olafurjohannsson/kjarni
Native ML inference engine — embeddings, classification, reranking, search, and text generation. Rust core with C# bindings. No Python, no ONNX, no CUDA.
This tool helps software developers integrate pre-trained machine learning models directly into their applications or command-line workflows, without complex setups. It takes text input and produces classified labels (like positive/negative sentiment), numerical embeddings (vectors representing text), or ranked search results. The primary users are developers building desktop applications, command-line tools, or backend services in C# or Go who need to add AI capabilities.
Use this if you are a developer looking to add machine learning features like sentiment analysis, text classification, semantic search, or text embeddings to your C# or Go applications or CLI tools, requiring local, fast, and dependency-light execution.
Not ideal if you need to train custom machine learning models, require deep integration with Python's data science ecosystem, or are working with non-text data types like images or audio.
Stars
28
Forks
2
Language
Rust
License
Apache-2.0
Category
Last pushed
Feb 19, 2026
Monthly downloads
5
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/olafurjohannsson/kjarni"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Anush008/fastembed-rs
Rust library for vector embeddings and reranking.
huggingface/text-embeddings-inference
A blazing fast inference solution for text embeddings models
MinishLab/model2vec-rs
Official Rust Implementation of Model2Vec
finalfusion/finalfusion-rust
finalfusion embeddings in Rust
finalfusion/finalfusion-python
Finalfusion embeddings in Python