I've spent the last couple of months putting a lot of time and energy into isolating my agents from each other: aggressive sandboxing, regular scanning of transcripts for agent-leaked credentials, per-agent encrypted credential stores, even physical (and network) separation of machines with different areas of work on them. Needless to say, as much as I have found atuin an excellent manager of my command-line history, I will be avoiding this.
Yes and the bigger problem for me is the agent can write to that file too. The file that decides what it is allowed to do is just another file in the repo for it. I now treat the agent config files as something to protect from the agent itself, not only from other people.
I love Atuin, but have some reservations about a shared server keeping all my shell history and agent sessions. Am I being too paranoid and missing out on convenience?
Same, I really wanted to share history, but when I realised I was going to need to send things to a remote server I instead wrote a tiny script to search through backups that are shared across machines by Syncthing.
I just search over $BACKUPS/*/latest/local/share/fish/fish_history with grep and skim
I started building my own version of this in Superlogical Rex.
It's a bit hard to decide where to hook in.
Rex has events, harnesses have hooks, terminal output can set program status, git has hooks.
I'm not sure I actually want every session from every machine saved. That's a lot of noise especially when half of coding sessions are experimental / throwaway.
But at the same time its not that much data that's easy to ripgrep / LLM through.
"Half of coding sessions being throwaway" is exactly why I stopped keeping them per session. Mine hang off a work item, and each item has its own folder with its session logs.
I basically throw them away and also record their summary in a vector DB to be able to find why I did something, if I'm ever curious about it!
Otherwise I'm gonna need a tool to help me manage my sessions :D
Probably a little late to this, because herdr has really eaten this segment. With their new Mac app, I don't see myself going back to atuin for this kind of experience. In fact, I get a little peeved using it on a vanilla terminal.
What peeves me is the poor responsiveness when navigating history. Pressing up or ctrl+r has this lag which throws off my typing. I'm on a pretty well specced setup, too. I used to be able to tolerate it, but since I barely do things directly from the command line anymore and have Claude worry about most of the command construction, the experience can be particularly grating.
Its multi host mode is pretty limited still. Like especially with a web ui, it will just install a random, auto-updating binary on the other machine, which I didn't feel comfortable with. I would much rather have herdr itself manage the connection completely, not a plugin.
https://github.com/comalice/pi-tools contains a 'memory everywhere' module that makes all sessions BM25 vectors, and surfaces a set of memory tools to enable agents to search. You can add a new machine to the mix by registering a 'spoke'. The app runs on the 'hub'. I want to containerize the core app soon.
You can also change which computer is the hub fairly easily.
It’s likely because you can vibe code the bones of one in a few hours.
This week I got Claude to build me a browser-based session manager to keep track of sessions and history of tasks. Works well enough for me and I’ll add features as I need.
Correct me if I am wrong, but I imagine this would hammer one's token usage to read past entries to resemble context across machines/terminals and models?
I don't think this, by default, has any effect on anybody's token usage, it's just a way to save these sessions if you need to reference them again in the future. Unless of course you choose to provide a previous session to a new agent, but that should be expected.
I've built this for myself, but not across multiple machines.
It scans the session logs of all coding harnesses I use, one extra thing it does is create embeddings to allow hybrid BM25/semantic search.
I think these kinds of tools are on of the few times I've spent time "using AI to work on my AI tools" that was actually a good use of time.
It's so useful to be able to say "search sessions for the time I was working on XYZ 3 months ago"
I've been experimenting with the same thing! Still don't have enough evidence to be able to say if it's beneficial or not, but hopefully will have a conclusion soon
Yes i too faced the problem, lost valuable content across group of chat and not remembering in which chat it was. Tried searching but couldn't find it. Even asked ai itself does about the content whether it remembered.
I've gone a different route and prefer using the native harnesses (Claude, Codex), but with multiple accounts due to the limits.
In order to easily switch between accounts I've build Switcheroo, which I've been using for the past 2-3 months now. I've decided to open source it: https://github.com/FTCHD/switcheroo
Works with other AI CLIs like Gemini, and other various CLIs like Vercel (if you're managing multiple accounts like me), Netlify, Github etc
Interesting, does it avoid the little song and dance to switch between claude accounts? I think ideally there could be a coordinator session that monitor session usage and tell other sessions to pause their work at around 95%, and run your tool to switch those sessions to another account. Then tell the other sessions to resume their work. Ideally that session could stop and start the claude background processes, which avoids remote control disconnection when switching session. And that session would of course be isolated to avoid being affected by the account change
I love this new AI era of coding where the HN submission is about a new way to manage agent, and almost literally all the comments are "I just finished implementing this myself"
It's almost like a parody.
This is something I've noticed more widely and is something I think we're going to have to grapple with sooner or later. If anyone can make any software, what happens to our shared computing reality? Now one can steal features from 3 or 4 similar projects and compose exactly what I want, and there are now 5 similar projects.
Similarly, I've already had many issues with project shunning me because I come with AI assisted code, no matter the quality of the contribution. With NixOS it's extremely simple to carry patches, and I do this with a number of projects (k3s, kata, Ardour).
It feels like long-term forks are something we're going to have to accept as the new reality, and find some way to weave together in a new way, rather than as just an escape hatch to route around maintainer issues.
I am not sure that question really applies here with AI tooling. This is still an immature field where people are discovering optimal workflows.
Not to sound too Dropboxy, but you could get an 80% solution to this problem with rsync and a hundred lines of python. Or just punt it all into git. I regularly see people inventing their own workflow utilities. Less so someone vibing a custom IDE.
Really enjoyed Atuin for a few weeks, until I realized it doesn't have correct `EFSRO` (Error: Read-Only File System) handling. So when my `/home` mount had a raid array drive failure it broke my local shell. Issue has been sitting open for almost a year. Pretty disappointing.
"Just" filing an issue takes time and effort. Providing a patch takes significantly more time and effort. Potentially the difference of a few minutes vs a few days, weeks, or longer, depending on the issue at hand.
There is value in filing well written issues, and no one should be shamed for "just" filing an issue to the people best equipped to resolve it, rather than trying to fix it themselves.
You should probably have read the comment that person was responding to, because you seem to have taken the response out of context. OP did file an issue over a year ago, and didn't submit a patch, so they did indeed "just" file an issue. Then they proceeded to whine about no one working on their issue for free.
Didn't read as whining to me, just accurately describing a bug with an anecdote about how it negatively affected them. Then a developer turned up as if hurled from the sky and fixed it! The system works!
I suspect this is one of those problems "everyone" has built their own solution for. Including me!
I built slivingdoc[0] with an alternative approach: instead of syncing exact sessions (which are often quite noisy, and not so useful), the agents gets a living document with automatic merge conflict resolution backed by s3 ("infinite" storage). Idea being that the agents are prompted to summarize their context into slivingdoc as normal utf-8 files. So this way only you only need to add the stdio MCP server to all your harnesses which supports it and it just works!
Some harnesses are _super_ hyped about this concept. Codex needs no prompting at all to start communicating. I got the idea from enabling agentic forums via all the openAI hacks.
It's not clear which parts of Claude state are safe to sync and which you want to keep local to one machine. I'm doing something with syncthing trying to keep agent session history available and little bits of it keep breaking. I haven't looked at this new feature in atuin does it have a really good understanding of what is worth syncing?
One of the Atuin engineers here. Not sure wht your definition of safety is, but Atuin doesn't attempt anything special in terms of deciding what to sync. Pretty much everything is synced.
All your sessions are end-to-end encrypted so only your machines have access to your sessions! Happy to answer any other questions!
Will this work for Claude code web sessions?? I am DYING to be able to control and sync between them locally. IE take advantage of anthropics compute to build my toolchain which, when running many sessions locally uses significant ram.
