Dump Memory
We fix your memory
166 followers
We fix your memory
166 followers
Dump is your private second brain. Capture notes, photos, voice memos, documents, screenshots, and X bookmarks in one place. No folders, tags, or filing. Dump enriches information with web context and lets you find anything using on-device semantic search. Everything stays on your device and personal iCloud with zero cloud storage, zero tracking, and zero compromise. Just dump, remember, and instantly recall what matters.
Free Options
Launch Team / Built With
Viktor.comAn AI coworker that actually does the work
Promoted
Dump Memory
👋 Hello Product Hunt,
I’m Rohil, Designer of Dump Memory. Download from App Store and get 50 Free Credits (Happy Dumping...) : https://apps.apple.com/us/app/dump-memory/id6760990641
A few years ago, I realized I was saving important things everywhere.
Ideas in Apple Notes. Links in X bookmarks. Documents in folders. Screenshots in Photos. Voice notes in different apps.
The problem wasn’t saving information. The problem was finding it later.
I would remember having something, but not where I saved it.
Many founders, creators, and professionals told me they had the exact same problem. So I built Dump.
Dump is a private second brain that helps you remember everything.
Just save things into Dump and forget about organizing them. No folders. No tags. No complicated systems.
When you need something later, simply describe what you remember and Dump finds it for you.
Maybe it’s:
• A screenshot you saved three months ago
• A business card from an event
• A voice note from a morning walk
• A PDF someone sent you
• A tweet you bookmarked late at night
Dump understands meaning, not just filenames.
One of my favorite features is that Dump makes your memories smarter.
For example, if you save a business card, Dump can automatically find company information, LinkedIn profiles, and other useful context, turning a simple card into valuable knowledge.
We also added support for X (Twitter) bookmarks. Your saved posts, threads, and images can now live inside your second brain and become searchable alongside everything else.
And because forgetting isn’t the only problem, Dump can also create Apple Reminders from the memories you save and the context you provide, helping you remember important things at the right time.
Most importantly, Dump is built around privacy.
Many AI apps ask you to upload your notes, documents, and memories to their servers before they can help you find information.
We took a different approach.
When you save something in Dump, your notes, photos, voice memos, documents, screenshots, and bookmarks are stored on your device or in your personal iCloud account.
To make your memories searchable, Dump uses Zero Data Retention AI Models to extract context from your content. These models do not store your data and do not use it for training.
The extracted knowledge is then saved back to your device and synced through your own iCloud account.
When you search, you have two options:
• Quick Search uses on-device search to instantly find relevant memories.
• Advanced Search uses Zero Data Retention AI to deeply understand your question and return richer, more accurate answers.
At no point do we store your memories on our servers.
• We can’t read them.
• We can’t access them.
• We can’t sell them.
Because we never have them.
Your data stays on your device and in your personal iCloud.
Dump is for anyone who has ever said:
“I know I saved that somewhere.”
If that sounds familiar, I’d love for you to try Dump and let me know what you think.
I’ll be here all day answering questions and would love to hear how you currently save and organize information in your life.
Thank you for checking out Dump ❤️
YourSitee
If you fix our memory, can it be retroactive too? 😅
This feels very relatable. I save things everywhere: Apple Notes, screenshots, X bookmarks, random docs, voice notes, links I swear I’ll need later... and then the actual problem is finding them again.
The X bookmarks part is especially interesting to me. I save a lot of startup/product/launch ideas there, but it usually becomes a black hole after a few weeks. I also really like the privacy direction here. for a second brain app, local-first + personal iCloud + zero data retention feels like the right trust model.
Curious how Dump handles messy saved content over time. if I save screenshots, tweets, PDFs, and notes around the same topic, can it connect them into one useful memory, or does each item stay separate?
Dump Memory
@andrasczeizel Thanks Andras.
Dump stores every memory with rich tags and enriches it with as much context as possible. When you search for a memory, it uses multiple retrieval signals to find and return the most relevant results.
ChatWebby AI
The business-card enrichment (pulling company info + LinkedIn context automatically) is a genuinely clever touch it turns a static save into something useful. The local-first + personal iCloud + zero-data-retention model is the right call for a second brain too. One question: for Advanced Search that uses the ZDR AI, does the relevant content get sent off-device per query, or is the semantic index built locally first so only the query goes out?
Dump Memory
@zain_sheikh Thanks. The semantic index is built locally on your device, and searches are performed entirely on-device. You can verify this by enabling Quick Search on the chat screen, turning on Airplane Mode, and searching your memories. Everything continues to work offline.
When you add memory or use advanced AI search it will use ZDR AI model for processing and the results store only on your device.
Curious how the semantic search holds up once you've dumped thousands of items, and whether the on-device model gets updated over time?
Dump Memory
@ssaglamoz92701 It should scale well to thousands of saved items, but it uses a local hybrid index rather than a full vector database. We cache embeddings for each memory chunk, only re-embed content that has changed, and combine semantic similarity with keyword search so exact matches are still easy to find.
One clarification: the embedding model itself is not updated on-device over time. The app updates its local index as memories change, but embeddings are generated via OpenRouter using openai-embedding model.
How does the on-device semantic search actually perform with thousands of mixed media files like voice memos and screenshots combined?
Dump Memory
@serafettin39697 Everything is extracted from voice, images etc using ZDR Models.
We cache embeddings for each memory chunk, only re-embed content that has changed, and combine semantic similarity with keyword search so exact matches are still easy to find.
The app updates its local index as memories change, but embeddings are generated via OpenRouter using openai-embedding model.
how does the semantic search actually work on-device without sending data out, especially for the web enrichment part?
Dump Memory
@gecit_gize13066 It’s not fully on-device today.
Search/ranking happens locally: memories and enriched web items are stored in a local SQLite index, and the app searches that index on-device.
But semantic embeddings are generated through OpenRouter (text-embedding-3-small), so memory chunks and queries are sent out for embedding. Web enrichment also uses external web/search tools when requested, then the enriched result can be saved and searched locally afterward. All data store only on local device.
How does the on-device semantic search actually perform when you've dumped thousands of items?
Dump Memory
@soneragah57306 It scales to thousands of saved items using a local hybrid index, not a full vector database. We cache embeddings, only re-embed changed content, and combine semantic and keyword search for fast, accurate results.
The embedding model isn’t updated on-device. Embeddings are generated via OpenRouter using text-embedding-3-small, while the local index updates as your memories change.