doshay

proof you can do amazing things with only html (and some <script> tags :)

Nice direction !

Just curious, how can Deliberate exactly identify the options the agent faced? and what do you consider an "option"? sometimes it can be vauge (say the agent decided to explore this way and not that way, would that be considered an option?)

anyway, i like seeing tools like that! good luck

seems like the link is not attached :X

it means using coding agents (cc) is allowed? anyway, nice idea. will give it a try

cool approach, i havent used jj actually in my workflow, ill try to adopt

sure, fair question i think the main difference is that entire are built on top of git == you would have to commit in order to track something...

i think you misunderstood the concept, actually . it's not built to replace git, rather to sit on top of it.

that's exactly what i tried in the first place, but i think it would be misuse of git protocol, git is built for files - the blobs/ tree calc & mechanism , for large contexts and linear thinking flow it's differnt, but honestly - i think you can get to a very good solution with pure git..

at the moment only Claude Code, i'm planning to add support for the other big 3, but at the moment it's just me ... hopefully in the near future :)

thanks! will do

cool!

actually not at the moment - would be nice to add it. i think the core of re_gent allows it very naturally, feel free to push it if want :)

exactly, imo - the llm should touch git only after explicit approval or after specific set of guardrails. this one of the reasons i built it actually, i think the agent workflow should be decoupled from git, until saving the code

super nice, indeed similar approach

but then you would have to commit each tool and action of the agents, which is polluting the git history and also huge overhead (at least imo)

absolutely right, i got this feedback from many people actually ...

- hopefully after a /compact. - what happens if want to undo, and then redo? i found the /rewind functionality in claude very lean in that matter.

tnx for the honest feedback! really, appreciate it! would you mine sharing more details about your workflow with jj?

hi guys.

been working on something i think is fundamentally missing in today's workflow with ai agents.

vcs.

i find myself struggling with questions that agents can't answer like "why did you do it?", "when did u delete this folder? why?", etc. or trying to /rewind (after a /compact...) or basically `bisect` to find when and why something was done by the agent in the current / previous session.

just like git did for code, i think we are the same core capabilities with ai agents

so...

i developed an open source solution for that (currently supporting claude code)

would love to get feedback, contribution or maybe other ideas or solutions you find for those problems.