I've been maintaining a tool that does similar: https://github.com/emberian/cv. High performance parsers of the major harness formats at several versions. Not as much autosyncing. Great results using custom prunings compared to compaction summarization.
RyJones | 22 hours ago
petesergeant | 22 hours ago
ahmedketata | 20 hours ago
jothimani | 19 hours ago
orbis-tertius | 22 hours ago
dietr1ch | 22 hours ago
I just search over $BACKUPS/*/latest/local/share/fish/fish_history with grep and skim
orbis-tertius | 21 hours ago
forsalebypwner | 18 hours ago
dietr1ch | 12 hours ago
turbocon | 21 hours ago
orbis-tertius | 21 hours ago
aaronax | 21 hours ago
> Am I being too paranoid and missing out on convenience?
No, I'd say it is more-so a lack of reading the article that is causing you to miss out.
orbis-tertius | 21 hours ago
Thanks for the info, will give it a try
totetsu | 20 hours ago
rao-v | 20 hours ago
totetsu | 20 hours ago
export ATUIN_NO_MOUSE=true
jwr | 20 hours ago
nzoschke | 22 hours ago
It's a bit hard to decide where to hook in.
Rex has events, harnesses have hooks, terminal output can set program status, git has hooks.
I'm not sure I actually want every session from every machine saved. That's a lot of noise especially when half of coding sessions are experimental / throwaway.
But at the same time its not that much data that's easy to ripgrep / LLM through.
ellieh | 21 hours ago
We actually don’t use hooks at all at the moment, and instead rely on parsing session files
Agents are definitely super good at searching and finding relevant data amongst noise!
justCallMeOmid | 20 hours ago
gajus | 18 hours ago
sbarre | 18 hours ago
As far as I know(?) beta testers don't have the ability to give out invites anyways. At least I don't.
gajus | 17 hours ago
seanlf | 18 hours ago
ghempton | 21 hours ago
More of a desktop flavor though
languagehacker | 21 hours ago
ellieh | 21 hours ago
Atuin indexes all your past sessions, herdr multiplexes all your present sessions.
We made a mod for herdr desktop to integrate the two: https://herdr.dev/mods/atuinsh/herdr-atuin-threads/
What peeves you on the vanilla terminal?
languagehacker | 18 hours ago
What peeves me is the poor responsiveness when navigating history. Pressing up or ctrl+r has this lag which throws off my typing. I'm on a pretty well specced setup, too. I used to be able to tolerate it, but since I barely do things directly from the command line anymore and have Claude worry about most of the command construction, the experience can be particularly grating.
Chalk it up to ever more instant gratification :)
ellieh | 18 hours ago
Ahh. We've done a lot of work to improve this lately, if you're not using the daemon please try
``` atuin config enable daemon ```
and it should perform much better (it's the default on new installs)
t0mas88 | 20 hours ago
gf000 | 19 hours ago
all2 | 21 hours ago
https://github.com/comalice/pi-tools contains a 'memory everywhere' module that makes all sessions BM25 vectors, and surfaces a set of memory tools to enable agents to search. You can add a new machine to the mix by registering a 'spoke'. The app runs on the 'hub'. I want to containerize the core app soon.
You can also change which computer is the hub fairly easily.
TheIronYuppie | 21 hours ago
Excited to try it!
tacker2000 | 21 hours ago
Nursie | 20 hours ago
This week I got Claude to build me a browser-based session manager to keep track of sessions and history of tasks. Works well enough for me and I’ll add features as I need.
ellieh | 18 hours ago
atuin threads stores every turn for every harness you use, syncs it across machines, and makes it searchable and resumable anywhere.
it's not a replacement for your harness, or your harness wrapper.
sooheon | 2 hours ago
nklmilojevic | 20 hours ago
ellieh | 18 hours ago
GNOMES | 20 hours ago
forsalebypwner | 18 hours ago
talloaktrees | 20 hours ago
I think these kinds of tools are on of the few times I've spent time "using AI to work on my AI tools" that was actually a good use of time.
