Stars
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Generate 3D objects conditioned on text or images
Instruct-tune LLaMA on consumer hardware
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/
Babylon.js is a powerful, beautiful, simple, and open game and rendering engine packed into a friendly JavaScript framework.
Examples and guides for using the OpenAI API
The OpenCog (hyper-)graph database and graph rewriting system
StableLM: Stability AI Language Models
Notebooks and various random fun
MiniLLM is a minimal system for running modern LLMs on consumer-grade GPUs
A markdown parser and compiler. Built for speed.
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
JavaScript framework for visual programming
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
MoonRay is an open-source, award-winning, state-of-the-art production path tracing renderer, initially developed at DreamWorks and an active member project of the Academy Software Foundation.
.NET library for the OpenAI service API by Betalgo Ranul
Instant neural graphics primitives: lightning fast NeRF and more
sketch + style = paints 🎨 (TOG2018/SIGGRAPH2018ASIA)
ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…