Alternatives
Products that do what I wrote a GPU-less billion-vector DB for molecule search (live demo) does
Input a SMILES string (or pick one molecule from the examples) and it returns up to 100k molecules closest in 3-D shape or electrostatic similarity – from 10+ billion scale databases — typically in under 5-10 s. *Why it might interest HN* * Entire index lives on disk — no GPU at query-time, less than ~10 GB RAM total. * Built from scratch (no FAISS index / Milvus / Pinecone). * Index-build cost: one Nvidia T4 (~ 300USD) for one 5.5B database. * Open to anyone, predict ADMET, export results as CSV/SDF. Full write-up & benchmarks (DUD-E, LIT-PCBA, SVS) in the pre-print:…
- 1IV
The video demo runs a 7b Model on a normal gaming GPU. I think it already works quite well (accounting for the limited hardware power). :)
2024 · github.com
- 2AG
This is a vector index I built that supports insertion and k-nearest neighbors (k-NN) querying, optimized for GPUs. It operates entirely in CUDA and can process queries on half a billion vectors in under 200 milliseconds. The codebase is structured as a standalone library with an HTTP API for remote access. It’s intended for high-performance search tasks—think similarity search, AI model retrieval, or reinforcement learning replay buffers. The codebase is located at https://github.com/rodlaf/BinaryGPUIndex.
2025 · rlafuente.com
- 3NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
May 2026 · github.com
- 4CH
Hi HN! We're thrilled to share CozoDB v0.6, a monumental update to our FOSS database, which already unifies relational and graph features. With the addition of vector search, CozoDB becomes an even better companion for LLMs like ChatGPT. This release introduces vector search using HNSW indices within Datalog, enabling seamless integration with powerful features such as ad-hoc joins, recursive Datalog, and classical whole-graph algorithms. This update significantly broadens CozoDB's capabilities. Check out the linked release note for an in-depth look at the new features, comparisons to other…
2023 · docs.cozodb.org
- 5HO
Hey HN, we want to share HelixDB (https://github.com/HelixDB/helix-db/), a project a college friend and I are working on. It’s a new database that natively intertwines graph and vector types, without sacrificing performance. It’s written in Rust and our initial focus is on supporting RAG. Here’s a video runthrough: https://screen.studio/share/szgQu3yq. Why a hybrid? Vector databases are useful for similarity queries, while graph databases are useful for relationship queries. Each stores data in a way that’s best for its main type of query (e.g.…
2025 · github.com
- 6
The first open-source price index for GPU compute
10d ago · getcomputable.com
- 7UC
Paste in my prompt to Claude Code with an embedded API key for accessing my public readonly SQL+vector database, and you have a state-of-the-art research tool over Hacker News, arXiv, LessWrong, and dozens of other high-quality public commons sites. Claude whips up the monster SQL queries that safely run on my machine, to answer your most nuanced questions. There's also an Alerts functionality, where you can just ask Claude to submit a SQL query as an alert, and you'll be emailed when the ultra nuanced criteria is met (and the output changes). Like I want to know when somebody posts about…
Dec 2025 · exopriors.com
- 8EO
Hey HN! We are building Epsilla (https://github.com/epsilla-cloud/vectordb), an open-source, self-hostable vector database for semantic similarity search that specializes in low query latency. When do we need a vector database? For example, GPT-3.5 has a 16k context window limit. If we want to let it answer a question about a 300 page book, we cannot put the whole book content into the context. We have to choose the sections of the book that are most relevant to the question. Vector database is specialized at ranking and picking the most relevant content from a large pool…
2023 · github.com
- 9FT
Aug 2026 · github.com
- 10LA
We are excited to share Lantern! Lantern is a PostgreSQL vector database extension for building AI applications. Install and use our extension here: https://github.com/lanterndata/lantern We have the most complete feature set of all the PostgreSQL vector database extensions. Our database is built on top of usearch — a state of the art implementation of HNSW, the most scalable and performant algorithm for handling vector search. There’s three key metrics we track. CREATE INDEX time, SELECT throughput, and SELECT latency. We match or outperform pgvector and pg_embedding…
2023 · docs.lantern.dev
- 11OF
OctaneDB is an open-source vector database for Python that focuses on ultra-fast similarity search for high-dimensional data—perfect for AI/ML, semantic search, and large-scale document or embedding retrieval. What does it do? Store, index, and search millions of embeddings (text, images, etc.) with sub-millisecond query time. Supports in-memory and efficient HDF5 persistent storage. Integrates seamlessly with sentence-transformers for automatic text embedding. Key Features: 10x faster than Pinecone or ChromaDB for vector search and batch insertions. Advanced indexing: HNSW (approximate…
2025 · github.com
- 12WM
Try it out! https://glhf.chat/ Hey HN! We’ve been working for the past few months on a website to let you easily run (almost) any open-source LLM on autoscaling GPU clusters. It’s free for now while we figure out how to price it, but we expect to be cheaper than most GPU offerings since we can run the models multi-tenant. Unlike Together AI, Fireworks, etc, we’ll run any model that the open-source vLLM project supports: we don’t have a hardcoded list. If you want a specific model or finetune, you don’t have to ask us for it: you can just paste the Hugging Face link in and…
2024 · glhf.chat
- 13TC
Hello HN! I’m Jonathan from TensorDock. After 7 months in beta, we’re finally launching Core Cloud, our platform to deploy GPU virtual machines in as little as 45 seconds! https://www.tensordock.com/product-core Why? Training machine learning workloads at large clouds can be extremely expensive. This left us wondering, “how did cloud ever become more expensive than on-prem?” I’ve seen too many ML startups buy their own hardware. Cheaper dedicated servers with NVIDIA GPUs are not too hard to find, but they lack the functionality and scalability of the big clouds. We thought to…
2022 · tensordock.com
- 14AF
2024 · github.com
- 15IM
This is another one of my automate-my-life projects - I'm constantly asking the same question to different AIs since there's always the hope of getting a better answer somewhere else. Maybe ChatGPT's answer is too short, so I ask Perplexity. But I realize that's hallucinated, so I try Gemini. That answer sounds right, but I cross-reference with Claude just to make sure. This doesn't really apply to math/coding (where o1 or Gemini can probably one-shot an excellent response), but more to online search, where information is more fluid and there's no "right" search engine + text…
2024 · ithy.com
- 16NG
Hi everyone, I started working on nanoeuler after the ban of anthropic's fable because my ambition and dream is to work in the AI field in anthropic. The two interesting reasons that led me to create nanoeuler were (1) interfacing with llm does not mean understanding how they are composed and (2), working on llm with a very low-level layer to understand the correlation between parameters and data and growth of the model and how the GPU works and how some layers can be optimized. So I started working on it with a research aspect by making nanoeuler grow more and more but doing one step after…
Jun 2026 · github.com
- 17
Affordable H100, H200, GB300, and B200 GPU compute for training, inference, and everything in between.