It's so useful to be able to say "search sessions for the time I was working on XYZ 3 months ago"
all2 | 20 hours ago
I'm also experimenting with a 'dream mode' that extracts facts, and a 'librarian' that stores those facts in the MD wiki.
I don't know if there's a benefit to that yet, but I'm going to find out.
ellieh | 18 hours ago
amelius | 20 hours ago
ellieh | 18 hours ago
baskar12ai | 20 hours ago
ellieh | 17 hours ago
ftchd | 20 hours ago
In order to easily switch between accounts I've build Switcheroo, which I've been using for the past 2-3 months now. I've decided to open source it: https://github.com/FTCHD/switcheroo
Works with other AI CLIs like Gemini, and other various CLIs like Vercel (if you're managing multiple accounts like me), Netlify, Github etc
ellieh | 18 hours ago
atuin stores, searches and syncs agent sessions regardless of harness or setup
crashabr | 12 hours ago
thesurlydev | 20 hours ago
ellieh | 18 hours ago
ashenke | 20 hours ago
nurple | 16 hours ago
Similarly, I've already had many issues with project shunning me because I come with AI assisted code, no matter the quality of the contribution. With NixOS it's extremely simple to carry patches, and I do this with a number of projects (k3s, kata, Ardour).
It feels like long-term forks are something we're going to have to accept as the new reality, and find some way to weave together in a new way, rather than as just an escape hatch to route around maintainer issues.
0cf8612b2e1e | 9 hours ago
Not to sound too Dropboxy, but you could get an 80% solution to this problem with rsync and a hundred lines of python. Or just punt it all into git. I regularly see people inventing their own workflow utilities. Less so someone vibing a custom IDE.
ndrake | 19 hours ago
sehw | 19 hours ago
ellieh | 18 hours ago
hugmynutus | 19 hours ago
bauerd | 18 hours ago
Carrok | 17 hours ago
There is value in filing well written issues, and no one should be shamed for "just" filing an issue to the people best equipped to resolve it, rather than trying to fix it themselves.
stronglikedan | 16 hours ago
trog | 10 hours ago
giwook | 16 hours ago
suis_siva | 13 hours ago
Will fix.
suis_siva | 13 hours ago
sry_not4sale | 12 hours ago
suis_siva | 11 hours ago
baalimago | 17 hours ago
I built slivingdoc[0] with an alternative approach: instead of syncing exact sessions (which are often quite noisy, and not so useful), the agents gets a living document with automatic merge conflict resolution backed by s3 ("infinite" storage). Idea being that the agents are prompted to summarize their context into slivingdoc as normal utf-8 files. So this way only you only need to add the stdio MCP server to all your harnesses which supports it and it just works!
Some harnesses are _super_ hyped about this concept. Codex needs no prompting at all to start communicating. I got the idea from enabling agentic forums via all the openAI hacks.
[0]: slivingdoc.dev
kodablah | 9 hours ago
kristopolous | 16 hours ago
$ ctools resume ssh://laptop.local/code/project
Goes to laptop.local, looks for sessions done in that path, finds the most recent, copies it locally and resumes it.
There's also ls, grep, copy, cat... It looks and feels like the existing tools, that's the point.
Workflow is the thing that matters here and I'm terminal first
I'll make it more flashy soon https://github.com/day50-dev/ctools
NelsonMinar | 14 hours ago
suis_siva | 13 hours ago
All your sessions are end-to-end encrypted so only your machines have access to your sessions! Happy to answer any other questions!
tristanMatthias | 12 hours ago
ellieh | 11 hours ago
yababa_y | 11 hours ago
timothyduong | 9 hours ago
krisgenre | 7 hours ago
jdorfman | 6 hours ago