed it but now I
           | know and will probably go back to fzf.
        
         | dcre wrote:
         | What here takes them over the complexity threshold?
        
         | hakcermani wrote:
         | not zsh .. plugging my bash script [1] (and gnome task bar UI)
         | - to start a gnome terminal with a different named history
         | file. [1]: https://github.com/appsmatics/gtsh-hist
        
         | quinncom wrote:
         | You can try McFly [1] and Television [2]. I still prefer fzf.
         | 
         | [1] https://github.com/cantino/mcfly
         | 
         | [2] https://github.com/alexpasmantier/television
        
       | colesantiago wrote:
       | As soon as a tool adds pricing, price increases or adds AI that's
       | when it begins to be enshittified.
       | 
       | Why does this happen mostly?
        
         | evandrofisico wrote:
         | Yep, out of precaution i've never used their sync
         | infrastructure, which I guess was reasonably cheap to run, but
         | the moment you add LLMs to the mix it is obvious that they are
         | in for the free VC money and are soon going to need a lot of
         | investment to keep the lights on.
        
           | mijoharas wrote:
           | The thing I found frustrating was I wanted to merge changes
           | with just files without their sync server (i.e. just import
           | this other atuin sqlite dB) so I raised a PR to support that.
           | 
           | They closed it (which is fine) but there is no offline
           | migrate alternative.
           | 
           | It's a shame, and fair enough, their project, but I don't
           | think my wishes and the projects are very aligned.
           | 
           | I keep half meaning to move back to zsh-histdb (I think
           | that's what it was called) but haven't found an impetus to.
           | 
           | I'll probably check if there's a file based sync option next
           | time I switch machines and decide then.
        
             | wswope wrote:
             | > They closed it (which is fine) but there is no offline
             | migrate alternative.
             | 
             | If it helps, you can copy the history table from one db to
             | another in 3 simple lines of sqlite. I've done it myself a
             | few times with zero fuss.
        
           | ilvez wrote:
           | It's MIT licensed software, Noone will turn off lights.
           | Community can take over or fork.
        
       | mpalmer wrote:
       | I was already turned off by their decision to remove support for
       | fzf, which I use everywhere else. I'm done.
        
         | ellieh wrote:
         | I'm not sure what you mean here - we never supported fzf, other
         | than a super early prototype in like 2021
         | 
         | This release actually adds support for nucleo, which matches
         | with the same algorithm as fzf and was a common request
        
           | evandrofisico wrote:
           | About the "ai", the announcement is very vague. Is this
           | incorporating a local model on device, something running on
           | your infrastructure or a third party model like Claude?
           | Because to me nowadays adding AI on anything usually means
           | higher running costs equals sooner or latter
           | enshittification.
        
           | mpalmer wrote:
           | Hey, thanks for responding. I guess I used the prototype
           | then. Definitely don't remember anyone saying "this is a
           | prototype" at the time, so I took the product at face value,
           | and part of the reason I chose it was the fzf support.
           | 
           | I'm sure I recall some unhappy GitHub issues about the shift
           | away...
           | 
           | And the algorithm isn't the value prop for me, not by a long
           | shot. fzf's customizability takes the cake. And now the
           | overall product is way too big and feature-ful for me. I want
           | simple, unix-y software that clicks together like Lego.
           | 
           | You should be proud of the project's success for sure, it's
           | just not for me!
        
       | duskdozer wrote:
       | I was really pleased finding this last year, but I guess it's
       | time to look for an alternative. I don't get why everything has
       | to have AI shoved into it
        
         | Bnjoroge wrote:
         | It's optional- you can choose to opt in or not.
        
           | ramon156 wrote:
           | Its also the Repo. There's a lot of AI-guided commits. I'm
           | all for using AI in a reliable and safe environment, but
           | letting Claude steer just leads to garbage
        
             | stingraycharles wrote:
             | I took a look at the repo, but i didn't see any garbage
             | commits / evidence of sloppy vibe coding.
             | 
             | Care to elaborate? Also, don't you trust that an author
             | knows what they're doing with AI in the same way as
             | trusting them with their regular code writing skills?
        
             | Bnjoroge wrote:
             | I've read and used some of the author's software. I trust
             | them to make good judgement of using AI.
        
             | quanwinn wrote:
             | Using AI to code doesn't automatically mean bad code.
             | Although I suspect the majority of AI code will be subpar.
        
             | TechSquidTV wrote:
             | So to be clear. You have no tangible complaints about the
             | software or its quality, but you are dismissing it because
             | of the potential for poor quality, because AI was
             | assisting?
        
           | imiric wrote:
           | That's a poor argument that doesn't change the fact that any
           | feature requires maintenance time and effort which for some
           | users could be better invested in features they actually use,
           | in improving overall stability, reliability, performance,
           | etc. The more such unused features a product has, the less
           | relevant it is for those users.
           | 
           | The question is, was adding "AI" to this product requested by
           | most users, or was it done to tick off a marketing checkbox
           | and capitalize on the hype?
        
             | wswope wrote:
             | What stability, reliability, and performance problems are
             | you hitting with Atuin?
             | 
             | I posted a longer comment upthread, but I've been self-
             | hosting and running an old version for over two years now,
             | and haven't had any recurring problems on those fronts.
             | It's pretty damn stable software and everything they've
             | been doing lately has just been extra features and gloss.
        
             | jauntywundrkind wrote:
             | It's open source software, so this attitude of "the work
             | hours have to be spent how I want them to be spent" feels
             | rather icky to me.
             | 
             | There's also a very weak souled scarcity mentality. It
             | feels like you are working to take umbrage, to come up with
             | outrage. Some users do find these features good and useful.
             | That should be celebrated. Demanding features _not_ be
             | present? That 's so condescending.
        
