Memora – A Vector DB with Multistage Reranking
Hey HN, Matusa here! A friend and I have built Memora. Memora is a vector database with built-in multistage reranking, which can significantly improve search accuracy over semantic search. It also features a proprietary embedding model tailored for RAG use cases — where there's a structural mismatch between the content stored and the query used for searching (hence why HyDE works well). Memora started because we were working on a stealth AI startup where we used an agent that would query into a vector DB, but it would take multiple tries for the agent to find what it needed (20% of the time…
What it does
In the maker’s words, at launch
Hey HN, Matusa here! A friend and I have built Memora. Memora is a vector database with built-in multistage reranking, which can significantly improve search accuracy over semantic search. It also features a proprietary embedding model tailored for RAG use cases — where there's a structural mismatch between the content stored and the query used for searching (hence why HyDE works well). Memora started because we were working on a stealth AI startup where we used an agent that would query into a vector DB, but it would take multiple tries for the agent to find what it needed (20% of the time it couldn't find at all). This process was not only costly but also time-consuming, with each search taking up precious seconds. We realized that our biggest bottleneck was the accuracy from the semantic search results. So, in order to improve the product, we had to go beyond simple semantic search and, ended up creating a retrieval pipeline that used semantic search as the initial step, providing the first 1k batch of documents. These documents were then reranked using neural rankers. Not only we were able to increase the product accuracy by over 4x, we were able to completely eliminate the need for the agent making multiple search queries. A cool challenge was creating the two ranking models for Memora's retrieval pipeline. We applied the rankT5 principle, converting a encoder-decoder LLM model to an encoder-only by transforming llama-7b into rank-llama. We, then, finetuned it further on a ton of synthetic data. However, running a model with 7B parameters can be costly. That's where our second ranking model, with 120M parameters, comes into play. This model was crafted by distilling rank-llama. On top of that, we're also trying to focus on offering a great DX: i) we feel that our Javascript/Typescript library offers great developer ergonomics by using the builder pattern; ii) having our own embedding model allows us to streamline the experience. Instead of calling one API to embed your data and another API to store the embedding, you simply call Memora, pass in your data, and we handle the embedding and storage. That said, Memora is still in its early stages. Both the embedding model and the retrieval pipeline have room are far from perfect. However, we feel it's reached a point where it works for most usecases pretty well. To be honest, we see still some low-hanging fruits way to improve the models but we are advocates of launching early. We're thrilled to share Memora to y'all, we would love to hear any feedback or critiques you might have!
Does the same job
all alternatives →
Memoria12d ago · memoria.anasouh.fr · ▲156Search photos by text, speech, object & faces. 100% offline.
- MRMemora – Replicating Human Memory for Personalized AI, Open Source2025 · github.com · ▲5
Memora gives AI the ability to recall memories during interactions, just like humans do subconsciously. For now, it’s just text-based memories, but our vision extends to the full spectrum of human memory: emotions, audio, video. Key Features: Built-in multi-tenancy for managing multiple organizations, users, and agents. Time-stamped memories to track how information evolves over time. Scalable, modular, and developer-friendly design. GitHub: https://github.com/ELZAI/memora Install: pip install memora-core We’re looking for feedback and contributions, let’s change how we…
- OAOtterTune – Automated Database Tuning Service for RDS MySQL/Postgres2021 · ▲164
Yo. OtterTune is a database optimization service. It uses machine learning to automatically tune your MySQL and Postgres configuration (i.e., RDS parameter groups) to improve performance and reduce costs. It does this by only looking at your database's runtime metrics (e.g., INNODB_METRICS, pg_stat_database, CloudWatch). We don't need to examine sensitive queries or user tables. We spun this project out of my research group at Carnegie Mellon University in 2020. This week we've announced that OtterTune is now available to the public. We are offering everyone a starter account to try it out…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, October 2023
the whole month →
Nudge 2.0▲1,051In-app experiences to activate, retain, & understand users
Growth · 2023 · nudgenow.com
Unlock AI magic for elevated customer engagement, fast
AI · 2023 · tiledesk.com
- OD
Effortlessly discover API behaviour with a Chrome extension that automatically generates OpenAPI specifications in real time for any app or website.
Dev tools · 2023 · github.com