Revolutionize your code reviews with AI. CodeRabbit offers PR summaries, code walkthroughs, 1-click suggestions, and AST-based analysis. Boost productivity and code quality across all major languages with each PR. Learn more โ
Top 23 Rust AI Projects
-
-
CodeRabbit
CodeRabbit: AI Code Reviews for Developers. Revolutionize your code reviews with AI. CodeRabbit offers PR summaries, code walkthroughs, 1-click suggestions, and AST-based analysis. Boost productivity and code quality across all major languages with each PR.
-
People in government agencies, defence and aerospace companies write code in airgapped environments every day.
Essentials like version control, CI/CD and artifact repositories are readily available, as they always have been.
The problem you'll face with LLM assists is they require very substantial hardware. I don't know how well that's going to fit your laptop-in-the-middle-of-nowhere use case, but there are projects floating around.
https://github.com/TabbyML/tabby
-
databend
๐๐ฎ๐๐ฎ, ๐๐ป๐ฎ๐น๐๐๐ถ๐ฐ๐ & ๐๐. Modern alternative to Snowflake. Cost-effective and simple for massive-scale analytics. https://databend.com
Project mention: Top 5 Snowflake Alternatives for Cost-Effective Data Warehousing | news.ycombinator.com | 2024-09-06Check out Databend, an open-source alternative to Snowflake with 90%+ product and syntax similarity (almost no migration cost). Itโs cost-effective and powerful.
GitHub: https://github.com/datafuselabs/databend/issues/13059
Comparison: https://www.databend.com/comparison
-
Project mention: Postgres Learns to RAG: Wikipedia Q&A using Llama 3.1 inside the database | news.ycombinator.com | 2024-09-24
GitHub: https://github.com/postgresml/postgresml
Looking forward to your feedback and any questions about the technical details.
-
aichat
All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.
Project mention: Show HN: Onit โ open-source ChatGPT Desktop with local mode, Claude, Gemini | news.ycombinator.com | 2025-01-24This one feels a bit buggy and it might be abandoned, but it has basic functionality for working with ollama models.
Also worth a mention is [aichat](https://github.com/sigoden/aichat). It's not a native gui app, but it's an impressive cli client.
-
code2prompt
A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.
๐ https://github.com/mufeedvh/code2prompt
-
deepclaude
A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthropic Claude models.
If you would like to see the CoT process visualized, try the โImprove promptโ feature in Anthropic console. Also check out https://github.com/getAsterisk/deepclaude
-
Nutrient
Nutrient - The #1 PDF SDK Library. Bad PDFs = bad UX. Slow load times, broken annotations, clunky UX frustrates users. Nutrientโs PDF SDKs gives seamless document experiences, fast rendering, annotations, real-time collaboration, 100+ features. Used by 10K+ devs, serving ~half a billion users worldwide. Explore the SDK for free.
-
Project mention: Probly: Spreadsheets and Python and AI, right in the browser | news.ycombinator.com | 2025-02-27
any comparisons with https://github.com/quadratichq/quadratic ?
*necessary disclosure, i'm a small angel investor in it but genuinely open to see new approaches
-
Project mention: Zero-Shot Text Classification on a low-end CPU-only machine? | news.ycombinator.com | 2024-10-07
Hugging Face does maintain a package named Text Embedding Inference (TEI) with GPU/CPU-optimized container images. While I have only used this for hosting embedding models, it does appear to support Roberta architecture classifiers (specifically sentiment analysis).
https://github.com/huggingface/text-embeddings-inference
You can always run a zero shot pipeline in HF with a simple Flask/FastAPI application.
-
tensorzero
TensorZero creates a feedback loop for optimizing LLM applications โ turning production data into smarter, faster, and cheaper models.
Project mention: Show HN: TensorZero โ open-source data and learning flywheel for LLMs | news.ycombinator.com | 2024-09-16 -
lsp-ai
LSP-AI is an open-source language server that serves as a backend for AI-powered functionality, designed to assist and empower software engineers, not replace them.
-
-
Thatโs right, if LLMs were really thinking/forming world models etc. we would expect them to be robust against word choice or phrasing. But in practice anyone using RAG can tell you that that is not the case.
