Production ready LLM model compression/quantization toolkit with accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang.

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/

A lightweight data processing framework built on DuckDB and 3FS.

adds Sequence Parallelism into LLaMA-Factory

Open-source vector similarity search for Postgres

Prefect is a workflow orchestration framework for building resilient data pipelines in Python.

draw.io

Synthetic Data SDK ✨

3D-printed open-source humanoid robot platform for sim-to-real and RL

Upsonic is a reliability-focused agent framework with dockerized, server-client architecture and MCP

Notebooks to demo the use of Azure AI Python SDK / LangChain with DeepSeek R1 reasoning model in Azure AI Foundry.

AdalFlow: The library to build & auto-optimize LLM applications.

Example project demonstrating how to use multimodal LLMs as a tool for PydanticAI applications

OGAI-RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Collection of handy online tools for developers, with great UX.

The open source Cursor for Designers. Design directly in your live React app and publish your changes to code.

Convert PDF to markdown + JSON quickly with high accuracy

A collection of examples that show how to use CrewAI framework to automate workflows.

Integrating AI into every workflow with our open-source, no-code platform, powered by the actor model for dynamic, graph-based solutions.

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

Customizable, AI-driven virtual assistant designed to streamline customer service operations, handle common inquiries, and improve overall user satisfaction through automated and contextually aware…

A React-based web app project that enables running Claude AI’s Artifacts either locally or on your own server.

Linux shell for iOS