Launched this week
Most AI tools make you explain the context before they can help. Goldfish already has it. It privately remembers what you’ve been working on across your Mac, then helps you write better from any app. Press Option in a text field to draft replies, summarize threads, rewrite sentences, or recall important details from your recent work without copying, pasting, or re-explaining the whole backstory.
Well done! Though where I'd get nervous is recall precision:) Once a month of my screen sits in that vector DB, what stops Option from grabbing the wrong thread when two clients have near identical projects open? Overall, solid work!
@artstavenka1 totally fair concern. the short answer is: Goldfish should not be “semantic search over your whole screen history and hope for the best”.
we’re treating context as scoped and ranked, with recency, active app/thread, focused field, and visible surface mattering a lot. if two client threads look similar, it should prefer the one you’re actually in, not some old near-match.
still early, and recall precision is exactly one of the things we’re obsessing over. thank you for calling it out 🐠 how do you think it works, if you've tried it?
@artstavenka1 super good question! We do use chronological relevance too, so if Goldfish gets any timing signal, we use that as a heuristic. Under the hood it has three representations: recent context, long-term memory, and chronological memory. Would love for you to try it and let me know how it goes!
Congrats on the launch you guys! Absolutely loved the onboarding and really enjoying getting to know the product so far.
The Option key functionality is really great & seamless (but is there a way to change it to the other Option key....? apparently, I use the right Option key a lot and not always for Goldfish!) 🐠
@josephinedt Hi Josephine!
Thank you so much, I'm happy to hear that! 🙏
Yes, you can rebind the option key to whatever you want in the settings after the onboarding! Just press the settings->shortcuts page. There you can also enable transcription.
Have you found any specific use case that goldfish is extra suitable for? 🐠
@josephinedt Awesome to hear!! Yes you can change key in Settings under Shortcuts. What have you used it for the most?
Hey, Joel. I really appreciate your innovation. I was pleasantly surprised by your project—it’s actually amazing! However, I’m a bit worried about security. Since Goldfish can see everything in every app on my computer, what guarantees do I have that it’s not actually spying on me? For example, when I’m doing something very private, how can I be sure that the info won’t be accessed by Goldfish or even stolen by hackers? Otherwise, I’m really impressed by your creative mind!
@denzel_gota Hey Denzel! Thank you for your comment and I'm happy to hear that you're finding Goldfish useful!
I understand what you mean - no worries! So all context that goldfish collects is saved to a local database. The only time data is sent outside the computer is when you do inline rewrite or chat with the aquarium, or when generating wiki pages. This is sent to a LLM with zero data retention.
Goldfish comes with a large blacklist and you can ask goldfish to pause tracking at any time! you can also ask goldfish not to track certain pages/domains/windows and it will follow that.
The database will be encrypted as well so even if hackers get to the actual file on the filesystem, they cannot open it as its encrypted with your authentication.
I hope this answered some of your questions and that you feel more secure with using goldfish! Do you think it would help if this was shown during the onboarding?
@denzel_gota very fair question. This is top prio for us.
The short version: your memory stays on your Mac in a local database. We do not have a backend where we can browse your data, there is no cloud sync, and AI calls have zero data retention.
You can also pause capture whenever you want, exclude specific apps or domains so they never get remembered, and delete stored history.
SocialBu
Congrats on the launch, Joel! The 'starting from zero every time' problem with AI is incredibly real—I waste so much time re-pasting Slack threads and briefs. Keeping the memory layer local via SQLite/vector DB is a massive win for trust. Quick question: How does it impact Mac performance or battery life when it's actively indexing active apps?
@bilal_niaz I feel you, we had the same problem before goldfish existed! Yes indeed - local first is a winner in our opinion :)!
It doesn't affect performance too much, we utilize the already existing accessibility APIs to get the text from open windows, which is super lightweight. We also run an optimized model for doing embeddings as not to tax the computer unnecessarily much.
Have you given goldfish a try yet? Best way to assess performance also! :- D
The Option-key workflow feels smart because it keeps AI inside the place you’re already writing. Curious how Goldfish decides which recent context should matter and which old context should fade out.
@farrukh_butt1 Very good question! We keep a buffer of the most recent-recent context which gets embedded with each option-click, but when it makes sense Goldfish can also search way back into the long term memory, but often the most recent memory is enough.
Have you tried it yet? What do you think? :)
Love the Option key shortcut, feels so friction less. How does it handle privacy with remembering work across apps? That balance of helpful and private is the hard part to get right. Excited to try it.
@shubham4real Thanks Shubham! Privacy is the main thing we designed around here.
Goldfish stores memory locally on your Mac, not in a cloud backend we can browse. You can pause capture whenever you want, exclude specific apps or domains, and delete stored history too. AI calls also have zero data retention.
That balance is definitely the hard part, so would love to hear where it feels too much or not enough once you try it 🐠
wow this product is gold. well done!
I do have a few questions on the infrastructure:
Is a local model used to generate the replies?
How does It formulate a reply in the language (writing style) of the user?
Does it only work with what is given on the screen in realtime?
@ibrahimkakson thank you!! not local right now, so we use azure hosted models for the replies etc. Goldfish uses the context it can see on your screen in realtime, plus your private memory from previous work, if you have it enabled.
For style, it learns from how you actually write across apps and uses the current surface as context, so a Slack reply, email, Product Hunt comment, etc. come out differently! :- D
You can also control what it remembers/ignores, so it is not just blindly saving everything.