Remix.run Logo
Show HN: Mindwalk – Replay coding-agent sessions on a 3D map of your codebase(github.com)
60 points by cosmtrek 5 hours ago | 28 comments
geeewhy 3 minutes ago | parent | next [-]

this is cool! i started tracking file changes across sessions with file hunk method on a binlog.. to see hot paths, or do partial reverts where files werent committed across my sessions. not for visual, but operational for the harness i use. approach lets you see the whole rollups on a period of days or minutes. think there are many use cases where you can run a side agent to check things / progress analyze risky areas as you go etc etcs .. all file change lookups are 3-5ms. script here: https://github.com/geeewhy/haicue-brew/tree/main/scripts

i wonder if i would be able to visualize with mindwalk

fxwin 43 minutes ago | parent | prev | next [-]

Tried exploring a small project i built with CC, but i don't see anything in the tree/terrain view (The edits/reads/writes do show up in the timeline). The project itself doesn't exist on my drive anymore, is that a requirement?

albert_e 8 minutes ago | parent | prev | next [-]

what visualization library is used -- looks cool -- maybe we could adapt it to other use cases that can benefit from a graph visualization

khurs a few seconds ago | parent [-]

This: https://www.npmjs.com/package/three?activeTab=readme

according to packages: https://github.com/cosmtrek/mindwalk/blob/master/web/package...

thunfischtoast an hour ago | parent | prev | next [-]

Haven't tried it yet, but I think we need something in that direction. The terminal "Read file: xyz" mentions are not really followable. It would be nice to easily see where the LLM is taking info from.

cududa 2 hours ago | parent | prev | next [-]

This is really cool! I’m becoming convinced the optimal UI to engage with agents, long term is going to be something spatial. No idea shape that even takes, though I really feel what you’ve made might be Xerox PARC days in terms of metaphor maturity, but there’s some real new seeds of “obvious in retrospect” ideas here. Thanks for conceiving of and building this!

cosmtrek an hour ago | parent [-]

Thanks for your thought!

nokeya 28 minutes ago | parent | prev | next [-]

First thought after reading “3D map of your codebase” was that now we will be able to code in Johnny Mnemonic style :D

freakynit 12 minutes ago | parent | prev | next [-]

This is freakin cool.. worked in first go.

Thanks OP.

Treegarden 42 minutes ago | parent | prev | next [-]

I tested it, history feature is per agent session, a cumulative history of all my agents would be nice.

khalic an hour ago | parent | prev | next [-]

I know I sound childish, but I'm very excited to see our UIs catching up to sci-fi movies. Very cool work, I'll check it out today

bakwan44 an hour ago | parent | prev | next [-]

That's great but im not sure what the use cases are. Did you have something in mind when building this to help the conception process ? I dont feel like i need to know what the agent did, never opened the session json. But there could be gold in there perhaps.

cosmtrek 6 minutes ago | parent | next [-]

My original motivation is to compare the task-solving ability of LLMs by visualizing the agent's trajectory. This offers an alternative way to inspect the capabilities of LLMs and agent systems.

freakynit 11 minutes ago | parent | prev [-]

This can help you evaluate agentic capabilites of various llm's. How they explore codebase.

pshc an hour ago | parent | prev | next [-]

Very glad to see this, I've been dreaming about spatial representations for code for a long time.

rcarmo 2 hours ago | parent | prev | next [-]

Very nice, but needs pi.dev / rcarmo/piclaw support :)

cosmtrek 2 hours ago | parent [-]

Thanks, added to my backlog~

altmanaltman an hour ago | parent | prev | next [-]

This reminds me of that community epsiode where they get the VR system and the dean has to walk through a maze, climb up several things so that they can go to a filing cabinet and then retrive a file. Yes, its cool to see and watch but it seems to be adding more friction than reducing it. Like who is going to spend that much time watching what their agents did when there are far quicker and efficient ways of scanning through changes and organizing code with better ergonomics?

lukan 35 minutes ago | parent [-]

"when there are far quicker and efficient ways of scanning through changes and organizing code with better ergonomics?"

Like what?

altmanaltman 32 minutes ago | parent [-]

Standard CLI version control tools like git diff, git log, or any built-in IDE diff viewer. Scrolling through a text summary of changes is inherently faster and more ergonomic than generating a 3D spatial visualization and watching an agent physically navigate through it.

lukan 19 minutes ago | parent [-]

(Though I disagree, not sure why this comment was flagged? vouched for it)

If you have a big codebase, text diff is not faster to see what was done here and there, then a visual overview. I don't know about this project, but experimented with other tools of this kind and am building one myself. With text diff - you have to parse lots of text and you cannot see on one glance that, oh, these changes are in the rendering, this is DB - and here was done something with the server connection. If done right, I can immediately or very quickly see what was changed - and also decide if the agent (or human) did work in the right spots or gone off track. Now doing this right is not easy, but reading lot's of text is definitely slower then seeing, oh in this area there was a change.

soupspaces an hour ago | parent | prev | next [-]

Sort of like gource?

cosmtrek 9 minutes ago | parent [-]

Wow, it's my first time learning it. The visualization seems similar.

daneel_w an hour ago | parent | prev | next [-]

Completely unrelated, but the name and the visual similarities triggered a memory for me: https://amiga.abime.net/games/view/mind-walker#screenshots

totetsu an hour ago | parent [-]

This would have been a better aesthetic by far.

andai 3 hours ago | parent | prev | next [-]

Nice. Ask your slopservant to make a video, please.

cosmtrek 2 hours ago | parent [-]

Good idea!

alentodorov an hour ago | parent | prev [-]

amazing!