qpdf: A content-preserving PDF document transformer

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

Optimize prompts, code, and more with AI-powered Reflective Text Evolution

textlintプリセット：AIっぽい記述パターンを検出し、より自然な日本語表現を促すルール集

orval is able to generate client with appropriate type-signatures (TypeScript) from any valid OpenAPI v3 or Swagger v2 specification, either in yaml or json formats. 🍺

A CLI interface for Marp and Marpit based converters

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Browser and NodeJS Web Assembly audio decoder libraries that are highly optimized for size and performance.

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

Voice activity detector (VAD) for the browser with a simple API

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

End-to-end realtime stack for connecting humans and AI

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

A PixiJS plugin to display Live2D models of any kind (With lip-sync from audio)

A PixiJS plugin to display Live2D models of any kind.

AivisSpeech: AI Voice Imitation System - Text to Speech Software

📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

Python bindings for FFmpeg - with complex filtering support

Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

Code for explaining and evaluating late chunking (chunked pooling)

☁️ Build multimodal AI applications with cloud-native stack

Robust Speech Recognition via Large-Scale Weak Supervision

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

Deezer source separation library including pretrained models.

repository to research & share the machine learning articles

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search