Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
💻 A fully functional local AWS cloud stack. Develop and test your cloud & Serverless apps offline
We write your reusable computer vision tools. 💜
LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
A language model programming library.
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
SOTA Open Source TTS
A PyTorch native platform for training generative AI models
🏡 Open source home automation that puts local control and privacy first.
WebApps in pure Python. No JavaScript, HTML and CSS needed
A high-performance, zero-overhead, extensible Python compiler with built-in NumPy support
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
Access a database of word frequencies, in various natural languages.
Build Real-Time Knowledge Graphs for AI Agents
aider is AI pair programming in your terminal
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
The definitive list that answers "I want to do X in Python, which tool should I use?"
Open source AI job application bot in Python: auto apply to jobs, with a tailored resume and cover letter for each posting.
Optimizing inference proxy for LLMs
real time face swap and one-click video deepfake with only a single image
[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment