跳过导航
AgentFS copy-on-write overlay in action 🔥
0:00 / 0:27

AgentFS copy-on-write overlay in action 🔥

Pekka Enberg

@penberg2万 位关注者

在 X 上查看
744 个赞下载原帖

62,741 次观看

AgentFS copy-on-write overlay in action 🔥 Multiple AI agents working on the same codebase. Each with isolated changes, zero conflicts. Host files stay untouched.

38 条评论

评论来自 X (Twitter) 上的原帖

  • Pekka Enberg 的头像

    @penberg

    Thanks to @jussisaur for explaining how to make Claude Code do animations.

    18 个赞

  • Tommy D. Rossi 的头像

    @__morse

    really cool! how much performance overhead does it add? how much longer would a command like npm install take?

    4 个赞

  • Pekka Enberg 的头像

    @penberg

    For example, ”npx create-react-app” takes 3x longer with agentfs compared to native xfs, but it’s just lack of async which should be fixable. That said, I use agentfs to build agentfs and don’t really notice any slowdown because agents usually work in parallel in the background

    4 个赞

  • Tommy D. Rossi 的头像

    @__morse

    it will be great to see performance improve as Turso is optimized more. do you think it will ever be faster than a real filesystem? using eventual consistency tricks like waiting on read and making writes instant?

  • Fernando 的头像

    @Principal_ADE

    hopefully ill have time to visualize this sometime this week I really like this concept

    3 个赞

  • Roger Johansson 的头像

    @RogerAlsing

    From a practical PoV, how is this different than GIT worktrees?

    3 个赞

  • Anayat 的头像

    @anayatkhan09

    AgentFS is such a nice middle ground between agents on prod and messy git worktrees. Curious how you are thinking about surfacing and merging the best overlay back once 5 agents diverge hard on the same feature.

    3 个赞

  • Pekka Enberg 的头像

    @penberg

    That's a great question! The agent needs to coordinate this because is such a use cases specific thing. However, I think we need an "agentfs apply" (easy) or "agentfs merge" (much harder) commands to assist in the merging of the delta layer to the base filesystem. But figuring out which overlay is best I think is purely agent stuff (we might need some nicer tooling to audit the overlay of course).

    1 个赞

  • Oleksandr Erm 的头像

    @ErmOleksandr

    sounds like a recipe for disaster. git branches/worktrees are simply superior it would be very easy to end up with both agents having broken code that all the time. What happens later, would it merge session files back into host filesystem once done?

    2 个赞

  • Pekka Enberg 的头像

    @penberg

    Nothing happens later unless you explicitly want something to happen. The way i use it is by making the agents push to git remote branch which means the agents never know about each other

    2 个赞

  • Oleksandr Erm 的头像

    @ErmOleksandr

    I can imagine case when multiple agents start at the same time: A1: edits file (F1) that refers to another non existent yet function in pre-existing file (F2) A2: meanwhile A2 has already made changes in F2 so it has its own copy, and starts modifying F1 for its own purpose, ending up with reference to non existing function A2 probably will simply invent variant of that function in this case, but still it is problematic. Nevertheless, I can as well imagine many use cases where AgentFS would work great. Great work, keep it up.

    1 个赞

  • Pekka Enberg 的头像

    @penberg

    Hey @ErmOleksandr! Does git worktree solve this problem somehow? Perhaps I misunderstand the example, but, sure, multiple agents can make semantically different interpretations of a function, but that's inherent if they work in parallel? (Humans can make this mistake too.)

    1 个赞

  • Oleksandr Erm 的头像

    @ErmOleksandr

    I agree with you. The key difference is that with worktrees, the agents aren’t stepping on each other in real time. And to be clear: my comment comes from experience and a lot of frustration. Since ChatGPT came out, I’ve been trying to move toward a fully AI-driven software creation workflow. At this point I can ship full features end-to-end: polished UI and user journeys, docs, blog posts, screenshots, landing and product pages, draft legal updates, tests, and security reviews, all while keeping code quality high. That works great when I do one thing at a time. The moment I try to run work in parallel, it falls apart. On large changes, merge conflicts across 20k+ lines can eat so much time that it’s often more efficient to switch and build something unrelated instead of untangling the merge. When I saw your approach, I was hoping it could at least reduce that pain.

    1 个赞

  • Sean 的头像

    @xujihui1985

    I saw the fuse implementation now, that’s impressive, must have a try

    2 个赞

  • Pekka Enberg 的头像

    @penberg

    Let me know if you have any issues with it!

  • Brian Cheung 的头像

    @justBCheung

    Very cool! Requires agents to use sdk though?

    1 个赞

  • Pekka Enberg 的头像

    @penberg

    No, there’s an ”agentfs” tool you can use for transparent sandboxing

  • Marc-André Moreau 的头像

    @awakecoding

    Does it work on Windows? I understand it's always trickier to implement nice filesystem tricks in Windows than on other platforms

    1 个赞

  • Pekka Enberg 的头像

    @penberg

    Not yet. I am unsure what is the right path is btw. NFS might work, but I read somewhere that it requires Windows Pro or something…

    1 个赞

  • Marc-André Moreau 的头像

    @awakecoding

    I understand agentfs is using FUSE on Linux?

    1 个赞