AI · alternatives · 2026

24 alternatives to Witchcraft and Pickbrain – fast multi-vector semantic search in Rust

Witchcraft is from-scratch Rust reimplementation of Stanford's XTR-Warp (SIGIR'25, https://arxiv.org/abs/2501.17788 ) multi-vector semantic search engine. Witchcraft runs out of a single SQLite database, is blazing-fast (21ms p.95 end-to-end search latency on NFCorpus on a MacBook Pro), accurate (33% NDCG@10), and easy to deploy in your own apps. The Witchcraft repo also comes with Pickbrain, a sample app and agent skill that you can use to instantly query across all your Claude Code and Codex CLI sessions, effectively giving your agents global long-term memory. Please…

Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes.

1
SeekStorm – open-source sub-millisecond search in Rust▲245
SeekStorm: vector & lexical search - in-process library & multi-tenancy server, in Rust. - SeekStorm/SeekStorm
2024 · github.com · its alternatives →
2
Meilisearch AI▲241
Boost relevance and UX with fast hybrid and semantic search
2025 · meilisearch.com · its alternatives →
3
Tantivy▲68
A full-text, horse-speed search engine library in Rust
2022 · github.com · its alternatives →
4
We made our own inference engine for Apple Silicon▲186
We wrote our inference engine on Rust, it is faster than llama cpp in all of the use cases. Your feedback is very welcomed. Written from scratch with idea that you can add support of any kernel and platform.
2025 · github.com · its alternatives →
5
HelixDB – Open-source vector-graph database for AI applications (Rust)▲237
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 · its alternatives →
6
A fast HNSW implementation in Rust▲111
HNSW implementation in Rust. Reference: https://arxiv.org/ftp/arxiv/papers/1603/1603.09320.pdf - swapneel/hnsw-rust
2024 · github.com · its alternatives →
7LA
Lingo – A linguistic database in Rust with nanosecond-level performance▲42
Hi HN, I made Lingo - the SQLite of semantic search. I'm a self-taught developer and researcher who left school at 16, and I've spent some time exploring a first-principles approach to system design for various frontier problems. In this case it's AI that challenges the 'bigger is better' transformer paradigm. Lingo is the first piece of that research, a high-performance linguistic database designed to run on-device. The full technical overview and manifesto is here: https://medium.com/@robm.antunes/bcd1e9752af6 The paper has been archived on Zenodo with a DOI:…
2025 · its alternatives →
8
TurboQuant for vector search – 2-4 bit compression▲89
A vector index built on TurboQuant, written in Rust with Python bindings - RyanCodrai/turbovec
Mar 2026 · github.com · its alternatives →
9
Spice.ai▲63
Hi HN, we’re Luke and Phillip, and we’re building Spice.ai OSS - a lightweight, portable data and AI engine and powered by Apache DataFusion & Ballista for SQL query, hybrid-search, and LLM-inference across disaggregated-storage used by enterprises like Barracuda Networks and Twilio. With v2.0, you can add a real-time analytics node to your operational database with high-throughput native CDC replication. We first introduced Spice [1] on HN in 2021 and re-launched it on HN [2] in 2024 re-built from the ground up in Rust. In 2025 we launched Spice Cayenne [5], our acceleration and query…
2023 · spice.ai · its alternatives →
10
FizzBuzz purely in Rust's trait system▲120
We all know Rust's trait system is Turing complete, so tell me, why aren't we exploiting this??? - cofibrant/trait-eval
2020 · github.com · its alternatives →
11
Forge Agent▲113
Swarm Agents That Turn Slow PyTorch Into Fast GPU Kernels
Jan 2026 · rightnowai.co · its alternatives →
12AF
Apache Fory Rust – 10-20x faster serialization than JSON/Protobuf▲67
Serialization framework with some interesting numbers: 10-20x faster on nested objects than json/protobuf. Technical approach: compile-time codegen (no reflection), compact binary protocol with meta-packing, little-endian layout optimized for modern CPUs. Unique features that other fast serializers don't have: - Cross-language without IDL files (Rust ↔ Python/Java/Go) - Trait object serialization (Box) - Automatic circular reference handling - Schema evolution without coordination Happy to discuss design trade-offs. Benchmarks:…
Oct 2025 · fory.apache.org · its alternatives →
13
KiviDB, a faster Redis-compatible memory database and vector cache▲69
A fast, multi-threaded Redis® and Valkey alternative written in Rust: drop-in compatible, with full-text and vector search built in - kividbio/kividb
4d ago · github.com · its alternatives →
14
Glowstick – type level tensor shapes in stable rust▲53