4d ago · compute.cheap
- 18IM
I scraped every Show HN from the last 12 months (41,301 posts) plus the full comment tree of every launch with 10+ comments, ~100k comment timestamps, all from the Algolia HN API. The median launch gets 2 points and 0 comments. For launches that do get traction, half the comments they'll ever get arrive within 7.2 hours and 90% within 26, and the top decile decays on the same clock as everyone else. Vote timestamps aren't public, so comment timing is the attention proxy; caveats are in the post. Everything reproduces from the repo with one command…
Jul 2026 · jonno.nz
- 19IB
Hey HN community, I built a tool that helps optimize your post for hitting the first page of Show HN. How it works: I used a Hugging Face dataset of all Hacker News posts from the past 3 years and trained a model that predicts how successful your post might be. There's still a lot of randomness on HN, so nothing is guaranteed, but the tool helps optimize your post for higher odds. A couple of interesting findings: - GitHub repo links work x3 better than regular domains - Open-source tools have a steady virality rate (13.9% - one of the highest) - "I built" outperforms "We built" - Using…
May 2026 · wannalaunch.com
- 20OD
Hi HN, We’ve launched a GPU cloud platform offering on-demand access to high-end GPUs — with pricing starting at $0.79/hr, no queue, and no preemption. What we offer: - On-demand H100, H200, and B200 instances - H200 pricing from $0.79/hr - Multi-region support: US, Singapore, and Europe - No queuing, no bidding, and no interruptions - Used by AI startups, researchers, and open-source developers Try it: https://hpc-ai.com/?utm_source=hackernews&utm_medium=post&ut... We built this after facing our own frustrations with high prices and long wait times on other…
2025 · hpc-ai.com
- 21ES
Hi HN, I built EdgeVec, a vector database that runs entirely in the browser. It implements HNSW (Hierarchical Navigable Small World) graphs for approximate nearest neighbor search. Performance: - Sub-millisecond search at 100k vectors (768 dimensions, k=10) - 148 KB gzipped bundle - 3.6x memory reduction with scalar quantization Use cases: browser extensions with semantic search, local-first apps, privacy-preserving RAG. Technical: Written in Rust, compiled to WASM. Uses AVX2 SIMD on native, simd128 on WASM. IndexedDB for browser persistence. npm:…
Dec 2025 · github.com
- 22VA
Hey HN, My friend Sam and I were bored one weekend, and wanted to make something self-contained but still useful. We ended up with Victor [0], a vector database designed to run in the browser. It’s written in Rust, which gives us access to things like super-fast and compact serialization and deserialization, but it’s compiled to WASM and uses web-sys to interact with the browser’s JS APIs to write the database contents to disk. We worked hard on designing it in a way that makes sense for the browser. It uses the private origin file system [1] and stores the vectors in a compact format (one…
2023 · github.com
- 23UI
Hey everyone! I am excited to share updates on four of my & my teams' open-source projects that take large-scale search systems to the next level: USearch, UForm, UCall, and StringZilla. These projects are designed to work seamlessly together, end-to-end—covering everything from indexing and AI to storage and networking. And yeah, they're optimized for x86 AVX2/512 and Arm NEON/SVE hardware. USearch [1]: Think of it as Meta FAISS on steroids. It's now quicker, supports clustering of any granularity, and offers multi-index lookups. Plus, it's got more native bindings than probably…
2023 · usearch-images.com
- 24IB
I built a web page that aggregates data about data center buildup, sovereign fund investments into AI and bottlenecks. The objective is to predict AI race cooldown by looking at a potential decrease of activity involving these elements. The website looks at the quarterly forms from the 5 biggest hyperscalers and adds their CapEx into the mix, calculating a composite index in the end showing how likely it is for the AI race to slow down. Enjoy!
Jul 2026 · laurentiugabriel.github.io
Ranked by how close each launch is in meaning, then by votes. Refine with a description →