SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 Rust Embedding Projects
-
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
lance
Open Lakehouse Format for Multimodal AI. Convert from Parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with more integrations coming..
Project mention: Accelerating Multimodal Vector DB with Hugging Face + LanceDB | dev.to | 2026-02-17 -
Daft
High-performance data engine for AI and multimodal workloads. Process images, audio, video, and structured data at any scale
Project mention: 650GB of Data (Delta Lake on S3). Polars vs. DuckDB vs. Daft vs. Spark | news.ycombinator.com | 2025-11-13Hey everyone, I'm a software engineer at Eventual, the team behind Daft! Huge thanks to the op for the benchmark, we're a huge fan of your blog posts and this gave us some really useful insights. For context, Daft is a high-performance data processing engine for AI workloads that works both on single-node and distributed setups.
We're actively looking into the results of the benchmark and hope to share some of our findings soon. From initial results, we found a lot of potential optimizations we could make to our deltalake reader to improve parallelism and our groupby operator to improve pipelining for count aggregations. We're hoping to roll our these improvements over the next couple of releases.
If you're interested to learn more about our findings, check out our GitHub (https://github.com/Eventual-Inc/Daft) or follow us on Twitter (https://x.com/daftengine) and LinkedIn (https://www.linkedin.com/showcase/daftengine) for updates. Also if Daft sounds interesting to you, give us a try via pip install daft!
-
Project mention: Cut token waste across your entire team with the MCP Optimizer | dev.to | 2026-03-11
The operator defaults to BAAI/bge-small-en-v1.5 as the model and runs the HuggingFace Text Embeddings Inference server. You can increase the replica count via spec.replicas to match your team's throughput needs. One shared instance serves every vMCP in the namespace. For all available configuration options, see the Optimizer docs.
-
Project mention: Semantic grep for Claude Code (RUST) (local embeddings) | news.ycombinator.com | 2025-09-07
I don't see how these are apples-to-apples given its "send me all your content" approach <https://github.com/run-llama/semtools#:~:text=get%20your%20a...>
versus https://github.com/BeaconBay/ck#:~:text=yes%2C%20completely%...
-
korvus
Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.
-
Project mention: Show HN: Fastembed-rs – Rust library for generating vector embeddings, reranking | news.ycombinator.com | 2026-06-15
-
-
Project mention: KiteSQL: Rust-native embedded SQL with TPC-C benchmarks and WASM support | news.ycombinator.com | 2026-01-29
-
-
Project mention: Ask HN: How do you give AI agents real codebase context without burning tokens? | news.ycombinator.com | 2026-03-05
Working on a large Rust codebase. The token problem is real — Claude Code will happily spend $5 of context just trying to understand how two modules relate before writing a single line. And once context compaction kicks in, it's even worse — the agent loses the thread completely and starts grepping the same files again from scratch.
Approaches I've tried:
Feeding CLAUDE.md / architecture docs manually — helps, but gets stale fast. Cursor's built-in indexing — breaks on monorepos, and I don't love proprietary code going to their servers. Basic MCP server with grep — works for exact matches, useless for semantic queries.
Eventually built something more serious: a local Tree-sitter indexer that builds a knowledge graph of file relationships and exposes it via MCP so agents query semantically instead of grepping blind. One tool call instead of 15 grep iterations. Published it here: https://github.com/Muvon/octocode
But genuinely curious what others are doing before I go deeper on it.
Three specific questions:
1. How do you handle the "ripple effect" problem — knowing that changing one file semantically affects others that aren't obviously linked?
2. Do you trust closed-source indexing with proprietary code, or have you gone local-first?
3. Has anyone gotten GraphRAG-style relationship mapping to work in practice at scale, or is it still mostly hype?
-
-
-
-
-
-
VelesDB
The explainable, local-first memory engine for AI agents. One ~9 MB binary fuses vector + graph + columnar under VelesQL; why() returns the evidence path behind every recall. No cloud, no glue code — runs on server, browser, mobile and desktop.
Project mention: VelesDB now has a Haystack connector - build a RAG pipeline with zero infrastructure | dev.to | 2026-05-01VelesDB now ships a first-party Haystack 2.x DocumentStore, contributed by @CrepuscularIRIS in PR #672. Two pip installs, zero infrastructure, and your Haystack pipeline has a vector backend that runs in-process.
-
rememex
semantic search for your local files find by meaning, not keywords. 120+ file types, OCR, MCP server for AI agents. 100% private.
Project mention: Show HN: Rememex – Semantic file search that runs 100% locally (Rust/Tauri) | news.ycombinator.com | 2026-02-19 -
Project mention: Rawq – semantic code search for AI agents (4x fewer wasted tokens, Rust, OSS) | news.ycombinator.com | 2026-03-20
-
sochdb
SochDB is a high-performance embedded, ACID-compliant vector database purpose-built for AI agents and memory
Project mention: Stop Reindexing: How We Built Real-Time Search Directly Into the Database using sochDB | dev.to | 2026-02-07In this post, I’ll explain why reindexing is fundamentally broken for real-time systems, and how we built SochDB to make search a native database capability instead of a separate infrastructure problem.
-
kjarni
Native and Private ML inference engine, embeddings, classification, reranking, search, and text generation. Rust core with C# bindings. No Python, no ONNX, no CUDA.
NuGet: https://www.nuget.org/packages/Kjarni GitHub: https://github.com/olafurjohannsson/kjarni
-
bridgerust
High-performance infrastructure libraries built in Rust, with seamless bindings for Python, Node.js, and WebAssembly.
Two weeks ago, I published Embex to PyPI and npm.
-
cortex
Memory for AI agents that never leaves your device. Local-first, end-to-end-encrypted, zero-telemetry memory engine (Rust, MCP) — gives Claude & any MCP client persistent cross-session memory. (by gambletan)
Project mention: Show HN: Cortex – local-first encrypted memory for AI agents (Rust, MCP) | news.ycombinator.com | 2026-06-13
Rust Embeddings discussion
Rust Embeddings related posts
-
Show HN: Fastembed-rs – Rust library for generating vector embeddings, reranking
-
Show HN: Cortex – local-first encrypted memory for AI agents (Rust, MCP)
-
Show HN: I embedded 685M public texts in 32 minutes (on 8x A100, Rust, TensorRT)
-
VelesDB now has a Haystack connector - build a RAG pipeline with zero infrastructure
-
I built a database in France because the Cloud Act makes EU data sovereignty impossible
-
What if SQL could search by meaning? Meet VelesQL
-
Share memory between AI agents without infrastructure
-
A note from our sponsor - SaaSHub
www.saashub.com | 20 Jul 2026
Index
What are some of the best open-source Embedding projects in Rust? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | postgresml | 6,807 |
| 2 | lance | 6,822 |
| 3 | Daft | 5,640 |
| 4 | text-embeddings-inference | 4,930 |
| 5 | semtools | 1,834 |
| 6 | korvus | 1,461 |
| 7 | fastembed-rs | 963 |
| 8 | lantern | 885 |
| 9 | KiteSQL | 730 |
| 10 | tinyvector | 433 |
| 11 | octocode | 433 |
| 12 | exograph | 348 |
| 13 | victor | 261 |
| 14 | PyCrucible | 208 |
| 15 | model2vec-rs | 197 |
| 16 | finalfusion-rust | 104 |
| 17 | VelesDB | 75 |
| 18 | rememex | 65 |
| 19 | rawq | 51 |
| 20 | sochdb | 36 |
| 21 | kjarni | 33 |
| 22 | bridgerust | 28 |
| 23 | cortex | 28 |