LightfieldAI-native CRM that builds itself and does work for you
Inventory
Search every AI Agent & IDE Conversation
99 followers
Search every AI Agent & IDE Conversation
99 followers
Inventory is your private spotlight for every Cursor, Claude Code, Zed, Codex and Kiro conversation. No signups, no cloud, one-time fee.
The local-only decision is the interesting one. I've got two years of Cursor and Claude Code history sitting in places I can't search, and the reason I've never tried a cloud tool for it is that those conversations contain client context I'm not willing to upload.
Two things I'd want to know: does it index historical conversations or only from install onwards? And when a tool changes its local storage format in an update, how much breaks?
Second one matters because that's the failure mode for anything indexing someone else's files, and it's the thing I'd need to trust before paying a one-time fee.
Upvoted, saw your five in Nika's thread, which is how I found this.
Inventory
@fasathor Hello, thank you for the agreeing with my decision of local-one. To answer both of your questions
Firstly Yes it indexed Historical, all of it. If one tool breaks it localstorage that tool's index will stop working for now. This is first public release and this concern i also had on which i am working on finding a solution that will work local only. I am hoping in next update i will try to solve that problem first as its on top of my checklist.
Thank you again for pointing this out.
@xshahneil Makes sense, and honestly "it breaks until I ship a fix" is the right answer for a first release - better than pretending it's solved. Good luck with it. I'll keep an eye out for the update
Inventory
@fasathor Sure, join the waitlist so once the update dropped. Will drop you and email.
Inventory
@xshahneil That was fast. Joining the waitlist now, I'll put it against two years of Cursor and Claude Code history and tell you what breaks.
Inventory
@fasathor https://www.myinventory.site/changelog
@xshahneil Read the changelog - the self-repair on next launch is the part I'd have missed. Not recording a failed parse as read is a neat solution.
That failure mode is one I need to handle too, on the extraction side. A parser returning nothing and a document genuinely having nothing are very different things, and they're easy to conflate.
Will report back once I've run it against my history.
no cloud is a real answer to one worry but it kind of creates a smaller version of the same problem: right now my secrets and half-finished thoughts are scattered across five separate tools' storage, which is annoying but also means no single file on disk is that valuable. an index of literally every agent and IDE conversation in one place, searchable, is a much juicier single target for anything else running on the machine. is the index itself encrypted at rest, or is it plain text once it's built?
Inventory
@galdayan Thank you for pointing this out. Currently I just ran strings on my own index before answering and real conversation text comes straight back, no decryption needed.
As a solo dev with nobody in my own circle running five AI tools the way I do, this first release was about finding out whether the problem is real for anyone else before building everything around it. Now that it's out and people are using it, this is exactly the kind of gap worth fixing properly rather than guessing at in advance.
The plan for 1.0.2: move the index onto SQLCipher instead of plain SQLite, with the encryption key generated once per machine and held in the macOS Keychain rather than the database file. Full-text search keeps working the same as it does today. SQLCipher decrypts pages transparently at runtime, but the file on disk is opaque to anything that doesn't have Keychain access, including a copied backup or another account on the same Mac.
And because the index is already fully rebuilt from your tools' own files on disk, losing or rotating that key in the future just means a one-time reindex, not lost data.
If you have more inputs do let me know, happy to learn and improve. Thanks again and do share a word if you have people who can use this tool.
Inventory
@galdayan https://www.myinventory.site/security 1.0.2 shipped and your concerned has been addressed. Thanks
@xshahneil that was fast, nice work. keychain-held key plus opaque file on disk is exactly the right shape for this, a stolen backup or synced drive won't hand someone your whole tool history. appreciate you actually shipping it instead of just noting it for later
Inventory
@galdayan Thank you, if you want i can give you an access to the product and you can use, if you like it you can share a word among your circle :)
This is a real gap for teams, not just individuals. Half the useful context in my company now lives in one-off chats nobody can find two weeks later. Does Inventory work across a team's conversations with permissions, or is it scoped to a single person's history for now?
Inventory
@artem_fedorovich for now it is focused towards individuals like me, as using multiple tool i was not able to find chats. Hence build this which is simple, local and easy to use.
But the use case which you told is excellent and i have noted it down. I will plan to implement it next release.
Would appreciate a share with your friends or colleague who uses multiple agents and have this same concern. Thanks
Inventory
Hey Product Hunters 👋
I'm Neil, maker of Inventory.
What inspired me to build this
I kept losing conversations. Not because I deleted them. Just because they pile up across Cursor, Claude Code, Zed, Codex, Kiro... and there's no way to search any of it.
I'd vaguely remember solving something in a session from two weeks ago. Which tool was it in? Which project? No idea. So I'd spend 20 minutes hunting, or just solve it again from scratch.
Browser history doesn't help. The apps themselves have weak or zero search. And honestly I didn't want some cloud tool indexing my private dev conversations anyway.
So I built Inventory. It runs locally, indexes everything on your machine, and gives you one search bar across all of it. No account, no sync, no subscription. One time and it's yours.
The problem
If you use more than one AI tool, you know how this goes. A conversation where you figured out a gnarly bug. A prompt that finally worked. An architectural decision you reasoned through with Claude. It's all sitting somewhere on your machine but it might as well be gone.
AI agents are becoming a real part of the workflow now and nobody built the memory layer for it. That's what Inventory is.
Happy to answer anything.
Would love to hear how others are managing this 🙌
Macaly
cross tool search for ai chats is such a usefull idea 🙌 context is so scattered rn
Inventory
@petrkovacik Thank you, I hope it reaches more people 🤞🏻
minimalist phone: reduce your screentime
Got there from your comment! :) Wishing GL!
Inventory
@busmark_w_nika Grateful 🤝
minimalist phone: reduce your screentime
@xshahneil You are welcome! :)