Iโm just a practitioner so my language might be imprecise but when I say similarly structured sentences what I mean is, and this is my interpretation based on my experience with using Agents and LLMs, that the shape of the context as in the phrasing and the word choice highly bias the outputs of LLMs.
In my own observations at work, those who interpret LLMs to be thinking often produce bad agents. LLM are not good at open ended questions, if you ask an LLM โimprove this codeโ you will often get bad results that just look passable. But if you interpret LLMs as probabilistic models highly biased by their context then you would add a lot more context and specific instructions in the prompt in order to get the Agent to produce the right output.
Side note, this is also why I like the AICI approach: https://github.com/microsoft/aici
-
You can find all the code involved in our NER system, including benchmarks, at github.com/devflowinc/trieve/tree/main/hallucination-detection.
-
Project mention: RefactAI: Use best-in-class LLMs for coding in your IDE | news.ycombinator.com | 2024-04-30
-
It is pretty good. I am working on an application that uses SVGs as a way to draw a workflow editor UI with Dioxus: https://github.com/floneum/floneum
-
-
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.
I find it misleading to use an f-string containing encoded `{CONTEXT}` <https://github.com/postgresml/korvus/blob/bce269a20a1dbea933...>, and after digging into TFM <https://postgresml.org/docs/open-source/korvus/guides/rag#si...> it seems in is not, in fact, an f-string artifact but rather the literal characters "{"+"CONTEXT"+"}" and are the same in all the language bindings?
IMHO it would be much clearer if you just used the normal %s for the "outer" string and left the implicit f-string syntax as it is, e.g.
{
-
-
To solve this, we built a native extension in Edge Runtime that enables using ONNX runtime via the Rust interface. This was made possible thanks to an excellent Rust wrapper called Ort:
-
ezkl
ezkl is an engine for doing inference for deep learning models and other computational graphs in a zk-snark (ZKML). Use it from Python, Javascript, or the command line.
Project mention: SP1: A performant, 100% open-source, contributor-friendly zkVM | news.ycombinator.com | 2024-12-08For those looking for applications outside crypto, this might also be interesting: https://docs.ezkl.xyz/
It's similar to Succinct but for proofs of ML models instead of RISCV. So you could generate a proof on some private data, on your computer or in a trusted environment, and submit the proof to show that you pass a fraud check without revealing any of your data.
-
-
Project mention: Show HN: MusicGPT โ An Open Source App for Generating Music with Local LLMs | news.ycombinator.com | 2024-05-23
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
Rust AI discussion
Rust AI related posts
-
Data Indexing and Common Challenges
-
[Open Source Project] Fresh Data For AI
-
Show HN: Fresh Data for AI
-
Open-Source ETL to prepare data for RAG ๐ฆ ๐
-
Ask HN: Air-Gapped Dev Environment?
-
My LLM codegen workflow ATM
-
Show HN: Transform Your Codebase into a Single Markdown Doc for Feeding into AI
-
A note from our sponsor - CodeRabbit
coderabbit.ai | 14 Mar 2025
Index
What are some of the best open-source AI projects in Rust? This list will help you:
# | Project | Stars |
---|---|---|
1 | ChatGPT | 53,647 |
2 | tabby | 30,394 |
3 | databend | 8,248 |
4 | postgresml | 6,188 |
5 | aichat | 5,927 |
6 | code2prompt | 5,002 |
7 | deepclaude | 4,710 |
8 | quadratic | 3,321 |
9 | text-embeddings-inference | 3,268 |
10 | tensorzero | 2,921 |
11 | lsp-ai | 2,561 |
12 | chat-ai-desktop | 2,007 |
13 | aici | 2,004 |
14 | trieve | 1,958 |
15 | refact | 1,779 |
16 | floneum | 1,769 |
17 | smartgpt | 1,759 |
18 | korvus | 1,340 |
19 | chidori | 1,308 |
20 | ort | 1,198 |
21 | ezkl | 1,039 |
22 | whatlang-rs | 997 |
23 | MusicGPT | 907 |