               | imiric wrote:
               | OSS is not immune to enshittification, and, in fact, is
               | prone to it. It's not entitled to have the opinion that a
               | piece of software might be heading in the wrong
               | direction. Paying for software doesn't somehow buy you
               | this right. What's icky to me is the idea that the
               | opinion of users who support the author financially is
               | more valuable than of those who don't, which goes against
               | the entire ideal of open source.
               | 
               | Besides, VC-funded OSS often prioritizes the needs of its
               | shareholders rather than its users. If you find these
               | features useful, that's great. But there's no reason that
               | they should be universally celebrated. The authors might
               | want to listen to all viewpoints.
        
               | cweagans wrote:
               | "I want this feature" and "I want this feature to not
               | exist" are fundamentally incompatible viewpoints when
               | applied to any given feature. It seems like adding that
               | feature and making it opt-in is a good middle ground. The
               | people that want it can have it and the people who don't
               | want it can pretend it doesn't exist. This outcome seems
               | like the result of listening to all viewpoints, so I'm
               | not sure what problem you're trying to point out.
        
             | Bnjoroge wrote:
             | Atuin is open source. You dont like their new release? Fork
             | the previous repo, and customize it however you want.
             | That's the whole essence of open source.
        
         | arcadianalpaca wrote:
         | Right, though looking at the release notes it seems like the AI
         | part at least is opt-in... for now.
        
           | duskdozer wrote:
           | For now. But looking at the repo, they're already having
           | commits done by claude.
        
             | dcre wrote:
             | I looked at the repo and couldn't even find an example, so
             | it can't be that many of their commits. But also: this is
             | ridiculous. Whether the commit appears as done by Claude or
             | not is a setting you can change. If they turned it off,
             | you'd never even notice.
             | 
             | These are great developers and they've built an incredible
             | tool. I use it a hundred times a day. It is very odd and
             | dogmatic to think that because you saw a commit authored by
             | Claude, whatever skills and qualities let them build
             | something so good are now being thrown out.
             | 
             | Edit: I found one:
             | https://github.com/atuinsh/atuin/pull/3231
             | 
             | Please, tell me where the bad code is in that PR. I see 200
             | lines of extremely straightforward Rust and 500 lines of
             | tests for it.
        
             | baq wrote:
             | And this is bad why?
        
         | wswope wrote:
         | Not to detract from your point, but I decided Atuin was feature
         | complete enough for my liking over two years ago, and have been
         | running the last v17 release ever since with zero problems.
         | 
         | You can still keep everything you like about the tool without
         | issue, and to the devs' credit, the sync server is some of the
         | easiest software to self-host possible.
        
       | theusus wrote:
       | All I want is auto complete for the commands on Windows. And none
       | provides
        
         | imiric wrote:
         | Take a look at clink[1]. Or use PowerShell.
         | 
         | [1]: https://chrisant996.github.io/clink/
        
           | theusus wrote:
           | I do use powershell but it doesn't provide auto complete for
           | commands. I repeat I don't want history. I want commands or
           | args suggestions. Just like zsh auto complete
        
       | Myzel394 wrote:
       | I'm still looking forward to being able to only remember a
       | command for a specific time. I currently block sensitive
       | commands, which completely destroys the ability to just press the
       | up arrow key to quickly edit the command. If we had like a
       | timeout of 1 minute for sensitive commands, we could edit them
       | and still make sure they are not persistent
        
         | BinaryMuse wrote:
         | I really like this idea -- might give an implementation a shot
        
         | skulk wrote:
         | zsh doesn't add commands that start with a space to stored
         | history. So you can up arrow recall them but once you exit the
         | session they're gone.
        
       | semiquaver wrote:
       | I'm baffled by how bitter and angry the comments are. Atuin is
       | one of my favorite everyday tools and this release sounds great!
        
       | Myzel394 wrote:
       | atuin ai kinda reminds me of https://github.com/Myzel394/zsh-
       | copilot (yes, that's by me :P)
        
         | anamexis wrote:
         | And reminds me of my take: https://github.com/micahbf/halp
         | 
         | Excited to use atuin ai though, especially as it gets more
         | features.
        
           | breuleux wrote:
           | And my take! A fork of fish where any command that starts
           | with > or a capital letter is fed to $fish_llm_command:
           | https://github.com/breuleux/fish-shell. With Claude's help,
           | that took all of 30 minutes to make.
        
       | thehours wrote:
       | The PTY proxy looks pretty neat! Excited to give that a try.
       | 
       | Losing some of the scrollback was a minor nuisance that I kind of
       | lived with until now.
        
         | ilvez wrote:
         | I've always felt this fullscreen was too much for actual use.
         | Eager to try it out.
        
         | thehours wrote:
         | Update: I gave it a try and it does exactly what I hoped.
         | However one (minor) annoyance I immediately realized was that
         | with `hex` enabled I will get this warning whenever I close the
         | terminal window:
         | 
         | > The terminal still has a running process. If you close the
         | terminal the process will be killed.
         | 
         | Hopefully there is a workaround for this (I'm using then
         | Ghostty emulator).
        
       | jauntywundrkind wrote:
       | Release notes have PR #'s but they aren't links. Would be great
       | to linkify, so folks can more easily dive into bits that catch
       | their eye.
        
       | fragmede wrote:
       | I had Claude write me fundcli, which goes over your atuin shell
       | history and suggests places to donate to.
       | 
       | https://github.com/fragmede/fundcli
        
       ___________________________________________________________________
       (page generated 2026-03-21 23:01 UTC)