Hacker News: doshayhttps://news.ycombinator.com/user?id=doshayHacker News RSShttps://hnrss.org/hnrss v2.1.1Mon, 18 May 2026 09:11:26 +0000<![CDATA[New comment by doshay in "Show HN: Git for AI Agents"]]>cool approach, i havent used jj actually in my workflow, ill try to adopt

]]>Sat, 09 May 2026 15:44:45 +0000https://news.ycombinator.com/item?id=48075875doshayhttps://news.ycombinator.com/item?id=48075875https://news.ycombinator.com/item?id=48075875<![CDATA[New comment by doshay in "Show HN: Git for AI Agents"]]>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...

]]>Sat, 09 May 2026 14:05:28 +0000https://news.ycombinator.com/item?id=48075095doshayhttps://news.ycombinator.com/item?id=48075095https://news.ycombinator.com/item?id=48075095<![CDATA[New comment by doshay in "Show HN: Git for AI Agents"]]>i think you misunderstood the concept, actually . it's not built to replace git, rather to sit on top of it.

]]>Sat, 09 May 2026 13:58:18 +0000https://news.ycombinator.com/item?id=48075033doshayhttps://news.ycombinator.com/item?id=48075033https://news.ycombinator.com/item?id=48075033<![CDATA[New comment by doshay in "Show HN: Git for AI Agents"]]>https://github.com/regent-vcs/re_gent

]]>Sat, 09 May 2026 13:57:25 +0000https://news.ycombinator.com/item?id=48075023doshayhttps://news.ycombinator.com/item?id=48075023https://news.ycombinator.com/item?id=48075023<![CDATA[New comment by doshay in "Show HN: Git for AI Agents"]]>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..

]]>Sat, 09 May 2026 13:57:12 +0000https://news.ycombinator.com/item?id=48075022doshayhttps://news.ycombinator.com/item?id=48075022https://news.ycombinator.com/item?id=48075022<![CDATA[New comment by doshay in "Show HN: Git for AI Agents"]]>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 :)

]]>Sat, 09 May 2026 13:55:23 +0000https://news.ycombinator.com/item?id=48075002doshayhttps://news.ycombinator.com/item?id=48075002https://news.ycombinator.com/item?id=48075002<![CDATA[New comment by doshay in "Show HN: Git for AI Agents"]]>thanks! will do

]]>Sat, 09 May 2026 13:54:38 +0000https://news.ycombinator.com/item?id=48074999doshayhttps://news.ycombinator.com/item?id=48074999https://news.ycombinator.com/item?id=48074999<![CDATA[New comment by doshay in "Show HN: Git for AI Agents"]]>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 :)

]]>Sat, 09 May 2026 13:53:44 +0000https://news.ycombinator.com/item?id=48074995doshayhttps://news.ycombinator.com/item?id=48074995https://news.ycombinator.com/item?id=48074995<![CDATA[New comment by doshay in "Show HN: Git for AI Agents"]]>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

]]>Sat, 09 May 2026 13:51:49 +0000https://news.ycombinator.com/item?id=48074986doshayhttps://news.ycombinator.com/item?id=48074986https://news.ycombinator.com/item?id=48074986<![CDATA[New comment by doshay in "Show HN: Git for AI Agents"]]>super nice, indeed similar approach

]]>Sat, 09 May 2026 13:50:02 +0000https://news.ycombinator.com/item?id=48074971doshayhttps://news.ycombinator.com/item?id=48074971https://news.ycombinator.com/item?id=48074971<![CDATA[New comment by doshay in "Show HN: Git for AI Agents"]]>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)

]]>Sat, 09 May 2026 13:48:50 +0000https://news.ycombinator.com/item?id=48074956doshayhttps://news.ycombinator.com/item?id=48074956https://news.ycombinator.com/item?id=48074956<![CDATA[New comment by doshay in "Show HN: Git for AI Agents"]]>absolutely right, i got this feedback from many people actually ...

]]>Sat, 09 May 2026 13:46:59 +0000https://news.ycombinator.com/item?id=48074933doshayhttps://news.ycombinator.com/item?id=48074933https://news.ycombinator.com/item?id=48074933<![CDATA[New comment by doshay in "Show HN: Git for AI Agents"]]>- 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.

]]>Sat, 09 May 2026 13:46:19 +0000https://news.ycombinator.com/item?id=48074928doshayhttps://news.ycombinator.com/item?id=48074928https://news.ycombinator.com/item?id=48074928<![CDATA[New comment by doshay in "Show HN: Git for AI Agents"]]>tnx for the honest feedback! really, appreciate it! would you mine sharing more details about your workflow with jj?

]]>Sat, 09 May 2026 13:45:25 +0000https://news.ycombinator.com/item?id=48074924doshayhttps://news.ycombinator.com/item?id=48074924https://news.ycombinator.com/item?id=48074924<![CDATA[Show HN: Git for AI Agents]]>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.

Comments URL: https://news.ycombinator.com/item?id=48063548

Points: 129

# Comments: 68

]]>Fri, 08 May 2026 14:15:36 +0000https://github.com/regent-vcs/re_gentdoshayhttps://news.ycombinator.com/item?id=48063548https://news.ycombinator.com/item?id=48063548<![CDATA[Show HN: Git for AI Agents]]>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.

Comments URL: https://news.ycombinator.com/item?id=48049431

Points: 5

# Comments: 0

]]>Thu, 07 May 2026 13:49:05 +0000https://github.com/regent-vcs/re_gentdoshayhttps://news.ycombinator.com/item?id=48049431https://news.ycombinator.com/item?id=48049431<![CDATA[Make your software arch context-ready]]>Article URL: https://www.shaylivni.com/blog/make-architecture-context-queryable

Comments URL: https://news.ycombinator.com/item?id=48005657

Points: 3

# Comments: 0

]]>Mon, 04 May 2026 07:21:01 +0000https://www.shaylivni.com/blog/make-architecture-context-queryabledoshayhttps://news.ycombinator.com/item?id=48005657https://news.ycombinator.com/item?id=48005657