#
Starred repositories
Stream-Omni is a GPT-4o-like language-vision-speech chatbot that simultaneously supports interaction across various modality combinations.
Dingo: A Comprehensive AI Data Quality Evaluation Tool
A flexible, adaptive classification system for dynamic text classification
This is a library of the original sprites of pokemon Red/Blue, drawn in OpenSCAD using cubes as pixels.
A lightweight LMM-based Document Parsing Model
NVIDIA cuOpt is an open-source GPU-accelerated optimization engine delivering near real-time solutions for complex decision-making challenges.
Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.
Prompts for our Grok chat assistant and the `@grok` bot on X.
Open source multi-modal RAG for building AI apps over private knowledge.
Tools for merging pretrained large language models.
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA/Tensor Cores Kernels, HGEMM, FA-2 MMA.🎉
Community maintained hardware plugin for vLLM on Ascend
An agentic company research tool powered by LangGraph and Tavily that conducts deep diligence on companies using a multi-agent framework. It leverages Google's Gemini 2.0 Flash and OpenAI's GPT-4.1…
Initialize your favorite chatbot, then apply the response with a single click
Achieve your exclusive DeepResearch.
Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation
Realtime AI speech with OpenAI Realtime API and Gemini Live API on Arduino ESP32 with Secure Websockets and Deno edge functions with >15 minutes uninterrupted conversations globally for AI toys, AI…
A unified library for object tracking featuring clean room re-implementations of leading multi-object tracking algorithms
Build Real-Time Knowledge Graphs for AI Agents
An AI-powered task-management system you can drop into Cursor, Lovable, Windsurf, Roo, and others.
⚡ TabPFN: Foundation Model for Tabular Data ⚡
An AI-powered interactive avatar engine using Live2D, LLM, ASR, TTS, and RVC. Ideal for VTubing, streaming, and virtual assistant applications.
mcp-use is the easiest way to interact with mcp servers with custom agents