Stars
Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥
highlight.io: The open source, full-stack monitoring platform. Error monitoring, session replay, logging, distributed tracing, and more.
Minimal PgBouncer image that is easy to configure
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Staging repo for development of native port of TypeScript
A data visualization and analytics component, especially well-suited for large and/or streaming datasets.
A FHIR® Server with internal, fast CQL Evaluation Engine
A Kubernetes deployable instance of GroundX for document parsing, storage, and search.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Async PHP client API for the telegram MTProto protocol
HunyuanVideo: A Systematic Framework For Large Video Generation Model
LLM-powered multiagent persona simulation for imagination enhancement and business insights.
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
This tutorial explains step by step how to connect your data to the Charting Library
A Git-compatible VCS that is both simple and powerful
Performant financial charts built with HTML5 canvas
DuckDB is an analytical in-process SQL database management system
A MLX port of FLUX based on the Huggingface Diffusers implementation.
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime