kyr0's repositories
nes-ui-react
A design system that paints the web in 8 bits.
redaktool
Browser extension for editors and professionals engaged in text-related research, writing, and evaluation tasks. This tool serves as a comprehensive "AI toolbox" enabling direct interaction with content on any website for extraction, translation, summarization, re-phrasing and more.
vectorstore
In-browser, multi-lingual vector embedding and search
fast-dotproduct
dotProduct(vectorsA, vectorsB) / matmul in JIT-optimized JavaScript, WebAssembly/WASM using SIMD vector instructions. pthread, WebGPU, WebGL, WebNN experiments.
quality-prompts-js
Write Quality Prompts - TypeScript/JavaScript edition. Use and evaluate prompting techniques quickly.
easy-embeddings
Easy, fast and WASM/WebGPU accelerated vector embedding for the web platform. Locally and via API. Compatible with Browsers, Workers, Web Extensions, Node.js & co.
redaktool-website
Website of redaktool.ai
baguetter
Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, implementing, and testing new search methods. Baguetter supports sparse (traditional), dense (semantic), and hybrid retrieval methods.
GLiNER
Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024
langdetect-ts
Google langdetect for the web platform. Detects 55 languages of of the box. Minimum 1 sentence input for >90% accuracy.
liquiprompt
Simple but powerful prompt and RAG workflow templating language.
main
Automatized research at the touch of a button 👆
neo
The application worker driven frontend framework
onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
optillm
Optimizing inference proxy for LLMs
pico
Minimal CSS Framework for semantic HTML
raptorgpt-ost
Original Soundtrack of RaptorGPT - Call of the Hallucination
smartprompt
Template language for prompting text-to-* AI models. Supports variables, defaults, conditions, loops, meta data and safely compiles. Runs in all JS/TS environments.
transformer-explainer
Transformer Explained: Learn How LLM Transformer Models Work with Interactive Visualization
transformers.js
State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!
ts-expert-knowledge-base
Specific, up-to-date knowledge for LLM coding experts.
usearch
Fast Open-Source Search & Clustering engine × for Vectors & 🔜 Strings × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍
web-llm
High-performance In-browser LLM Inference Engine
Wiki-BM25-search
Calculate term specificity for a single doc with BM25 formula by using Wikipedia IDF