Hi HN, In the past few years I've become more interested in machine learning. Since I'm sure the same is true for many here, I wanted to share this project I've been working on: glowstick uses type-directed metaprogramming to keep track of tensor shapes in Rust's type system and determine which operations are permitted or not at compile time. I find Rust has a lot of strengths when it comes to ML applications, but waiting until runtime to find shape related issues feels a bit strange since normally I don't run the code all that often while developing. Given Rust has fancy types available, I…
2025 · github.com · its alternatives →
15AG
A GPU-accelerated binary vector index▲65
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 · its alternatives →
16SA
Spart – A Rust library for fast spatial search with Python bindings▲31
Hi everyone, I've made an open-source library for fast spatial search in Rust. It's called Spart, and it currently provides the following features: - Five tree implementations: Quadtree, Octree, Kd-tree, R-tree, and R*-tree - Python bindings (`pyspart` on PyPI) - Fast k-nearest neighbor (kNN) and radius search - Bulk data loading for efficient tree construction Project's GitHub repo: https://github.com/habedi/spart
2025 · its alternatives →
17
20x faster pgvector alternative written in Rust▲23
Scalable, Low-latency and Hybrid-enabled Vector Search in Postgres. Revolutionize Vector Search, not Database. - tensorchord/pgvecto.rs
2023 · github.com · its alternatives →
18
Modeling the human body in Rust so I can cmd+click through it▲46
I started this trying to understand two things: why my Asian friends turn red after drinking, and why several friends all seemed to have migraine clusters. I was reading medical papers and textbooks, but kept getting lost jumping between topics. I thought: what if I could just Cmd+Click through this like code? What if "ALDH2 gene" was actually clickable, and took me to the variant, the phenotype, the population frequencies? So I started modeling human biology in Rust with my Ralph agent (Claude in a loop, ty ghuntley). Turns out the type system is perfect for this. Every biological entity is…
2025 · github.com · its alternatives →
19T5
TensorBase: 5x~10000x Faster Drop-In/Accelerator for ClickHouse in Rust▲19
2021 · tensorbase.io · its alternatives →
20
Optimizing LiteLLM with Rust – When Expectations Meet Reality▲27
I've been working on Fast LiteLLM - a Rust acceleration layer for the popular LiteLLM library - and I had some interesting learnings that might resonate with other developers trying to squeeze performance out of existing systems. My assumption was that LiteLLM, being a Python library, would have plenty of low-hanging fruit for optimization. I set out to create a Rust layer using PyO3 to accelerate the performance-critical parts: token counting, routing, rate limiting, and connection pooling. The Approach - Built Rust implementations for token counting using tiktoken-rs - Added lock-free data…
Nov 2025 · github.com · its alternatives →
21
Spanda – Sub-microsecond LLM epistemic uncertainty in Rust▲13
Zero-cost epistemic uncertainty quantification & hallucination detection for LLMs (90,000x faster than Semantic Entropy) - Adarshent/Spnda
Sep 2026 · github.com · its alternatives →
22
Faking SIMD to Search and Sort Strings 5x Faster▲29
I want to share a really dumb, but very practical project I have packaged this summer, to perform operations on strings much faster. I was using Python to work with a multi-terabyte newline-delimited file. Reading, splitting, and shuffling it was a nightmare. So, I wrapped a trivial hardware-friendly heuristic I've been using for the last few years into a CPython library. The part I enjoyed the most is implementing SIMD behavior without SIMD instructions... Using 64-bit words to work at 8-bit granularity. Unlike conventional SIMD, the code would remain the same for ~~almost~~ any hardware.…
2023 · ashvardanian.com · its alternatives →
23
Victor, a browser-optimized vector database written in Rust▲27
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 · its alternatives →
24
Moss – AI-Powered Semantic Search Running In-Browser (No Cloud)▲6
Hey HN, We’ve been heads-down building MOSS - a semantic memory layer that brings AI-powered search and personalization fully on-device (No cloud | No latency | No data leaving the user’s device) We just launched a live demo showing MOSS running entirely in-browser, performing lightning-fast semantic search over local in-browser VectorDB. This unlocks a new class of privacy-first, hybrid AI experiences that work even without a server connection. If you’re curious about: - how to run AI search right inside the browser - the technical challenges behind on-device vector search - why we believe…
2025 · twitter.com · its alternatives →

Also compare

Ranked by how close each launch is in meaning, then by votes. Prices were read from each product’s own site when checked and can change. Refine with your own description →